mirror of
https://github.com/gryf/coach.git
synced 2025-12-18 03:30:19 +01:00
update of api docstrings across coach and tutorials [WIP] (#91)
* updating the documentation website * adding the built docs * update of api docstrings across coach and tutorials 0-2 * added some missing api documentation * New Sphinx based documentation
This commit is contained in:
Itai Caspi
695
docs/_modules/rl_coach/environments/carla_environment.html
Normal file
695
docs/_modules/rl_coach/environments/carla_environment.html
Normal file
@@ -0,0 +1,695 @@
|
||||
|
||||
|
||||
<!DOCTYPE html>
|
||||
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
|
||||
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
|
||||
<head>
|
||||
<meta charset="utf-8">
|
||||
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
|
||||
<title>rl_coach.environments.carla_environment — Reinforcement Learning Coach 0.11.0 documentation</title>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
|
||||
<link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
|
||||
<link rel="stylesheet" href="../../../_static/css/custom.css" type="text/css" />
|
||||
<link rel="index" title="Index" href="../../../genindex.html" />
|
||||
<link rel="search" title="Search" href="../../../search.html" />
|
||||
<link href="../../../_static/css/custom.css" rel="stylesheet" type="text/css">
|
||||
|
||||
|
||||
|
||||
<script src="../../../_static/js/modernizr.min.js"></script>
|
||||
|
||||
</head>
|
||||
|
||||
<body class="wy-body-for-nav">
|
||||
|
||||
|
||||
<div class="wy-grid-for-nav">
|
||||
|
||||
|
||||
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
|
||||
<div class="wy-side-scroll">
|
||||
<div class="wy-side-nav-search">
|
||||
|
||||
|
||||
|
||||
<a href="../../../index.html" class="icon icon-home"> Reinforcement Learning Coach
|
||||
|
||||
|
||||
|
||||
|
||||
<img src="../../../_static/dark_logo.png" class="logo" alt="Logo"/>
|
||||
|
||||
</a>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<div role="search">
|
||||
<form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get">
|
||||
<input type="text" name="q" placeholder="Search docs" />
|
||||
<input type="hidden" name="check_keywords" value="yes" />
|
||||
<input type="hidden" name="area" value="default" />
|
||||
</form>
|
||||
</div>
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<p class="caption"><span class="caption-text">Intro</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../usage.html">Usage</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../features/index.html">Features</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../selecting_an_algorithm.html">Selecting an Algorithm</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../dashboard.html">Coach Dashboard</a></li>
|
||||
</ul>
|
||||
<p class="caption"><span class="caption-text">Design</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../design/control_flow.html">Control Flow</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../design/network.html">Network Design</a></li>
|
||||
</ul>
|
||||
<p class="caption"><span class="caption-text">Contributing</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../contributing/add_agent.html">Adding a New Agent</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../contributing/add_env.html">Adding a New Environment</a></li>
|
||||
</ul>
|
||||
<p class="caption"><span class="caption-text">Components</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/agents/index.html">Agents</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/architectures/index.html">Architectures</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/environments/index.html">Environments</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/exploration_policies/index.html">Exploration Policies</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/filters/index.html">Filters</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/memories/index.html">Memories</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/core_types.html">Core Types</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/spaces.html">Spaces</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/additional_parameters.html">Additional Parameters</a></li>
|
||||
</ul>
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
</nav>
|
||||
|
||||
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
|
||||
|
||||
|
||||
<nav class="wy-nav-top" aria-label="top navigation">
|
||||
|
||||
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
|
||||
<a href="../../../index.html">Reinforcement Learning Coach</a>
|
||||
|
||||
</nav>
|
||||
|
||||
|
||||
<div class="wy-nav-content">
|
||||
|
||||
<div class="rst-content">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<div role="navigation" aria-label="breadcrumbs navigation">
|
||||
|
||||
<ul class="wy-breadcrumbs">
|
||||
|
||||
<li><a href="../../../index.html">Docs</a> »</li>
|
||||
|
||||
<li><a href="../../index.html">Module code</a> »</li>
|
||||
|
||||
<li>rl_coach.environments.carla_environment</li>
|
||||
|
||||
|
||||
<li class="wy-breadcrumbs-aside">
|
||||
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
|
||||
|
||||
<hr/>
|
||||
</div>
|
||||
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
|
||||
<div itemprop="articleBody">
|
||||
|
||||
<h1>Source code for rl_coach.environments.carla_environment</h1><div class="highlight"><pre>
|
||||
<span></span><span class="c1">#</span>
|
||||
<span class="c1"># Copyright (c) 2017 Intel Corporation</span>
|
||||
<span class="c1">#</span>
|
||||
<span class="c1"># Licensed under the Apache License, Version 2.0 (the "License");</span>
|
||||
<span class="c1"># you may not use this file except in compliance with the License.</span>
|
||||
<span class="c1"># You may obtain a copy of the License at</span>
|
||||
<span class="c1">#</span>
|
||||
<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
|
||||
<span class="c1">#</span>
|
||||
<span class="c1"># Unless required by applicable law or agreed to in writing, software</span>
|
||||
<span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span>
|
||||
<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
|
||||
<span class="c1"># See the License for the specific language governing permissions and</span>
|
||||
<span class="c1"># limitations under the License.</span>
|
||||
<span class="c1">#</span>
|
||||
|
||||
<span class="kn">import</span> <span class="nn">random</span>
|
||||
<span class="kn">import</span> <span class="nn">sys</span>
|
||||
<span class="kn">from</span> <span class="nn">os</span> <span class="k">import</span> <span class="n">path</span><span class="p">,</span> <span class="n">environ</span>
|
||||
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.logger</span> <span class="k">import</span> <span class="n">screen</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.filters.action.partial_discrete_action_space_map</span> <span class="k">import</span> <span class="n">PartialDiscreteActionSpaceMap</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.filters.observation.observation_rgb_to_y_filter</span> <span class="k">import</span> <span class="n">ObservationRGBToYFilter</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.filters.observation.observation_to_uint8_filter</span> <span class="k">import</span> <span class="n">ObservationToUInt8Filter</span>
|
||||
|
||||
<span class="k">try</span><span class="p">:</span>
|
||||
<span class="k">if</span> <span class="s1">'CARLA_ROOT'</span> <span class="ow">in</span> <span class="n">environ</span><span class="p">:</span>
|
||||
<span class="n">sys</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">environ</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'CARLA_ROOT'</span><span class="p">),</span> <span class="s1">'PythonClient'</span><span class="p">))</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="n">screen</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="s2">"CARLA_ROOT was not defined. Please set it to point to the CARLA root directory and try again."</span><span class="p">)</span>
|
||||
<span class="kn">from</span> <span class="nn">carla.client</span> <span class="k">import</span> <span class="n">CarlaClient</span>
|
||||
<span class="kn">from</span> <span class="nn">carla.settings</span> <span class="k">import</span> <span class="n">CarlaSettings</span>
|
||||
<span class="kn">from</span> <span class="nn">carla.tcp</span> <span class="k">import</span> <span class="n">TCPConnectionError</span>
|
||||
<span class="kn">from</span> <span class="nn">carla.sensor</span> <span class="k">import</span> <span class="n">Camera</span>
|
||||
<span class="kn">from</span> <span class="nn">carla.client</span> <span class="k">import</span> <span class="n">VehicleControl</span>
|
||||
<span class="kn">from</span> <span class="nn">carla.planner.planner</span> <span class="k">import</span> <span class="n">Planner</span>
|
||||
<span class="kn">from</span> <span class="nn">carla.driving_benchmark.experiment_suites.experiment_suite</span> <span class="k">import</span> <span class="n">ExperimentSuite</span>
|
||||
<span class="k">except</span> <span class="ne">ImportError</span><span class="p">:</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.logger</span> <span class="k">import</span> <span class="n">failed_imports</span>
|
||||
<span class="n">failed_imports</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s2">"CARLA"</span><span class="p">)</span>
|
||||
|
||||
<span class="kn">import</span> <span class="nn">logging</span>
|
||||
<span class="kn">import</span> <span class="nn">subprocess</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.environments.environment</span> <span class="k">import</span> <span class="n">Environment</span><span class="p">,</span> <span class="n">EnvironmentParameters</span><span class="p">,</span> <span class="n">LevelSelection</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.spaces</span> <span class="k">import</span> <span class="n">BoxActionSpace</span><span class="p">,</span> <span class="n">ImageObservationSpace</span><span class="p">,</span> <span class="n">StateSpace</span><span class="p">,</span> \
|
||||
<span class="n">VectorObservationSpace</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.utils</span> <span class="k">import</span> <span class="n">get_open_port</span><span class="p">,</span> <span class="n">force_list</span>
|
||||
<span class="kn">from</span> <span class="nn">enum</span> <span class="k">import</span> <span class="n">Enum</span>
|
||||
<span class="kn">import</span> <span class="nn">os</span>
|
||||
<span class="kn">import</span> <span class="nn">signal</span>
|
||||
<span class="kn">from</span> <span class="nn">typing</span> <span class="k">import</span> <span class="n">List</span><span class="p">,</span> <span class="n">Union</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.base_parameters</span> <span class="k">import</span> <span class="n">VisualizationParameters</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.filters.filter</span> <span class="k">import</span> <span class="n">InputFilter</span><span class="p">,</span> <span class="n">NoOutputFilter</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.filters.observation.observation_rescale_to_size_filter</span> <span class="k">import</span> <span class="n">ObservationRescaleToSizeFilter</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.filters.observation.observation_stacking_filter</span> <span class="k">import</span> <span class="n">ObservationStackingFilter</span>
|
||||
<span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
|
||||
|
||||
|
||||
<span class="c1"># enum of the available levels and their path</span>
|
||||
<span class="k">class</span> <span class="nc">CarlaLevel</span><span class="p">(</span><span class="n">Enum</span><span class="p">):</span>
|
||||
<span class="n">TOWN1</span> <span class="o">=</span> <span class="p">{</span><span class="s2">"map_name"</span><span class="p">:</span> <span class="s2">"Town01"</span><span class="p">,</span> <span class="s2">"map_path"</span><span class="p">:</span> <span class="s2">"/Game/Maps/Town01"</span><span class="p">}</span>
|
||||
<span class="n">TOWN2</span> <span class="o">=</span> <span class="p">{</span><span class="s2">"map_name"</span><span class="p">:</span> <span class="s2">"Town02"</span><span class="p">,</span> <span class="s2">"map_path"</span><span class="p">:</span> <span class="s2">"/Game/Maps/Town02"</span><span class="p">}</span>
|
||||
|
||||
<span class="n">key_map</span> <span class="o">=</span> <span class="p">{</span>
|
||||
<span class="s1">'BRAKE'</span><span class="p">:</span> <span class="p">(</span><span class="mi">274</span><span class="p">,),</span> <span class="c1"># down arrow</span>
|
||||
<span class="s1">'GAS'</span><span class="p">:</span> <span class="p">(</span><span class="mi">273</span><span class="p">,),</span> <span class="c1"># up arrow</span>
|
||||
<span class="s1">'TURN_LEFT'</span><span class="p">:</span> <span class="p">(</span><span class="mi">276</span><span class="p">,),</span> <span class="c1"># left arrow</span>
|
||||
<span class="s1">'TURN_RIGHT'</span><span class="p">:</span> <span class="p">(</span><span class="mi">275</span><span class="p">,),</span> <span class="c1"># right arrow</span>
|
||||
<span class="s1">'GAS_AND_TURN_LEFT'</span><span class="p">:</span> <span class="p">(</span><span class="mi">273</span><span class="p">,</span> <span class="mi">276</span><span class="p">),</span>
|
||||
<span class="s1">'GAS_AND_TURN_RIGHT'</span><span class="p">:</span> <span class="p">(</span><span class="mi">273</span><span class="p">,</span> <span class="mi">275</span><span class="p">),</span>
|
||||
<span class="s1">'BRAKE_AND_TURN_LEFT'</span><span class="p">:</span> <span class="p">(</span><span class="mi">274</span><span class="p">,</span> <span class="mi">276</span><span class="p">),</span>
|
||||
<span class="s1">'BRAKE_AND_TURN_RIGHT'</span><span class="p">:</span> <span class="p">(</span><span class="mi">274</span><span class="p">,</span> <span class="mi">275</span><span class="p">),</span>
|
||||
<span class="p">}</span>
|
||||
|
||||
<span class="n">CarlaInputFilter</span> <span class="o">=</span> <span class="n">InputFilter</span><span class="p">(</span><span class="n">is_a_reference_filter</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||||
<span class="n">CarlaInputFilter</span><span class="o">.</span><span class="n">add_observation_filter</span><span class="p">(</span><span class="s1">'forward_camera'</span><span class="p">,</span> <span class="s1">'rescaling'</span><span class="p">,</span>
|
||||
<span class="n">ObservationRescaleToSizeFilter</span><span class="p">(</span><span class="n">ImageObservationSpace</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="mi">128</span><span class="p">,</span> <span class="mi">180</span><span class="p">,</span> <span class="mi">3</span><span class="p">]),</span>
|
||||
<span class="n">high</span><span class="o">=</span><span class="mi">255</span><span class="p">)))</span>
|
||||
<span class="n">CarlaInputFilter</span><span class="o">.</span><span class="n">add_observation_filter</span><span class="p">(</span><span class="s1">'forward_camera'</span><span class="p">,</span> <span class="s1">'to_grayscale'</span><span class="p">,</span> <span class="n">ObservationRGBToYFilter</span><span class="p">())</span>
|
||||
<span class="n">CarlaInputFilter</span><span class="o">.</span><span class="n">add_observation_filter</span><span class="p">(</span><span class="s1">'forward_camera'</span><span class="p">,</span> <span class="s1">'to_uint8'</span><span class="p">,</span> <span class="n">ObservationToUInt8Filter</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">255</span><span class="p">))</span>
|
||||
<span class="n">CarlaInputFilter</span><span class="o">.</span><span class="n">add_observation_filter</span><span class="p">(</span><span class="s1">'forward_camera'</span><span class="p">,</span> <span class="s1">'stacking'</span><span class="p">,</span> <span class="n">ObservationStackingFilter</span><span class="p">(</span><span class="mi">4</span><span class="p">))</span>
|
||||
|
||||
<span class="n">CarlaOutputFilter</span> <span class="o">=</span> <span class="n">NoOutputFilter</span><span class="p">()</span>
|
||||
|
||||
|
||||
<span class="k">class</span> <span class="nc">CameraTypes</span><span class="p">(</span><span class="n">Enum</span><span class="p">):</span>
|
||||
<span class="n">FRONT</span> <span class="o">=</span> <span class="s2">"forward_camera"</span>
|
||||
<span class="n">LEFT</span> <span class="o">=</span> <span class="s2">"left_camera"</span>
|
||||
<span class="n">RIGHT</span> <span class="o">=</span> <span class="s2">"right_camera"</span>
|
||||
<span class="n">SEGMENTATION</span> <span class="o">=</span> <span class="s2">"segmentation"</span>
|
||||
<span class="n">DEPTH</span> <span class="o">=</span> <span class="s2">"depth"</span>
|
||||
<span class="n">LIDAR</span> <span class="o">=</span> <span class="s2">"lidar"</span>
|
||||
|
||||
|
||||
<span class="k">class</span> <span class="nc">CarlaEnvironmentParameters</span><span class="p">(</span><span class="n">EnvironmentParameters</span><span class="p">):</span>
|
||||
<span class="k">class</span> <span class="nc">Quality</span><span class="p">(</span><span class="n">Enum</span><span class="p">):</span>
|
||||
<span class="n">LOW</span> <span class="o">=</span> <span class="s2">"Low"</span>
|
||||
<span class="n">EPIC</span> <span class="o">=</span> <span class="s2">"Epic"</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">level</span><span class="o">=</span><span class="s2">"town1"</span><span class="p">):</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">level</span><span class="o">=</span><span class="n">level</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">frame_skip</span> <span class="o">=</span> <span class="mi">3</span> <span class="c1"># the frame skip affects the fps of the server directly. fps = 30 / frameskip</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">server_height</span> <span class="o">=</span> <span class="mi">512</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">server_width</span> <span class="o">=</span> <span class="mi">720</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">camera_height</span> <span class="o">=</span> <span class="mi">128</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">camera_width</span> <span class="o">=</span> <span class="mi">180</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">experiment_suite</span> <span class="o">=</span> <span class="kc">None</span> <span class="c1"># an optional CARLA experiment suite to use</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">config</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">level</span> <span class="o">=</span> <span class="n">level</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">quality</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">Quality</span><span class="o">.</span><span class="n">LOW</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">cameras</span> <span class="o">=</span> <span class="p">[</span><span class="n">CameraTypes</span><span class="o">.</span><span class="n">FRONT</span><span class="p">]</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">weather_id</span> <span class="o">=</span> <span class="p">[</span><span class="mi">1</span><span class="p">]</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">verbose</span> <span class="o">=</span> <span class="kc">True</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">episode_max_time</span> <span class="o">=</span> <span class="mi">100000</span> <span class="c1"># miliseconds for each episode</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">allow_braking</span> <span class="o">=</span> <span class="kc">False</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">separate_actions_for_throttle_and_brake</span> <span class="o">=</span> <span class="kc">False</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">num_speedup_steps</span> <span class="o">=</span> <span class="mi">30</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">max_speed</span> <span class="o">=</span> <span class="mf">35.0</span> <span class="c1"># km/h</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">default_input_filter</span> <span class="o">=</span> <span class="n">CarlaInputFilter</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">default_output_filter</span> <span class="o">=</span> <span class="n">CarlaOutputFilter</span>
|
||||
|
||||
<span class="nd">@property</span>
|
||||
<span class="k">def</span> <span class="nf">path</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="k">return</span> <span class="s1">'rl_coach.environments.carla_environment:CarlaEnvironment'</span>
|
||||
|
||||
|
||||
<div class="viewcode-block" id="CarlaEnvironment"><a class="viewcode-back" href="../../../components/environments/index.html#rl_coach.environments.carla_environment.CarlaEnvironment">[docs]</a><span class="k">class</span> <span class="nc">CarlaEnvironment</span><span class="p">(</span><span class="n">Environment</span><span class="p">):</span>
|
||||
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">level</span><span class="p">:</span> <span class="n">LevelSelection</span><span class="p">,</span>
|
||||
<span class="n">seed</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">frame_skip</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">human_control</span><span class="p">:</span> <span class="nb">bool</span><span class="p">,</span> <span class="n">custom_reward_threshold</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">],</span>
|
||||
<span class="n">visualization_parameters</span><span class="p">:</span> <span class="n">VisualizationParameters</span><span class="p">,</span>
|
||||
<span class="n">server_height</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">server_width</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">camera_height</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">camera_width</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
|
||||
<span class="n">verbose</span><span class="p">:</span> <span class="nb">bool</span><span class="p">,</span> <span class="n">experiment_suite</span><span class="p">:</span> <span class="n">ExperimentSuite</span><span class="p">,</span> <span class="n">config</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">episode_max_time</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
|
||||
<span class="n">allow_braking</span><span class="p">:</span> <span class="nb">bool</span><span class="p">,</span> <span class="n">quality</span><span class="p">:</span> <span class="n">CarlaEnvironmentParameters</span><span class="o">.</span><span class="n">Quality</span><span class="p">,</span>
|
||||
<span class="n">cameras</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="n">CameraTypes</span><span class="p">],</span> <span class="n">weather_id</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="nb">int</span><span class="p">],</span> <span class="n">experiment_path</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
|
||||
<span class="n">separate_actions_for_throttle_and_brake</span><span class="p">:</span> <span class="nb">bool</span><span class="p">,</span>
|
||||
<span class="n">num_speedup_steps</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">max_speed</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span> <span class="n">target_success_rate</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.0</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">level</span><span class="p">,</span> <span class="n">seed</span><span class="p">,</span> <span class="n">frame_skip</span><span class="p">,</span> <span class="n">human_control</span><span class="p">,</span> <span class="n">custom_reward_threshold</span><span class="p">,</span> <span class="n">visualization_parameters</span><span class="p">,</span> <span class="n">target_success_rate</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># server configuration</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">server_height</span> <span class="o">=</span> <span class="n">server_height</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">server_width</span> <span class="o">=</span> <span class="n">server_width</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">port</span> <span class="o">=</span> <span class="n">get_open_port</span><span class="p">()</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">host</span> <span class="o">=</span> <span class="s1">'localhost'</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">map_name</span> <span class="o">=</span> <span class="n">CarlaLevel</span><span class="p">[</span><span class="n">level</span><span class="o">.</span><span class="n">upper</span><span class="p">()]</span><span class="o">.</span><span class="n">value</span><span class="p">[</span><span class="s1">'map_name'</span><span class="p">]</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">map_path</span> <span class="o">=</span> <span class="n">CarlaLevel</span><span class="p">[</span><span class="n">level</span><span class="o">.</span><span class="n">upper</span><span class="p">()]</span><span class="o">.</span><span class="n">value</span><span class="p">[</span><span class="s1">'map_path'</span><span class="p">]</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">experiment_path</span> <span class="o">=</span> <span class="n">experiment_path</span>
|
||||
|
||||
<span class="c1"># client configuration</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">verbose</span> <span class="o">=</span> <span class="n">verbose</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">quality</span> <span class="o">=</span> <span class="n">quality</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">cameras</span> <span class="o">=</span> <span class="n">cameras</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">weather_id</span> <span class="o">=</span> <span class="n">weather_id</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">episode_max_time</span> <span class="o">=</span> <span class="n">episode_max_time</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">allow_braking</span> <span class="o">=</span> <span class="n">allow_braking</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">separate_actions_for_throttle_and_brake</span> <span class="o">=</span> <span class="n">separate_actions_for_throttle_and_brake</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">camera_width</span> <span class="o">=</span> <span class="n">camera_width</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">camera_height</span> <span class="o">=</span> <span class="n">camera_height</span>
|
||||
|
||||
<span class="c1"># setup server settings</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">experiment_suite</span> <span class="o">=</span> <span class="n">experiment_suite</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">config</span> <span class="o">=</span> <span class="n">config</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="p">:</span>
|
||||
<span class="c1"># load settings from file</span>
|
||||
<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="p">,</span> <span class="s1">'r'</span><span class="p">)</span> <span class="k">as</span> <span class="n">fp</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">settings</span> <span class="o">=</span> <span class="n">fp</span><span class="o">.</span><span class="n">read</span><span class="p">()</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="c1"># hard coded settings</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">settings</span> <span class="o">=</span> <span class="n">CarlaSettings</span><span class="p">()</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">settings</span><span class="o">.</span><span class="n">set</span><span class="p">(</span>
|
||||
<span class="n">SynchronousMode</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
|
||||
<span class="n">SendNonPlayerAgentsInfo</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||||
<span class="n">NumberOfVehicles</span><span class="o">=</span><span class="mi">15</span><span class="p">,</span>
|
||||
<span class="n">NumberOfPedestrians</span><span class="o">=</span><span class="mi">30</span><span class="p">,</span>
|
||||
<span class="n">WeatherId</span><span class="o">=</span><span class="n">random</span><span class="o">.</span><span class="n">choice</span><span class="p">(</span><span class="n">force_list</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">weather_id</span><span class="p">)),</span>
|
||||
<span class="n">QualityLevel</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">quality</span><span class="o">.</span><span class="n">value</span><span class="p">,</span>
|
||||
<span class="n">SeedVehicles</span><span class="o">=</span><span class="n">seed</span><span class="p">,</span>
|
||||
<span class="n">SeedPedestrians</span><span class="o">=</span><span class="n">seed</span><span class="p">)</span>
|
||||
<span class="k">if</span> <span class="n">seed</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">settings</span><span class="o">.</span><span class="n">randomize_seeds</span><span class="p">()</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">settings</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_add_cameras</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">settings</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">cameras</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">camera_width</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">camera_height</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># open the server</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">server</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_open_server</span><span class="p">()</span>
|
||||
|
||||
<span class="n">logging</span><span class="o">.</span><span class="n">disable</span><span class="p">(</span><span class="mi">40</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># open the client</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">game</span> <span class="o">=</span> <span class="n">CarlaClient</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">host</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">port</span><span class="p">,</span> <span class="n">timeout</span><span class="o">=</span><span class="mi">99999999</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="o">.</span><span class="n">connect</span><span class="p">()</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">experiment_suite</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">current_experiment_idx</span> <span class="o">=</span> <span class="mi">0</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">current_experiment</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">experiment_suite</span><span class="o">.</span><span class="n">get_experiments</span><span class="p">()[</span><span class="bp">self</span><span class="o">.</span><span class="n">current_experiment_idx</span><span class="p">]</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">scene</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="o">.</span><span class="n">load_settings</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">current_experiment</span><span class="o">.</span><span class="n">conditions</span><span class="p">)</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">scene</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="o">.</span><span class="n">load_settings</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">settings</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># get available start positions</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">positions</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">scene</span><span class="o">.</span><span class="n">player_start_spots</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">num_positions</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">positions</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">current_start_position_idx</span> <span class="o">=</span> <span class="mi">0</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">current_pose</span> <span class="o">=</span> <span class="mi">0</span>
|
||||
|
||||
<span class="c1"># state space</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">state_space</span> <span class="o">=</span> <span class="n">StateSpace</span><span class="p">({</span>
|
||||
<span class="s2">"measurements"</span><span class="p">:</span> <span class="n">VectorObservationSpace</span><span class="p">(</span><span class="mi">4</span><span class="p">,</span> <span class="n">measurements_names</span><span class="o">=</span><span class="p">[</span><span class="s2">"forward_speed"</span><span class="p">,</span> <span class="s2">"x"</span><span class="p">,</span> <span class="s2">"y"</span><span class="p">,</span> <span class="s2">"z"</span><span class="p">])</span>
|
||||
<span class="p">})</span>
|
||||
<span class="k">for</span> <span class="n">camera</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">scene</span><span class="o">.</span><span class="n">sensors</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">state_space</span><span class="p">[</span><span class="n">camera</span><span class="o">.</span><span class="n">name</span><span class="p">]</span> <span class="o">=</span> <span class="n">ImageObservationSpace</span><span class="p">(</span>
|
||||
<span class="n">shape</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="bp">self</span><span class="o">.</span><span class="n">camera_height</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">camera_width</span><span class="p">,</span> <span class="mi">3</span><span class="p">]),</span>
|
||||
<span class="n">high</span><span class="o">=</span><span class="mi">255</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># action space</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">separate_actions_for_throttle_and_brake</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">action_space</span> <span class="o">=</span> <span class="n">BoxActionSpace</span><span class="p">(</span><span class="n">shape</span><span class="o">=</span><span class="mi">3</span><span class="p">,</span> <span class="n">low</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">]),</span> <span class="n">high</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">]),</span>
|
||||
<span class="n">descriptions</span><span class="o">=</span><span class="p">[</span><span class="s2">"steer"</span><span class="p">,</span> <span class="s2">"gas"</span><span class="p">,</span> <span class="s2">"brake"</span><span class="p">])</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">action_space</span> <span class="o">=</span> <span class="n">BoxActionSpace</span><span class="p">(</span><span class="n">shape</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">low</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="o">-</span><span class="mi">1</span><span class="p">]),</span> <span class="n">high</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">]),</span>
|
||||
<span class="n">descriptions</span><span class="o">=</span><span class="p">[</span><span class="s2">"steer"</span><span class="p">,</span> <span class="s2">"gas_and_brake"</span><span class="p">])</span>
|
||||
|
||||
<span class="c1"># human control</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">human_control</span><span class="p">:</span>
|
||||
<span class="c1"># convert continuous action space to discrete</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">steering_strength</span> <span class="o">=</span> <span class="mf">0.5</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">gas_strength</span> <span class="o">=</span> <span class="mf">1.0</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">brake_strength</span> <span class="o">=</span> <span class="mf">0.5</span>
|
||||
<span class="c1"># TODO: reverse order of actions</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">action_space</span> <span class="o">=</span> <span class="n">PartialDiscreteActionSpaceMap</span><span class="p">(</span>
|
||||
<span class="n">target_actions</span><span class="o">=</span><span class="p">[[</span><span class="mf">0.</span><span class="p">,</span> <span class="mf">0.</span><span class="p">],</span>
|
||||
<span class="p">[</span><span class="mf">0.</span><span class="p">,</span> <span class="o">-</span><span class="bp">self</span><span class="o">.</span><span class="n">steering_strength</span><span class="p">],</span>
|
||||
<span class="p">[</span><span class="mf">0.</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">steering_strength</span><span class="p">],</span>
|
||||
<span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">gas_strength</span><span class="p">,</span> <span class="mf">0.</span><span class="p">],</span>
|
||||
<span class="p">[</span><span class="o">-</span><span class="bp">self</span><span class="o">.</span><span class="n">brake_strength</span><span class="p">,</span> <span class="mi">0</span><span class="p">],</span>
|
||||
<span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">gas_strength</span><span class="p">,</span> <span class="o">-</span><span class="bp">self</span><span class="o">.</span><span class="n">steering_strength</span><span class="p">],</span>
|
||||
<span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">gas_strength</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">steering_strength</span><span class="p">],</span>
|
||||
<span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">brake_strength</span><span class="p">,</span> <span class="o">-</span><span class="bp">self</span><span class="o">.</span><span class="n">steering_strength</span><span class="p">],</span>
|
||||
<span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">brake_strength</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">steering_strength</span><span class="p">]],</span>
|
||||
<span class="n">descriptions</span><span class="o">=</span><span class="p">[</span><span class="s1">'NO-OP'</span><span class="p">,</span> <span class="s1">'TURN_LEFT'</span><span class="p">,</span> <span class="s1">'TURN_RIGHT'</span><span class="p">,</span> <span class="s1">'GAS'</span><span class="p">,</span> <span class="s1">'BRAKE'</span><span class="p">,</span>
|
||||
<span class="s1">'GAS_AND_TURN_LEFT'</span><span class="p">,</span> <span class="s1">'GAS_AND_TURN_RIGHT'</span><span class="p">,</span>
|
||||
<span class="s1">'BRAKE_AND_TURN_LEFT'</span><span class="p">,</span> <span class="s1">'BRAKE_AND_TURN_RIGHT'</span><span class="p">]</span>
|
||||
<span class="p">)</span>
|
||||
|
||||
<span class="c1"># map keyboard keys to actions</span>
|
||||
<span class="k">for</span> <span class="n">idx</span><span class="p">,</span> <span class="n">action</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">action_space</span><span class="o">.</span><span class="n">descriptions</span><span class="p">):</span>
|
||||
<span class="k">for</span> <span class="n">key</span> <span class="ow">in</span> <span class="n">key_map</span><span class="o">.</span><span class="n">keys</span><span class="p">():</span>
|
||||
<span class="k">if</span> <span class="n">action</span> <span class="o">==</span> <span class="n">key</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">key_to_action</span><span class="p">[</span><span class="n">key_map</span><span class="p">[</span><span class="n">key</span><span class="p">]]</span> <span class="o">=</span> <span class="n">idx</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">num_speedup_steps</span> <span class="o">=</span> <span class="n">num_speedup_steps</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">max_speed</span> <span class="o">=</span> <span class="n">max_speed</span>
|
||||
|
||||
<span class="c1"># measurements</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">autopilot</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">planner</span> <span class="o">=</span> <span class="n">Planner</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">map_name</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># env initialization</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reset_internal_state</span><span class="p">(</span><span class="kc">True</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># render</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_rendered</span><span class="p">:</span>
|
||||
<span class="n">image</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_rendered_image</span><span class="p">()</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">renderer</span><span class="o">.</span><span class="n">create_screen</span><span class="p">(</span><span class="n">image</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n">image</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">target_success_rate</span> <span class="o">=</span> <span class="n">target_success_rate</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_add_cameras</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">settings</span><span class="p">,</span> <span class="n">cameras</span><span class="p">,</span> <span class="n">camera_width</span><span class="p">,</span> <span class="n">camera_height</span><span class="p">):</span>
|
||||
<span class="c1"># add a front facing camera</span>
|
||||
<span class="k">if</span> <span class="n">CameraTypes</span><span class="o">.</span><span class="n">FRONT</span> <span class="ow">in</span> <span class="n">cameras</span><span class="p">:</span>
|
||||
<span class="n">camera</span> <span class="o">=</span> <span class="n">Camera</span><span class="p">(</span><span class="n">CameraTypes</span><span class="o">.</span><span class="n">FRONT</span><span class="o">.</span><span class="n">value</span><span class="p">)</span>
|
||||
<span class="n">camera</span><span class="o">.</span><span class="n">set</span><span class="p">(</span><span class="n">FOV</span><span class="o">=</span><span class="mi">100</span><span class="p">)</span>
|
||||
<span class="n">camera</span><span class="o">.</span><span class="n">set_image_size</span><span class="p">(</span><span class="n">camera_width</span><span class="p">,</span> <span class="n">camera_height</span><span class="p">)</span>
|
||||
<span class="n">camera</span><span class="o">.</span><span class="n">set_position</span><span class="p">(</span><span class="mf">2.0</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mf">1.4</span><span class="p">)</span>
|
||||
<span class="n">camera</span><span class="o">.</span><span class="n">set_rotation</span><span class="p">(</span><span class="o">-</span><span class="mf">15.0</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span>
|
||||
<span class="n">settings</span><span class="o">.</span><span class="n">add_sensor</span><span class="p">(</span><span class="n">camera</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># add a left facing camera</span>
|
||||
<span class="k">if</span> <span class="n">CameraTypes</span><span class="o">.</span><span class="n">LEFT</span> <span class="ow">in</span> <span class="n">cameras</span><span class="p">:</span>
|
||||
<span class="n">camera</span> <span class="o">=</span> <span class="n">Camera</span><span class="p">(</span><span class="n">CameraTypes</span><span class="o">.</span><span class="n">LEFT</span><span class="o">.</span><span class="n">value</span><span class="p">)</span>
|
||||
<span class="n">camera</span><span class="o">.</span><span class="n">set</span><span class="p">(</span><span class="n">FOV</span><span class="o">=</span><span class="mi">100</span><span class="p">)</span>
|
||||
<span class="n">camera</span><span class="o">.</span><span class="n">set_image_size</span><span class="p">(</span><span class="n">camera_width</span><span class="p">,</span> <span class="n">camera_height</span><span class="p">)</span>
|
||||
<span class="n">camera</span><span class="o">.</span><span class="n">set_position</span><span class="p">(</span><span class="mf">2.0</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mf">1.4</span><span class="p">)</span>
|
||||
<span class="n">camera</span><span class="o">.</span><span class="n">set_rotation</span><span class="p">(</span><span class="o">-</span><span class="mf">15.0</span><span class="p">,</span> <span class="o">-</span><span class="mi">30</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span>
|
||||
<span class="n">settings</span><span class="o">.</span><span class="n">add_sensor</span><span class="p">(</span><span class="n">camera</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># add a right facing camera</span>
|
||||
<span class="k">if</span> <span class="n">CameraTypes</span><span class="o">.</span><span class="n">RIGHT</span> <span class="ow">in</span> <span class="n">cameras</span><span class="p">:</span>
|
||||
<span class="n">camera</span> <span class="o">=</span> <span class="n">Camera</span><span class="p">(</span><span class="n">CameraTypes</span><span class="o">.</span><span class="n">RIGHT</span><span class="o">.</span><span class="n">value</span><span class="p">)</span>
|
||||
<span class="n">camera</span><span class="o">.</span><span class="n">set</span><span class="p">(</span><span class="n">FOV</span><span class="o">=</span><span class="mi">100</span><span class="p">)</span>
|
||||
<span class="n">camera</span><span class="o">.</span><span class="n">set_image_size</span><span class="p">(</span><span class="n">camera_width</span><span class="p">,</span> <span class="n">camera_height</span><span class="p">)</span>
|
||||
<span class="n">camera</span><span class="o">.</span><span class="n">set_position</span><span class="p">(</span><span class="mf">2.0</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mf">1.4</span><span class="p">)</span>
|
||||
<span class="n">camera</span><span class="o">.</span><span class="n">set_rotation</span><span class="p">(</span><span class="o">-</span><span class="mf">15.0</span><span class="p">,</span> <span class="mi">30</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span>
|
||||
<span class="n">settings</span><span class="o">.</span><span class="n">add_sensor</span><span class="p">(</span><span class="n">camera</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># add a front facing depth camera</span>
|
||||
<span class="k">if</span> <span class="n">CameraTypes</span><span class="o">.</span><span class="n">DEPTH</span> <span class="ow">in</span> <span class="n">cameras</span><span class="p">:</span>
|
||||
<span class="n">camera</span> <span class="o">=</span> <span class="n">Camera</span><span class="p">(</span><span class="n">CameraTypes</span><span class="o">.</span><span class="n">DEPTH</span><span class="o">.</span><span class="n">value</span><span class="p">)</span>
|
||||
<span class="n">camera</span><span class="o">.</span><span class="n">set_image_size</span><span class="p">(</span><span class="n">camera_width</span><span class="p">,</span> <span class="n">camera_height</span><span class="p">)</span>
|
||||
<span class="n">camera</span><span class="o">.</span><span class="n">set_position</span><span class="p">(</span><span class="mf">0.2</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mf">1.3</span><span class="p">)</span>
|
||||
<span class="n">camera</span><span class="o">.</span><span class="n">set_rotation</span><span class="p">(</span><span class="mi">8</span><span class="p">,</span> <span class="mi">30</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span>
|
||||
<span class="n">camera</span><span class="o">.</span><span class="n">PostProcessing</span> <span class="o">=</span> <span class="s1">'Depth'</span>
|
||||
<span class="n">settings</span><span class="o">.</span><span class="n">add_sensor</span><span class="p">(</span><span class="n">camera</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># add a front facing semantic segmentation camera</span>
|
||||
<span class="k">if</span> <span class="n">CameraTypes</span><span class="o">.</span><span class="n">SEGMENTATION</span> <span class="ow">in</span> <span class="n">cameras</span><span class="p">:</span>
|
||||
<span class="n">camera</span> <span class="o">=</span> <span class="n">Camera</span><span class="p">(</span><span class="n">CameraTypes</span><span class="o">.</span><span class="n">SEGMENTATION</span><span class="o">.</span><span class="n">value</span><span class="p">)</span>
|
||||
<span class="n">camera</span><span class="o">.</span><span class="n">set_image_size</span><span class="p">(</span><span class="n">camera_width</span><span class="p">,</span> <span class="n">camera_height</span><span class="p">)</span>
|
||||
<span class="n">camera</span><span class="o">.</span><span class="n">set_position</span><span class="p">(</span><span class="mf">0.2</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mf">1.3</span><span class="p">)</span>
|
||||
<span class="n">camera</span><span class="o">.</span><span class="n">set_rotation</span><span class="p">(</span><span class="mi">8</span><span class="p">,</span> <span class="mi">30</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span>
|
||||
<span class="n">camera</span><span class="o">.</span><span class="n">PostProcessing</span> <span class="o">=</span> <span class="s1">'SemanticSegmentation'</span>
|
||||
<span class="n">settings</span><span class="o">.</span><span class="n">add_sensor</span><span class="p">(</span><span class="n">camera</span><span class="p">)</span>
|
||||
|
||||
<span class="k">return</span> <span class="n">settings</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_get_directions</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">current_point</span><span class="p">,</span> <span class="n">end_point</span><span class="p">):</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Class that should return the directions to reach a certain goal</span>
|
||||
<span class="sd"> """</span>
|
||||
|
||||
<span class="n">directions</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">planner</span><span class="o">.</span><span class="n">get_next_command</span><span class="p">(</span>
|
||||
<span class="p">(</span><span class="n">current_point</span><span class="o">.</span><span class="n">location</span><span class="o">.</span><span class="n">x</span><span class="p">,</span>
|
||||
<span class="n">current_point</span><span class="o">.</span><span class="n">location</span><span class="o">.</span><span class="n">y</span><span class="p">,</span> <span class="mf">0.22</span><span class="p">),</span>
|
||||
<span class="p">(</span><span class="n">current_point</span><span class="o">.</span><span class="n">orientation</span><span class="o">.</span><span class="n">x</span><span class="p">,</span>
|
||||
<span class="n">current_point</span><span class="o">.</span><span class="n">orientation</span><span class="o">.</span><span class="n">y</span><span class="p">,</span>
|
||||
<span class="n">current_point</span><span class="o">.</span><span class="n">orientation</span><span class="o">.</span><span class="n">z</span><span class="p">),</span>
|
||||
<span class="p">(</span><span class="n">end_point</span><span class="o">.</span><span class="n">location</span><span class="o">.</span><span class="n">x</span><span class="p">,</span> <span class="n">end_point</span><span class="o">.</span><span class="n">location</span><span class="o">.</span><span class="n">y</span><span class="p">,</span> <span class="mf">0.22</span><span class="p">),</span>
|
||||
<span class="p">(</span><span class="n">end_point</span><span class="o">.</span><span class="n">orientation</span><span class="o">.</span><span class="n">x</span><span class="p">,</span> <span class="n">end_point</span><span class="o">.</span><span class="n">orientation</span><span class="o">.</span><span class="n">y</span><span class="p">,</span> <span class="n">end_point</span><span class="o">.</span><span class="n">orientation</span><span class="o">.</span><span class="n">z</span><span class="p">))</span>
|
||||
<span class="k">return</span> <span class="n">directions</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_open_server</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="n">log_path</span> <span class="o">=</span> <span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">experiment_path</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">experiment_path</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="k">else</span> <span class="s1">'.'</span><span class="p">,</span> <span class="s1">'logs'</span><span class="p">,</span>
|
||||
<span class="s2">"CARLA_LOG_</span><span class="si">{}</span><span class="s2">.txt"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">port</span><span class="p">))</span>
|
||||
<span class="k">if</span> <span class="ow">not</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">exists</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">dirname</span><span class="p">(</span><span class="n">log_path</span><span class="p">)):</span>
|
||||
<span class="n">os</span><span class="o">.</span><span class="n">makedirs</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">dirname</span><span class="p">(</span><span class="n">log_path</span><span class="p">))</span>
|
||||
<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">log_path</span><span class="p">,</span> <span class="s2">"wb"</span><span class="p">)</span> <span class="k">as</span> <span class="n">out</span><span class="p">:</span>
|
||||
<span class="n">cmd</span> <span class="o">=</span> <span class="p">[</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">environ</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'CARLA_ROOT'</span><span class="p">),</span> <span class="s1">'CarlaUE4.sh'</span><span class="p">),</span> <span class="bp">self</span><span class="o">.</span><span class="n">map_path</span><span class="p">,</span>
|
||||
<span class="s2">"-benchmark"</span><span class="p">,</span> <span class="s2">"-carla-server"</span><span class="p">,</span> <span class="s2">"-fps=</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="mi">30</span> <span class="o">/</span> <span class="bp">self</span><span class="o">.</span><span class="n">frame_skip</span><span class="p">),</span>
|
||||
<span class="s2">"-world-port=</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">port</span><span class="p">),</span>
|
||||
<span class="s2">"-windowed -ResX=</span><span class="si">{}</span><span class="s2"> -ResY=</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">server_width</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">server_height</span><span class="p">),</span>
|
||||
<span class="s2">"-carla-no-hud"</span><span class="p">]</span>
|
||||
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="p">:</span>
|
||||
<span class="n">cmd</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s2">"-carla-settings=</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="p">))</span>
|
||||
<span class="n">p</span> <span class="o">=</span> <span class="n">subprocess</span><span class="o">.</span><span class="n">Popen</span><span class="p">(</span><span class="n">cmd</span><span class="p">,</span> <span class="n">stdout</span><span class="o">=</span><span class="n">out</span><span class="p">,</span> <span class="n">stderr</span><span class="o">=</span><span class="n">out</span><span class="p">)</span>
|
||||
|
||||
<span class="k">return</span> <span class="n">p</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_close_server</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="n">os</span><span class="o">.</span><span class="n">killpg</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">getpgid</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">server</span><span class="o">.</span><span class="n">pid</span><span class="p">),</span> <span class="n">signal</span><span class="o">.</span><span class="n">SIGKILL</span><span class="p">)</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_update_state</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="c1"># get measurements and observations</span>
|
||||
<span class="n">measurements</span> <span class="o">=</span> <span class="p">[]</span>
|
||||
<span class="k">while</span> <span class="nb">type</span><span class="p">(</span><span class="n">measurements</span><span class="p">)</span> <span class="o">==</span> <span class="nb">list</span><span class="p">:</span>
|
||||
<span class="n">measurements</span><span class="p">,</span> <span class="n">sensor_data</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="o">.</span><span class="n">read_data</span><span class="p">()</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">state</span> <span class="o">=</span> <span class="p">{}</span>
|
||||
|
||||
<span class="k">for</span> <span class="n">camera</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">scene</span><span class="o">.</span><span class="n">sensors</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">state</span><span class="p">[</span><span class="n">camera</span><span class="o">.</span><span class="n">name</span><span class="p">]</span> <span class="o">=</span> <span class="n">sensor_data</span><span class="p">[</span><span class="n">camera</span><span class="o">.</span><span class="n">name</span><span class="p">]</span><span class="o">.</span><span class="n">data</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">location</span> <span class="o">=</span> <span class="p">[</span><span class="n">measurements</span><span class="o">.</span><span class="n">player_measurements</span><span class="o">.</span><span class="n">transform</span><span class="o">.</span><span class="n">location</span><span class="o">.</span><span class="n">x</span><span class="p">,</span>
|
||||
<span class="n">measurements</span><span class="o">.</span><span class="n">player_measurements</span><span class="o">.</span><span class="n">transform</span><span class="o">.</span><span class="n">location</span><span class="o">.</span><span class="n">y</span><span class="p">,</span>
|
||||
<span class="n">measurements</span><span class="o">.</span><span class="n">player_measurements</span><span class="o">.</span><span class="n">transform</span><span class="o">.</span><span class="n">location</span><span class="o">.</span><span class="n">z</span><span class="p">]</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">distance_from_goal</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">linalg</span><span class="o">.</span><span class="n">norm</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">location</span><span class="p">[:</span><span class="mi">2</span><span class="p">])</span> <span class="o">-</span>
|
||||
<span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">current_goal</span><span class="o">.</span><span class="n">location</span><span class="o">.</span><span class="n">x</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">current_goal</span><span class="o">.</span><span class="n">location</span><span class="o">.</span><span class="n">y</span><span class="p">])</span>
|
||||
|
||||
<span class="n">is_collision</span> <span class="o">=</span> <span class="n">measurements</span><span class="o">.</span><span class="n">player_measurements</span><span class="o">.</span><span class="n">collision_vehicles</span> <span class="o">!=</span> <span class="mi">0</span> \
|
||||
<span class="ow">or</span> <span class="n">measurements</span><span class="o">.</span><span class="n">player_measurements</span><span class="o">.</span><span class="n">collision_pedestrians</span> <span class="o">!=</span> <span class="mi">0</span> \
|
||||
<span class="ow">or</span> <span class="n">measurements</span><span class="o">.</span><span class="n">player_measurements</span><span class="o">.</span><span class="n">collision_other</span> <span class="o">!=</span> <span class="mi">0</span>
|
||||
|
||||
<span class="n">speed_reward</span> <span class="o">=</span> <span class="n">measurements</span><span class="o">.</span><span class="n">player_measurements</span><span class="o">.</span><span class="n">forward_speed</span> <span class="o">-</span> <span class="mi">1</span>
|
||||
<span class="k">if</span> <span class="n">speed_reward</span> <span class="o">></span> <span class="mf">30.</span><span class="p">:</span>
|
||||
<span class="n">speed_reward</span> <span class="o">=</span> <span class="mf">30.</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reward</span> <span class="o">=</span> <span class="n">speed_reward</span> \
|
||||
<span class="o">-</span> <span class="p">(</span><span class="n">measurements</span><span class="o">.</span><span class="n">player_measurements</span><span class="o">.</span><span class="n">intersection_otherlane</span> <span class="o">*</span> <span class="mi">5</span><span class="p">)</span> \
|
||||
<span class="o">-</span> <span class="p">(</span><span class="n">measurements</span><span class="o">.</span><span class="n">player_measurements</span><span class="o">.</span><span class="n">intersection_offroad</span> <span class="o">*</span> <span class="mi">5</span><span class="p">)</span> \
|
||||
<span class="o">-</span> <span class="n">is_collision</span> <span class="o">*</span> <span class="mi">100</span> \
|
||||
<span class="o">-</span> <span class="n">np</span><span class="o">.</span><span class="n">abs</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">control</span><span class="o">.</span><span class="n">steer</span><span class="p">)</span> <span class="o">*</span> <span class="mi">10</span>
|
||||
|
||||
<span class="c1"># update measurements</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">measurements</span> <span class="o">=</span> <span class="p">[</span><span class="n">measurements</span><span class="o">.</span><span class="n">player_measurements</span><span class="o">.</span><span class="n">forward_speed</span><span class="p">]</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">location</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">autopilot</span> <span class="o">=</span> <span class="n">measurements</span><span class="o">.</span><span class="n">player_measurements</span><span class="o">.</span><span class="n">autopilot_control</span>
|
||||
|
||||
<span class="c1"># The directions to reach the goal (0 Follow lane, 1 Left, 2 Right, 3 Straight)</span>
|
||||
<span class="n">directions</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_get_directions</span><span class="p">(</span><span class="n">measurements</span><span class="o">.</span><span class="n">player_measurements</span><span class="o">.</span><span class="n">transform</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">current_goal</span><span class="p">)</span> <span class="o">-</span> <span class="mi">2</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">state</span><span class="p">[</span><span class="s1">'high_level_command'</span><span class="p">]</span> <span class="o">=</span> <span class="n">directions</span>
|
||||
|
||||
<span class="k">if</span> <span class="p">(</span><span class="n">measurements</span><span class="o">.</span><span class="n">game_timestamp</span> <span class="o">>=</span> <span class="bp">self</span><span class="o">.</span><span class="n">episode_max_time</span><span class="p">)</span> <span class="ow">or</span> <span class="n">is_collision</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">done</span> <span class="o">=</span> <span class="kc">True</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">state</span><span class="p">[</span><span class="s1">'measurements'</span><span class="p">]</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">measurements</span><span class="p">)</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_take_action</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">action</span><span class="p">):</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">control</span> <span class="o">=</span> <span class="n">VehicleControl</span><span class="p">()</span>
|
||||
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">separate_actions_for_throttle_and_brake</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">control</span><span class="o">.</span><span class="n">steer</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">clip</span><span class="p">(</span><span class="n">action</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">control</span><span class="o">.</span><span class="n">throttle</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">clip</span><span class="p">(</span><span class="n">action</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">control</span><span class="o">.</span><span class="n">brake</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">clip</span><span class="p">(</span><span class="n">action</span><span class="p">[</span><span class="mi">2</span><span class="p">],</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="c1"># transform the 2 value action (steer, throttle - brake) into a 3 value action (steer, throttle, brake)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">control</span><span class="o">.</span><span class="n">steer</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">clip</span><span class="p">(</span><span class="n">action</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">control</span><span class="o">.</span><span class="n">throttle</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">clip</span><span class="p">(</span><span class="n">action</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">control</span><span class="o">.</span><span class="n">brake</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">abs</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">clip</span><span class="p">(</span><span class="n">action</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="mi">0</span><span class="p">))</span>
|
||||
|
||||
<span class="c1"># prevent braking</span>
|
||||
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">allow_braking</span> <span class="ow">or</span> <span class="bp">self</span><span class="o">.</span><span class="n">control</span><span class="o">.</span><span class="n">brake</span> <span class="o"><</span> <span class="mf">0.1</span> <span class="ow">or</span> <span class="bp">self</span><span class="o">.</span><span class="n">control</span><span class="o">.</span><span class="n">throttle</span> <span class="o">></span> <span class="bp">self</span><span class="o">.</span><span class="n">control</span><span class="o">.</span><span class="n">brake</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">control</span><span class="o">.</span><span class="n">brake</span> <span class="o">=</span> <span class="mi">0</span>
|
||||
|
||||
<span class="c1"># prevent over speeding</span>
|
||||
<span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s1">'measurements'</span><span class="p">)</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">measurements</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">*</span> <span class="mf">3.6</span> <span class="o">></span> <span class="bp">self</span><span class="o">.</span><span class="n">max_speed</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">control</span><span class="o">.</span><span class="n">brake</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">control</span><span class="o">.</span><span class="n">throttle</span> <span class="o">=</span> <span class="mf">0.0</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">control</span><span class="o">.</span><span class="n">hand_brake</span> <span class="o">=</span> <span class="kc">False</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">control</span><span class="o">.</span><span class="n">reverse</span> <span class="o">=</span> <span class="kc">False</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="o">.</span><span class="n">send_control</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">control</span><span class="p">)</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_load_experiment</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">experiment_idx</span><span class="p">):</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">current_experiment</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">experiment_suite</span><span class="o">.</span><span class="n">get_experiments</span><span class="p">()[</span><span class="n">experiment_idx</span><span class="p">]</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">scene</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="o">.</span><span class="n">load_settings</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">current_experiment</span><span class="o">.</span><span class="n">conditions</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">positions</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">scene</span><span class="o">.</span><span class="n">player_start_spots</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">num_positions</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">positions</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">current_start_position_idx</span> <span class="o">=</span> <span class="mi">0</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">current_pose</span> <span class="o">=</span> <span class="mi">0</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_restart_environment_episode</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">force_environment_reset</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
|
||||
<span class="c1"># select start and end positions</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">experiment_suite</span><span class="p">:</span>
|
||||
<span class="c1"># if an expeirent suite is available, follow its given poses</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">current_pose</span> <span class="o">>=</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">current_experiment</span><span class="o">.</span><span class="n">poses</span><span class="p">):</span>
|
||||
<span class="c1"># load a new experiment</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">current_experiment_idx</span> <span class="o">=</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">current_experiment_idx</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)</span> <span class="o">%</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">experiment_suite</span><span class="o">.</span><span class="n">get_experiments</span><span class="p">())</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_load_experiment</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">current_experiment_idx</span><span class="p">)</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">current_start_position_idx</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">current_experiment</span><span class="o">.</span><span class="n">poses</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">current_pose</span><span class="p">][</span><span class="mi">0</span><span class="p">]</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">current_goal</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">positions</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">current_experiment</span><span class="o">.</span><span class="n">poses</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">current_pose</span><span class="p">][</span><span class="mi">1</span><span class="p">]]</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">current_pose</span> <span class="o">+=</span> <span class="mi">1</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="c1"># go over all the possible positions in a cyclic manner</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">current_start_position_idx</span> <span class="o">=</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">current_start_position_idx</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)</span> <span class="o">%</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_positions</span>
|
||||
|
||||
<span class="c1"># choose a random goal destination</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">current_goal</span> <span class="o">=</span> <span class="n">random</span><span class="o">.</span><span class="n">choice</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">positions</span><span class="p">)</span>
|
||||
|
||||
<span class="k">try</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="o">.</span><span class="n">start_episode</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">current_start_position_idx</span><span class="p">)</span>
|
||||
<span class="k">except</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="o">.</span><span class="n">connect</span><span class="p">()</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="o">.</span><span class="n">start_episode</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">current_start_position_idx</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># start the game with some initial speed</span>
|
||||
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">num_speedup_steps</span><span class="p">):</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">control</span> <span class="o">=</span> <span class="n">VehicleControl</span><span class="p">(</span><span class="n">throttle</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span> <span class="n">brake</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">steer</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">hand_brake</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">reverse</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="o">.</span><span class="n">send_control</span><span class="p">(</span><span class="n">VehicleControl</span><span class="p">())</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">get_rendered_image</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Return a numpy array containing the image that will be rendered to the screen.</span>
|
||||
<span class="sd"> This can be different from the observation. For example, mujoco's observation is a measurements vector.</span>
|
||||
<span class="sd"> :return: numpy array containing the image that will be rendered to the screen</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="n">image</span> <span class="o">=</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">state</span><span class="p">[</span><span class="n">camera</span><span class="o">.</span><span class="n">name</span><span class="p">]</span> <span class="k">for</span> <span class="n">camera</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">scene</span><span class="o">.</span><span class="n">sensors</span><span class="p">]</span>
|
||||
<span class="n">image</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">vstack</span><span class="p">(</span><span class="n">image</span><span class="p">)</span>
|
||||
<span class="k">return</span> <span class="n">image</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">get_target_success_rate</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span>
|
||||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">target_success_rate</span></div>
|
||||
</pre></div>
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
<footer>
|
||||
|
||||
|
||||
<hr/>
|
||||
|
||||
<div role="contentinfo">
|
||||
<p>
|
||||
© Copyright 2018, Intel AI Lab
|
||||
|
||||
</p>
|
||||
</div>
|
||||
Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
|
||||
|
||||
</footer>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
|
||||
</section>
|
||||
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<script type="text/javascript" id="documentation_options" data-url_root="../../../" src="../../../_static/documentation_options.js"></script>
|
||||
<script type="text/javascript" src="../../../_static/jquery.js"></script>
|
||||
<script type="text/javascript" src="../../../_static/underscore.js"></script>
|
||||
<script type="text/javascript" src="../../../_static/doctools.js"></script>
|
||||
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></script>
|
||||
|
||||
|
||||
|
||||
|
||||
<script type="text/javascript" src="../../../_static/js/theme.js"></script>
|
||||
|
||||
<script type="text/javascript">
|
||||
jQuery(function () {
|
||||
SphinxRtdTheme.Navigation.enable(true);
|
||||
});
|
||||
</script>
|
||||
|
||||
</body>
|
||||
</html>
|
||||
@@ -0,0 +1,426 @@
|
||||
|
||||
|
||||
<!DOCTYPE html>
|
||||
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
|
||||
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
|
||||
<head>
|
||||
<meta charset="utf-8">
|
||||
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
|
||||
<title>rl_coach.environments.control_suite_environment — Reinforcement Learning Coach 0.11.0 documentation</title>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
|
||||
<link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
|
||||
<link rel="stylesheet" href="../../../_static/css/custom.css" type="text/css" />
|
||||
<link rel="index" title="Index" href="../../../genindex.html" />
|
||||
<link rel="search" title="Search" href="../../../search.html" />
|
||||
<link href="../../../_static/css/custom.css" rel="stylesheet" type="text/css">
|
||||
|
||||
|
||||
|
||||
<script src="../../../_static/js/modernizr.min.js"></script>
|
||||
|
||||
</head>
|
||||
|
||||
<body class="wy-body-for-nav">
|
||||
|
||||
|
||||
<div class="wy-grid-for-nav">
|
||||
|
||||
|
||||
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
|
||||
<div class="wy-side-scroll">
|
||||
<div class="wy-side-nav-search">
|
||||
|
||||
|
||||
|
||||
<a href="../../../index.html" class="icon icon-home"> Reinforcement Learning Coach
|
||||
|
||||
|
||||
|
||||
|
||||
<img src="../../../_static/dark_logo.png" class="logo" alt="Logo"/>
|
||||
|
||||
</a>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<div role="search">
|
||||
<form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get">
|
||||
<input type="text" name="q" placeholder="Search docs" />
|
||||
<input type="hidden" name="check_keywords" value="yes" />
|
||||
<input type="hidden" name="area" value="default" />
|
||||
</form>
|
||||
</div>
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<p class="caption"><span class="caption-text">Intro</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../usage.html">Usage</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../features/index.html">Features</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../selecting_an_algorithm.html">Selecting an Algorithm</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../dashboard.html">Coach Dashboard</a></li>
|
||||
</ul>
|
||||
<p class="caption"><span class="caption-text">Design</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../design/control_flow.html">Control Flow</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../design/network.html">Network Design</a></li>
|
||||
</ul>
|
||||
<p class="caption"><span class="caption-text">Contributing</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../contributing/add_agent.html">Adding a New Agent</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../contributing/add_env.html">Adding a New Environment</a></li>
|
||||
</ul>
|
||||
<p class="caption"><span class="caption-text">Components</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/agents/index.html">Agents</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/architectures/index.html">Architectures</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/environments/index.html">Environments</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/exploration_policies/index.html">Exploration Policies</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/filters/index.html">Filters</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/memories/index.html">Memories</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/core_types.html">Core Types</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/spaces.html">Spaces</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/additional_parameters.html">Additional Parameters</a></li>
|
||||
</ul>
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
</nav>
|
||||
|
||||
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
|
||||
|
||||
|
||||
<nav class="wy-nav-top" aria-label="top navigation">
|
||||
|
||||
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
|
||||
<a href="../../../index.html">Reinforcement Learning Coach</a>
|
||||
|
||||
</nav>
|
||||
|
||||
|
||||
<div class="wy-nav-content">
|
||||
|
||||
<div class="rst-content">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<div role="navigation" aria-label="breadcrumbs navigation">
|
||||
|
||||
<ul class="wy-breadcrumbs">
|
||||
|
||||
<li><a href="../../../index.html">Docs</a> »</li>
|
||||
|
||||
<li><a href="../../index.html">Module code</a> »</li>
|
||||
|
||||
<li>rl_coach.environments.control_suite_environment</li>
|
||||
|
||||
|
||||
<li class="wy-breadcrumbs-aside">
|
||||
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
|
||||
|
||||
<hr/>
|
||||
</div>
|
||||
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
|
||||
<div itemprop="articleBody">
|
||||
|
||||
<h1>Source code for rl_coach.environments.control_suite_environment</h1><div class="highlight"><pre>
|
||||
<span></span><span class="c1">#</span>
|
||||
<span class="c1"># Copyright (c) 2017 Intel Corporation</span>
|
||||
<span class="c1">#</span>
|
||||
<span class="c1"># Licensed under the Apache License, Version 2.0 (the "License");</span>
|
||||
<span class="c1"># you may not use this file except in compliance with the License.</span>
|
||||
<span class="c1"># You may obtain a copy of the License at</span>
|
||||
<span class="c1">#</span>
|
||||
<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
|
||||
<span class="c1">#</span>
|
||||
<span class="c1"># Unless required by applicable law or agreed to in writing, software</span>
|
||||
<span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span>
|
||||
<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
|
||||
<span class="c1"># See the License for the specific language governing permissions and</span>
|
||||
<span class="c1"># limitations under the License.</span>
|
||||
<span class="c1">#</span>
|
||||
|
||||
|
||||
|
||||
<span class="kn">import</span> <span class="nn">random</span>
|
||||
<span class="kn">from</span> <span class="nn">enum</span> <span class="k">import</span> <span class="n">Enum</span>
|
||||
<span class="kn">from</span> <span class="nn">typing</span> <span class="k">import</span> <span class="n">Union</span>
|
||||
|
||||
<span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
|
||||
|
||||
<span class="k">try</span><span class="p">:</span>
|
||||
<span class="kn">from</span> <span class="nn">dm_control</span> <span class="k">import</span> <span class="n">suite</span>
|
||||
<span class="kn">from</span> <span class="nn">dm_control.suite.wrappers</span> <span class="k">import</span> <span class="n">pixels</span>
|
||||
<span class="k">except</span> <span class="ne">ImportError</span><span class="p">:</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.logger</span> <span class="k">import</span> <span class="n">failed_imports</span>
|
||||
<span class="n">failed_imports</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s2">"DeepMind Control Suite"</span><span class="p">)</span>
|
||||
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.base_parameters</span> <span class="k">import</span> <span class="n">VisualizationParameters</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.environments.environment</span> <span class="k">import</span> <span class="n">Environment</span><span class="p">,</span> <span class="n">EnvironmentParameters</span><span class="p">,</span> <span class="n">LevelSelection</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.filters.filter</span> <span class="k">import</span> <span class="n">NoInputFilter</span><span class="p">,</span> <span class="n">NoOutputFilter</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.spaces</span> <span class="k">import</span> <span class="n">BoxActionSpace</span><span class="p">,</span> <span class="n">ImageObservationSpace</span><span class="p">,</span> <span class="n">VectorObservationSpace</span><span class="p">,</span> <span class="n">StateSpace</span>
|
||||
|
||||
|
||||
<span class="k">class</span> <span class="nc">ObservationType</span><span class="p">(</span><span class="n">Enum</span><span class="p">):</span>
|
||||
<span class="n">Measurements</span> <span class="o">=</span> <span class="mi">1</span>
|
||||
<span class="n">Image</span> <span class="o">=</span> <span class="mi">2</span>
|
||||
<span class="n">Image_and_Measurements</span> <span class="o">=</span> <span class="mi">3</span>
|
||||
|
||||
|
||||
<span class="c1"># Parameters</span>
|
||||
<span class="k">class</span> <span class="nc">ControlSuiteEnvironmentParameters</span><span class="p">(</span><span class="n">EnvironmentParameters</span><span class="p">):</span>
|
||||
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">level</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">level</span><span class="o">=</span><span class="n">level</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">observation_type</span> <span class="o">=</span> <span class="n">ObservationType</span><span class="o">.</span><span class="n">Measurements</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">default_input_filter</span> <span class="o">=</span> <span class="n">ControlSuiteInputFilter</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">default_output_filter</span> <span class="o">=</span> <span class="n">ControlSuiteOutputFilter</span>
|
||||
|
||||
<span class="nd">@property</span>
|
||||
<span class="k">def</span> <span class="nf">path</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="k">return</span> <span class="s1">'rl_coach.environments.control_suite_environment:ControlSuiteEnvironment'</span>
|
||||
|
||||
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd">ControlSuite Environment Components</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="n">ControlSuiteInputFilter</span> <span class="o">=</span> <span class="n">NoInputFilter</span><span class="p">()</span>
|
||||
<span class="n">ControlSuiteOutputFilter</span> <span class="o">=</span> <span class="n">NoOutputFilter</span><span class="p">()</span>
|
||||
|
||||
<span class="n">control_suite_envs</span> <span class="o">=</span> <span class="p">{</span><span class="s1">':'</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">env</span><span class="p">):</span> <span class="s1">':'</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">env</span><span class="p">)</span> <span class="k">for</span> <span class="n">env</span> <span class="ow">in</span> <span class="n">suite</span><span class="o">.</span><span class="n">BENCHMARKING</span><span class="p">}</span>
|
||||
|
||||
|
||||
<span class="c1"># Environment</span>
|
||||
<div class="viewcode-block" id="ControlSuiteEnvironment"><a class="viewcode-back" href="../../../components/environments/index.html#rl_coach.environments.control_suite_environment.ControlSuiteEnvironment">[docs]</a><span class="k">class</span> <span class="nc">ControlSuiteEnvironment</span><span class="p">(</span><span class="n">Environment</span><span class="p">):</span>
|
||||
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">level</span><span class="p">:</span> <span class="n">LevelSelection</span><span class="p">,</span> <span class="n">frame_skip</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">visualization_parameters</span><span class="p">:</span> <span class="n">VisualizationParameters</span><span class="p">,</span>
|
||||
<span class="n">target_success_rate</span><span class="p">:</span> <span class="nb">float</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span> <span class="n">seed</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="kc">None</span><span class="p">,</span> <span class="nb">int</span><span class="p">]</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">human_control</span><span class="p">:</span> <span class="nb">bool</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||||
<span class="n">observation_type</span><span class="p">:</span> <span class="n">ObservationType</span><span class="o">=</span><span class="n">ObservationType</span><span class="o">.</span><span class="n">Measurements</span><span class="p">,</span>
|
||||
<span class="n">custom_reward_threshold</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">]</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> :param level: (str)</span>
|
||||
<span class="sd"> A string representing the control suite level to run. This can also be a LevelSelection object.</span>
|
||||
<span class="sd"> For example, cartpole:swingup.</span>
|
||||
|
||||
<span class="sd"> :param frame_skip: (int)</span>
|
||||
<span class="sd"> The number of frames to skip between any two actions given by the agent. The action will be repeated</span>
|
||||
<span class="sd"> for all the skipped frames.</span>
|
||||
|
||||
<span class="sd"> :param visualization_parameters: (VisualizationParameters)</span>
|
||||
<span class="sd"> The parameters used for visualizing the environment, such as the render flag, storing videos etc.</span>
|
||||
|
||||
<span class="sd"> :param target_success_rate: (float)</span>
|
||||
<span class="sd"> Stop experiment if given target success rate was achieved.</span>
|
||||
|
||||
<span class="sd"> :param seed: (int)</span>
|
||||
<span class="sd"> A seed to use for the random number generator when running the environment.</span>
|
||||
|
||||
<span class="sd"> :param human_control: (bool)</span>
|
||||
<span class="sd"> A flag that allows controlling the environment using the keyboard keys.</span>
|
||||
|
||||
<span class="sd"> :param observation_type: (ObservationType)</span>
|
||||
<span class="sd"> An enum which defines which observation to use. The current options are to use:</span>
|
||||
<span class="sd"> * Measurements only - a vector of joint torques and similar measurements</span>
|
||||
<span class="sd"> * Image only - an image of the environment as seen by a camera attached to the simulator</span>
|
||||
<span class="sd"> * Measurements & Image - both type of observations will be returned in the state using the keys</span>
|
||||
<span class="sd"> 'measurements' and 'pixels' respectively.</span>
|
||||
|
||||
<span class="sd"> :param custom_reward_threshold: (float)</span>
|
||||
<span class="sd"> Allows defining a custom reward that will be used to decide when the agent succeeded in passing the environment.</span>
|
||||
|
||||
<span class="sd"> """</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">level</span><span class="p">,</span> <span class="n">seed</span><span class="p">,</span> <span class="n">frame_skip</span><span class="p">,</span> <span class="n">human_control</span><span class="p">,</span> <span class="n">custom_reward_threshold</span><span class="p">,</span> <span class="n">visualization_parameters</span><span class="p">,</span> <span class="n">target_success_rate</span><span class="p">)</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">observation_type</span> <span class="o">=</span> <span class="n">observation_type</span>
|
||||
|
||||
<span class="c1"># load and initialize environment</span>
|
||||
<span class="n">domain_name</span><span class="p">,</span> <span class="n">task_name</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">env_id</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">":"</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">env</span> <span class="o">=</span> <span class="n">suite</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="n">domain_name</span><span class="o">=</span><span class="n">domain_name</span><span class="p">,</span> <span class="n">task_name</span><span class="o">=</span><span class="n">task_name</span><span class="p">,</span> <span class="n">task_kwargs</span><span class="o">=</span><span class="p">{</span><span class="s1">'random'</span><span class="p">:</span> <span class="n">seed</span><span class="p">})</span>
|
||||
|
||||
<span class="k">if</span> <span class="n">observation_type</span> <span class="o">!=</span> <span class="n">ObservationType</span><span class="o">.</span><span class="n">Measurements</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">env</span> <span class="o">=</span> <span class="n">pixels</span><span class="o">.</span><span class="n">Wrapper</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="p">,</span> <span class="n">pixels_only</span><span class="o">=</span><span class="n">observation_type</span> <span class="o">==</span> <span class="n">ObservationType</span><span class="o">.</span><span class="n">Image</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># seed</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">seed</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">seed</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">seed</span><span class="p">)</span>
|
||||
<span class="n">random</span><span class="o">.</span><span class="n">seed</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">seed</span><span class="p">)</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">state_space</span> <span class="o">=</span> <span class="n">StateSpace</span><span class="p">({})</span>
|
||||
|
||||
<span class="c1"># image observations</span>
|
||||
<span class="k">if</span> <span class="n">observation_type</span> <span class="o">!=</span> <span class="n">ObservationType</span><span class="o">.</span><span class="n">Measurements</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">state_space</span><span class="p">[</span><span class="s1">'pixels'</span><span class="p">]</span> <span class="o">=</span> <span class="n">ImageObservationSpace</span><span class="p">(</span><span class="n">shape</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">observation_spec</span><span class="p">()[</span><span class="s1">'pixels'</span><span class="p">]</span><span class="o">.</span><span class="n">shape</span><span class="p">,</span>
|
||||
<span class="n">high</span><span class="o">=</span><span class="mi">255</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># measurements observations</span>
|
||||
<span class="k">if</span> <span class="n">observation_type</span> <span class="o">!=</span> <span class="n">ObservationType</span><span class="o">.</span><span class="n">Image</span><span class="p">:</span>
|
||||
<span class="n">measurements_space_size</span> <span class="o">=</span> <span class="mi">0</span>
|
||||
<span class="n">measurements_names</span> <span class="o">=</span> <span class="p">[]</span>
|
||||
<span class="k">for</span> <span class="n">observation_space_name</span><span class="p">,</span> <span class="n">observation_space</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">observation_spec</span><span class="p">()</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
|
||||
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">observation_space</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
|
||||
<span class="n">measurements_space_size</span> <span class="o">+=</span> <span class="mi">1</span>
|
||||
<span class="n">measurements_names</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">observation_space_name</span><span class="p">)</span>
|
||||
<span class="k">elif</span> <span class="nb">len</span><span class="p">(</span><span class="n">observation_space</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span>
|
||||
<span class="n">measurements_space_size</span> <span class="o">+=</span> <span class="n">observation_space</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
|
||||
<span class="n">measurements_names</span><span class="o">.</span><span class="n">extend</span><span class="p">([</span><span class="s2">"</span><span class="si">{}</span><span class="s2">_</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">observation_space_name</span><span class="p">,</span> <span class="n">i</span><span class="p">)</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span>
|
||||
<span class="nb">range</span><span class="p">(</span><span class="n">observation_space</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">])])</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">state_space</span><span class="p">[</span><span class="s1">'measurements'</span><span class="p">]</span> <span class="o">=</span> <span class="n">VectorObservationSpace</span><span class="p">(</span><span class="n">shape</span><span class="o">=</span><span class="n">measurements_space_size</span><span class="p">,</span>
|
||||
<span class="n">measurements_names</span><span class="o">=</span><span class="n">measurements_names</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># actions</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">action_space</span> <span class="o">=</span> <span class="n">BoxActionSpace</span><span class="p">(</span>
|
||||
<span class="n">shape</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">action_spec</span><span class="p">()</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span>
|
||||
<span class="n">low</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">action_spec</span><span class="p">()</span><span class="o">.</span><span class="n">minimum</span><span class="p">,</span>
|
||||
<span class="n">high</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">action_spec</span><span class="p">()</span><span class="o">.</span><span class="n">maximum</span>
|
||||
<span class="p">)</span>
|
||||
|
||||
<span class="c1"># initialize the state by getting a new state from the environment</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reset_internal_state</span><span class="p">(</span><span class="kc">True</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># render</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_rendered</span><span class="p">:</span>
|
||||
<span class="n">image</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_rendered_image</span><span class="p">()</span>
|
||||
<span class="n">scale</span> <span class="o">=</span> <span class="mi">1</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">human_control</span><span class="p">:</span>
|
||||
<span class="n">scale</span> <span class="o">=</span> <span class="mi">2</span>
|
||||
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">native_rendering</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">renderer</span><span class="o">.</span><span class="n">create_screen</span><span class="p">(</span><span class="n">image</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span><span class="o">*</span><span class="n">scale</span><span class="p">,</span> <span class="n">image</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">*</span><span class="n">scale</span><span class="p">)</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">target_success_rate</span> <span class="o">=</span> <span class="n">target_success_rate</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_update_state</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">state</span> <span class="o">=</span> <span class="p">{}</span>
|
||||
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">observation_type</span> <span class="o">!=</span> <span class="n">ObservationType</span><span class="o">.</span><span class="n">Measurements</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">pixels</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">last_result</span><span class="o">.</span><span class="n">observation</span><span class="p">[</span><span class="s1">'pixels'</span><span class="p">]</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">state</span><span class="p">[</span><span class="s1">'pixels'</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">pixels</span>
|
||||
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">observation_type</span> <span class="o">!=</span> <span class="n">ObservationType</span><span class="o">.</span><span class="n">Image</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">measurements</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([])</span>
|
||||
<span class="k">for</span> <span class="n">sub_observation</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">last_result</span><span class="o">.</span><span class="n">observation</span><span class="o">.</span><span class="n">values</span><span class="p">():</span>
|
||||
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">sub_observation</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">)</span> <span class="ow">and</span> <span class="nb">len</span><span class="p">(</span><span class="n">sub_observation</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">measurements</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">concatenate</span><span class="p">((</span><span class="bp">self</span><span class="o">.</span><span class="n">measurements</span><span class="p">,</span> <span class="n">sub_observation</span><span class="p">))</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">measurements</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">concatenate</span><span class="p">((</span><span class="bp">self</span><span class="o">.</span><span class="n">measurements</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="n">sub_observation</span><span class="p">])))</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">state</span><span class="p">[</span><span class="s1">'measurements'</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">measurements</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reward</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">last_result</span><span class="o">.</span><span class="n">reward</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">last_result</span><span class="o">.</span><span class="n">reward</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="k">else</span> <span class="mi">0</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">done</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">last_result</span><span class="o">.</span><span class="n">last</span><span class="p">()</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_take_action</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">action</span><span class="p">):</span>
|
||||
<span class="k">if</span> <span class="nb">type</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">action_space</span><span class="p">)</span> <span class="o">==</span> <span class="n">BoxActionSpace</span><span class="p">:</span>
|
||||
<span class="n">action</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">action_space</span><span class="o">.</span><span class="n">clip_action_to_space</span><span class="p">(</span><span class="n">action</span><span class="p">)</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">last_result</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">step</span><span class="p">(</span><span class="n">action</span><span class="p">)</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_restart_environment_episode</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">force_environment_reset</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">last_result</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">reset</span><span class="p">()</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_render</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="k">pass</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">get_rendered_image</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">physics</span><span class="o">.</span><span class="n">render</span><span class="p">(</span><span class="n">camera_id</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">get_target_success_rate</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span>
|
||||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">target_success_rate</span></div>
|
||||
</pre></div>
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
<footer>
|
||||
|
||||
|
||||
<hr/>
|
||||
|
||||
<div role="contentinfo">
|
||||
<p>
|
||||
© Copyright 2018, Intel AI Lab
|
||||
|
||||
</p>
|
||||
</div>
|
||||
Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
|
||||
|
||||
</footer>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
|
||||
</section>
|
||||
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<script type="text/javascript" id="documentation_options" data-url_root="../../../" src="../../../_static/documentation_options.js"></script>
|
||||
<script type="text/javascript" src="../../../_static/jquery.js"></script>
|
||||
<script type="text/javascript" src="../../../_static/underscore.js"></script>
|
||||
<script type="text/javascript" src="../../../_static/doctools.js"></script>
|
||||
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></script>
|
||||
|
||||
|
||||
|
||||
|
||||
<script type="text/javascript" src="../../../_static/js/theme.js"></script>
|
||||
|
||||
<script type="text/javascript">
|
||||
jQuery(function () {
|
||||
SphinxRtdTheme.Navigation.enable(true);
|
||||
});
|
||||
</script>
|
||||
|
||||
</body>
|
||||
</html>
|
||||
495
docs/_modules/rl_coach/environments/doom_environment.html
Normal file
495
docs/_modules/rl_coach/environments/doom_environment.html
Normal file
@@ -0,0 +1,495 @@
|
||||
|
||||
|
||||
<!DOCTYPE html>
|
||||
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
|
||||
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
|
||||
<head>
|
||||
<meta charset="utf-8">
|
||||
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
|
||||
<title>rl_coach.environments.doom_environment — Reinforcement Learning Coach 0.11.0 documentation</title>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
|
||||
<link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
|
||||
<link rel="stylesheet" href="../../../_static/css/custom.css" type="text/css" />
|
||||
<link rel="index" title="Index" href="../../../genindex.html" />
|
||||
<link rel="search" title="Search" href="../../../search.html" />
|
||||
<link href="../../../_static/css/custom.css" rel="stylesheet" type="text/css">
|
||||
|
||||
|
||||
|
||||
<script src="../../../_static/js/modernizr.min.js"></script>
|
||||
|
||||
</head>
|
||||
|
||||
<body class="wy-body-for-nav">
|
||||
|
||||
|
||||
<div class="wy-grid-for-nav">
|
||||
|
||||
|
||||
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
|
||||
<div class="wy-side-scroll">
|
||||
<div class="wy-side-nav-search">
|
||||
|
||||
|
||||
|
||||
<a href="../../../index.html" class="icon icon-home"> Reinforcement Learning Coach
|
||||
|
||||
|
||||
|
||||
|
||||
<img src="../../../_static/dark_logo.png" class="logo" alt="Logo"/>
|
||||
|
||||
</a>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<div role="search">
|
||||
<form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get">
|
||||
<input type="text" name="q" placeholder="Search docs" />
|
||||
<input type="hidden" name="check_keywords" value="yes" />
|
||||
<input type="hidden" name="area" value="default" />
|
||||
</form>
|
||||
</div>
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<p class="caption"><span class="caption-text">Intro</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../usage.html">Usage</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../features/index.html">Features</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../selecting_an_algorithm.html">Selecting an Algorithm</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../dashboard.html">Coach Dashboard</a></li>
|
||||
</ul>
|
||||
<p class="caption"><span class="caption-text">Design</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../design/control_flow.html">Control Flow</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../design/network.html">Network Design</a></li>
|
||||
</ul>
|
||||
<p class="caption"><span class="caption-text">Contributing</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../contributing/add_agent.html">Adding a New Agent</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../contributing/add_env.html">Adding a New Environment</a></li>
|
||||
</ul>
|
||||
<p class="caption"><span class="caption-text">Components</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/agents/index.html">Agents</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/architectures/index.html">Architectures</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/environments/index.html">Environments</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/exploration_policies/index.html">Exploration Policies</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/filters/index.html">Filters</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/memories/index.html">Memories</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/core_types.html">Core Types</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/spaces.html">Spaces</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/additional_parameters.html">Additional Parameters</a></li>
|
||||
</ul>
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
</nav>
|
||||
|
||||
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
|
||||
|
||||
|
||||
<nav class="wy-nav-top" aria-label="top navigation">
|
||||
|
||||
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
|
||||
<a href="../../../index.html">Reinforcement Learning Coach</a>
|
||||
|
||||
</nav>
|
||||
|
||||
|
||||
<div class="wy-nav-content">
|
||||
|
||||
<div class="rst-content">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<div role="navigation" aria-label="breadcrumbs navigation">
|
||||
|
||||
<ul class="wy-breadcrumbs">
|
||||
|
||||
<li><a href="../../../index.html">Docs</a> »</li>
|
||||
|
||||
<li><a href="../../index.html">Module code</a> »</li>
|
||||
|
||||
<li>rl_coach.environments.doom_environment</li>
|
||||
|
||||
|
||||
<li class="wy-breadcrumbs-aside">
|
||||
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
|
||||
|
||||
<hr/>
|
||||
</div>
|
||||
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
|
||||
<div itemprop="articleBody">
|
||||
|
||||
<h1>Source code for rl_coach.environments.doom_environment</h1><div class="highlight"><pre>
|
||||
<span></span><span class="c1">#</span>
|
||||
<span class="c1"># Copyright (c) 2017 Intel Corporation</span>
|
||||
<span class="c1">#</span>
|
||||
<span class="c1"># Licensed under the Apache License, Version 2.0 (the "License");</span>
|
||||
<span class="c1"># you may not use this file except in compliance with the License.</span>
|
||||
<span class="c1"># You may obtain a copy of the License at</span>
|
||||
<span class="c1">#</span>
|
||||
<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
|
||||
<span class="c1">#</span>
|
||||
<span class="c1"># Unless required by applicable law or agreed to in writing, software</span>
|
||||
<span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span>
|
||||
<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
|
||||
<span class="c1"># See the License for the specific language governing permissions and</span>
|
||||
<span class="c1"># limitations under the License.</span>
|
||||
<span class="c1">#</span>
|
||||
|
||||
<span class="k">try</span><span class="p">:</span>
|
||||
<span class="kn">import</span> <span class="nn">vizdoom</span>
|
||||
<span class="k">except</span> <span class="ne">ImportError</span><span class="p">:</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.logger</span> <span class="k">import</span> <span class="n">failed_imports</span>
|
||||
<span class="n">failed_imports</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s2">"ViZDoom"</span><span class="p">)</span>
|
||||
|
||||
<span class="kn">import</span> <span class="nn">os</span>
|
||||
<span class="kn">from</span> <span class="nn">enum</span> <span class="k">import</span> <span class="n">Enum</span>
|
||||
<span class="kn">from</span> <span class="nn">os</span> <span class="k">import</span> <span class="n">path</span><span class="p">,</span> <span class="n">environ</span>
|
||||
<span class="kn">from</span> <span class="nn">typing</span> <span class="k">import</span> <span class="n">Union</span><span class="p">,</span> <span class="n">List</span>
|
||||
|
||||
<span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
|
||||
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.base_parameters</span> <span class="k">import</span> <span class="n">VisualizationParameters</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.environments.environment</span> <span class="k">import</span> <span class="n">Environment</span><span class="p">,</span> <span class="n">EnvironmentParameters</span><span class="p">,</span> <span class="n">LevelSelection</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.filters.action.full_discrete_action_space_map</span> <span class="k">import</span> <span class="n">FullDiscreteActionSpaceMap</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.filters.filter</span> <span class="k">import</span> <span class="n">InputFilter</span><span class="p">,</span> <span class="n">OutputFilter</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.filters.observation.observation_rescale_to_size_filter</span> <span class="k">import</span> <span class="n">ObservationRescaleToSizeFilter</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.filters.observation.observation_rgb_to_y_filter</span> <span class="k">import</span> <span class="n">ObservationRGBToYFilter</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.filters.observation.observation_stacking_filter</span> <span class="k">import</span> <span class="n">ObservationStackingFilter</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.filters.observation.observation_to_uint8_filter</span> <span class="k">import</span> <span class="n">ObservationToUInt8Filter</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.spaces</span> <span class="k">import</span> <span class="n">MultiSelectActionSpace</span><span class="p">,</span> <span class="n">ImageObservationSpace</span><span class="p">,</span> \
|
||||
<span class="n">VectorObservationSpace</span><span class="p">,</span> <span class="n">StateSpace</span>
|
||||
|
||||
|
||||
<span class="c1"># enum of the available levels and their path</span>
|
||||
<span class="k">class</span> <span class="nc">DoomLevel</span><span class="p">(</span><span class="n">Enum</span><span class="p">):</span>
|
||||
<span class="n">BASIC</span> <span class="o">=</span> <span class="s2">"basic.cfg"</span>
|
||||
<span class="n">DEFEND</span> <span class="o">=</span> <span class="s2">"defend_the_center.cfg"</span>
|
||||
<span class="n">DEATHMATCH</span> <span class="o">=</span> <span class="s2">"deathmatch.cfg"</span>
|
||||
<span class="n">MY_WAY_HOME</span> <span class="o">=</span> <span class="s2">"my_way_home.cfg"</span>
|
||||
<span class="n">TAKE_COVER</span> <span class="o">=</span> <span class="s2">"take_cover.cfg"</span>
|
||||
<span class="n">HEALTH_GATHERING</span> <span class="o">=</span> <span class="s2">"health_gathering.cfg"</span>
|
||||
<span class="n">HEALTH_GATHERING_SUPREME_COACH_LOCAL</span> <span class="o">=</span> <span class="s2">"D2_navigation.cfg"</span> <span class="c1"># from https://github.com/IntelVCL/DirectFuturePrediction/tree/master/maps</span>
|
||||
<span class="n">DEFEND_THE_LINE</span> <span class="o">=</span> <span class="s2">"defend_the_line.cfg"</span>
|
||||
<span class="n">DEADLY_CORRIDOR</span> <span class="o">=</span> <span class="s2">"deadly_corridor.cfg"</span>
|
||||
<span class="n">BATTLE_COACH_LOCAL</span> <span class="o">=</span> <span class="s2">"D3_battle.cfg"</span> <span class="c1"># from https://github.com/IntelVCL/DirectFuturePrediction/tree/master/maps</span>
|
||||
|
||||
<span class="n">key_map</span> <span class="o">=</span> <span class="p">{</span>
|
||||
<span class="s1">'NO-OP'</span><span class="p">:</span> <span class="mi">96</span><span class="p">,</span> <span class="c1"># `</span>
|
||||
<span class="s1">'ATTACK'</span><span class="p">:</span> <span class="mi">13</span><span class="p">,</span> <span class="c1"># enter</span>
|
||||
<span class="s1">'CROUCH'</span><span class="p">:</span> <span class="mi">306</span><span class="p">,</span> <span class="c1"># ctrl</span>
|
||||
<span class="s1">'DROP_SELECTED_ITEM'</span><span class="p">:</span> <span class="nb">ord</span><span class="p">(</span><span class="s2">"t"</span><span class="p">),</span>
|
||||
<span class="s1">'DROP_SELECTED_WEAPON'</span><span class="p">:</span> <span class="nb">ord</span><span class="p">(</span><span class="s2">"t"</span><span class="p">),</span>
|
||||
<span class="s1">'JUMP'</span><span class="p">:</span> <span class="mi">32</span><span class="p">,</span> <span class="c1"># spacebar</span>
|
||||
<span class="s1">'LAND'</span><span class="p">:</span> <span class="nb">ord</span><span class="p">(</span><span class="s2">"l"</span><span class="p">),</span>
|
||||
<span class="s1">'LOOK_DOWN'</span><span class="p">:</span> <span class="mi">274</span><span class="p">,</span> <span class="c1"># down arrow</span>
|
||||
<span class="s1">'LOOK_UP'</span><span class="p">:</span> <span class="mi">273</span><span class="p">,</span> <span class="c1"># up arrow</span>
|
||||
<span class="s1">'MOVE_BACKWARD'</span><span class="p">:</span> <span class="nb">ord</span><span class="p">(</span><span class="s2">"s"</span><span class="p">),</span>
|
||||
<span class="s1">'MOVE_DOWN'</span><span class="p">:</span> <span class="nb">ord</span><span class="p">(</span><span class="s2">"s"</span><span class="p">),</span>
|
||||
<span class="s1">'MOVE_FORWARD'</span><span class="p">:</span> <span class="nb">ord</span><span class="p">(</span><span class="s2">"w"</span><span class="p">),</span>
|
||||
<span class="s1">'MOVE_LEFT'</span><span class="p">:</span> <span class="mi">276</span><span class="p">,</span>
|
||||
<span class="s1">'MOVE_RIGHT'</span><span class="p">:</span> <span class="mi">275</span><span class="p">,</span>
|
||||
<span class="s1">'MOVE_UP'</span><span class="p">:</span> <span class="nb">ord</span><span class="p">(</span><span class="s2">"w"</span><span class="p">),</span>
|
||||
<span class="s1">'RELOAD'</span><span class="p">:</span> <span class="nb">ord</span><span class="p">(</span><span class="s2">"r"</span><span class="p">),</span>
|
||||
<span class="s1">'SELECT_NEXT_WEAPON'</span><span class="p">:</span> <span class="nb">ord</span><span class="p">(</span><span class="s2">"q"</span><span class="p">),</span>
|
||||
<span class="s1">'SELECT_PREV_WEAPON'</span><span class="p">:</span> <span class="nb">ord</span><span class="p">(</span><span class="s2">"e"</span><span class="p">),</span>
|
||||
<span class="s1">'SELECT_WEAPON0'</span><span class="p">:</span> <span class="nb">ord</span><span class="p">(</span><span class="s2">"0"</span><span class="p">),</span>
|
||||
<span class="s1">'SELECT_WEAPON1'</span><span class="p">:</span> <span class="nb">ord</span><span class="p">(</span><span class="s2">"1"</span><span class="p">),</span>
|
||||
<span class="s1">'SELECT_WEAPON2'</span><span class="p">:</span> <span class="nb">ord</span><span class="p">(</span><span class="s2">"2"</span><span class="p">),</span>
|
||||
<span class="s1">'SELECT_WEAPON3'</span><span class="p">:</span> <span class="nb">ord</span><span class="p">(</span><span class="s2">"3"</span><span class="p">),</span>
|
||||
<span class="s1">'SELECT_WEAPON4'</span><span class="p">:</span> <span class="nb">ord</span><span class="p">(</span><span class="s2">"4"</span><span class="p">),</span>
|
||||
<span class="s1">'SELECT_WEAPON5'</span><span class="p">:</span> <span class="nb">ord</span><span class="p">(</span><span class="s2">"5"</span><span class="p">),</span>
|
||||
<span class="s1">'SELECT_WEAPON6'</span><span class="p">:</span> <span class="nb">ord</span><span class="p">(</span><span class="s2">"6"</span><span class="p">),</span>
|
||||
<span class="s1">'SELECT_WEAPON7'</span><span class="p">:</span> <span class="nb">ord</span><span class="p">(</span><span class="s2">"7"</span><span class="p">),</span>
|
||||
<span class="s1">'SELECT_WEAPON8'</span><span class="p">:</span> <span class="nb">ord</span><span class="p">(</span><span class="s2">"8"</span><span class="p">),</span>
|
||||
<span class="s1">'SELECT_WEAPON9'</span><span class="p">:</span> <span class="nb">ord</span><span class="p">(</span><span class="s2">"9"</span><span class="p">),</span>
|
||||
<span class="s1">'SPEED'</span><span class="p">:</span> <span class="mi">304</span><span class="p">,</span> <span class="c1"># shift</span>
|
||||
<span class="s1">'STRAFE'</span><span class="p">:</span> <span class="mi">9</span><span class="p">,</span> <span class="c1"># tab</span>
|
||||
<span class="s1">'TURN180'</span><span class="p">:</span> <span class="nb">ord</span><span class="p">(</span><span class="s2">"u"</span><span class="p">),</span>
|
||||
<span class="s1">'TURN_LEFT'</span><span class="p">:</span> <span class="nb">ord</span><span class="p">(</span><span class="s2">"a"</span><span class="p">),</span> <span class="c1"># left arrow</span>
|
||||
<span class="s1">'TURN_RIGHT'</span><span class="p">:</span> <span class="nb">ord</span><span class="p">(</span><span class="s2">"d"</span><span class="p">),</span> <span class="c1"># right arrow</span>
|
||||
<span class="s1">'USE'</span><span class="p">:</span> <span class="nb">ord</span><span class="p">(</span><span class="s2">"f"</span><span class="p">),</span>
|
||||
<span class="p">}</span>
|
||||
|
||||
|
||||
<span class="n">DoomInputFilter</span> <span class="o">=</span> <span class="n">InputFilter</span><span class="p">(</span><span class="n">is_a_reference_filter</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||||
<span class="n">DoomInputFilter</span><span class="o">.</span><span class="n">add_observation_filter</span><span class="p">(</span><span class="s1">'observation'</span><span class="p">,</span> <span class="s1">'rescaling'</span><span class="p">,</span>
|
||||
<span class="n">ObservationRescaleToSizeFilter</span><span class="p">(</span><span class="n">ImageObservationSpace</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="mi">60</span><span class="p">,</span> <span class="mi">76</span><span class="p">,</span> <span class="mi">3</span><span class="p">]),</span>
|
||||
<span class="n">high</span><span class="o">=</span><span class="mi">255</span><span class="p">)))</span>
|
||||
<span class="n">DoomInputFilter</span><span class="o">.</span><span class="n">add_observation_filter</span><span class="p">(</span><span class="s1">'observation'</span><span class="p">,</span> <span class="s1">'to_grayscale'</span><span class="p">,</span> <span class="n">ObservationRGBToYFilter</span><span class="p">())</span>
|
||||
<span class="n">DoomInputFilter</span><span class="o">.</span><span class="n">add_observation_filter</span><span class="p">(</span><span class="s1">'observation'</span><span class="p">,</span> <span class="s1">'to_uint8'</span><span class="p">,</span> <span class="n">ObservationToUInt8Filter</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">255</span><span class="p">))</span>
|
||||
<span class="n">DoomInputFilter</span><span class="o">.</span><span class="n">add_observation_filter</span><span class="p">(</span><span class="s1">'observation'</span><span class="p">,</span> <span class="s1">'stacking'</span><span class="p">,</span> <span class="n">ObservationStackingFilter</span><span class="p">(</span><span class="mi">3</span><span class="p">))</span>
|
||||
|
||||
|
||||
<span class="n">DoomOutputFilter</span> <span class="o">=</span> <span class="n">OutputFilter</span><span class="p">(</span><span class="n">is_a_reference_filter</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||||
<span class="n">DoomOutputFilter</span><span class="o">.</span><span class="n">add_action_filter</span><span class="p">(</span><span class="s1">'to_discrete'</span><span class="p">,</span> <span class="n">FullDiscreteActionSpaceMap</span><span class="p">())</span>
|
||||
|
||||
|
||||
<span class="k">class</span> <span class="nc">DoomEnvironmentParameters</span><span class="p">(</span><span class="n">EnvironmentParameters</span><span class="p">):</span>
|
||||
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">level</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">level</span><span class="o">=</span><span class="n">level</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">default_input_filter</span> <span class="o">=</span> <span class="n">DoomInputFilter</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">default_output_filter</span> <span class="o">=</span> <span class="n">DoomOutputFilter</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">cameras</span> <span class="o">=</span> <span class="p">[</span><span class="n">DoomEnvironment</span><span class="o">.</span><span class="n">CameraTypes</span><span class="o">.</span><span class="n">OBSERVATION</span><span class="p">]</span>
|
||||
|
||||
<span class="nd">@property</span>
|
||||
<span class="k">def</span> <span class="nf">path</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="k">return</span> <span class="s1">'rl_coach.environments.doom_environment:DoomEnvironment'</span>
|
||||
|
||||
|
||||
<div class="viewcode-block" id="DoomEnvironment"><a class="viewcode-back" href="../../../components/environments/index.html#rl_coach.environments.doom_environment.DoomEnvironment">[docs]</a><span class="k">class</span> <span class="nc">DoomEnvironment</span><span class="p">(</span><span class="n">Environment</span><span class="p">):</span>
|
||||
<span class="k">class</span> <span class="nc">CameraTypes</span><span class="p">(</span><span class="n">Enum</span><span class="p">):</span>
|
||||
<span class="n">OBSERVATION</span> <span class="o">=</span> <span class="p">(</span><span class="s2">"observation"</span><span class="p">,</span> <span class="s2">"screen_buffer"</span><span class="p">)</span>
|
||||
<span class="n">DEPTH</span> <span class="o">=</span> <span class="p">(</span><span class="s2">"depth"</span><span class="p">,</span> <span class="s2">"depth_buffer"</span><span class="p">)</span>
|
||||
<span class="n">LABELS</span> <span class="o">=</span> <span class="p">(</span><span class="s2">"labels"</span><span class="p">,</span> <span class="s2">"labels_buffer"</span><span class="p">)</span>
|
||||
<span class="n">MAP</span> <span class="o">=</span> <span class="p">(</span><span class="s2">"map"</span><span class="p">,</span> <span class="s2">"automap_buffer"</span><span class="p">)</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">level</span><span class="p">:</span> <span class="n">LevelSelection</span><span class="p">,</span> <span class="n">seed</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">frame_skip</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">human_control</span><span class="p">:</span> <span class="nb">bool</span><span class="p">,</span>
|
||||
<span class="n">custom_reward_threshold</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">],</span> <span class="n">visualization_parameters</span><span class="p">:</span> <span class="n">VisualizationParameters</span><span class="p">,</span>
|
||||
<span class="n">cameras</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="n">CameraTypes</span><span class="p">],</span> <span class="n">target_success_rate</span><span class="p">:</span> <span class="nb">float</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> :param level: (str)</span>
|
||||
<span class="sd"> A string representing the doom level to run. This can also be a LevelSelection object.</span>
|
||||
<span class="sd"> This should be one of the levels defined in the DoomLevel enum. For example, HEALTH_GATHERING.</span>
|
||||
|
||||
<span class="sd"> :param seed: (int)</span>
|
||||
<span class="sd"> A seed to use for the random number generator when running the environment.</span>
|
||||
|
||||
<span class="sd"> :param frame_skip: (int)</span>
|
||||
<span class="sd"> The number of frames to skip between any two actions given by the agent. The action will be repeated</span>
|
||||
<span class="sd"> for all the skipped frames.</span>
|
||||
|
||||
<span class="sd"> :param human_control: (bool)</span>
|
||||
<span class="sd"> A flag that allows controlling the environment using the keyboard keys.</span>
|
||||
|
||||
<span class="sd"> :param custom_reward_threshold: (float)</span>
|
||||
<span class="sd"> Allows defining a custom reward that will be used to decide when the agent succeeded in passing the environment.</span>
|
||||
|
||||
<span class="sd"> :param visualization_parameters: (VisualizationParameters)</span>
|
||||
<span class="sd"> The parameters used for visualizing the environment, such as the render flag, storing videos etc.</span>
|
||||
|
||||
<span class="sd"> :param cameras: (List[CameraTypes])</span>
|
||||
<span class="sd"> A list of camera types to use as observation in the state returned from the environment.</span>
|
||||
<span class="sd"> Each camera should be an enum from CameraTypes, and there are several options like an RGB observation,</span>
|
||||
<span class="sd"> a depth map, a segmentation map, and a top down map of the enviornment.</span>
|
||||
|
||||
<span class="sd"> :param target_success_rate: (float)</span>
|
||||
<span class="sd"> Stop experiment if given target success rate was achieved.</span>
|
||||
|
||||
<span class="sd"> """</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">level</span><span class="p">,</span> <span class="n">seed</span><span class="p">,</span> <span class="n">frame_skip</span><span class="p">,</span> <span class="n">human_control</span><span class="p">,</span> <span class="n">custom_reward_threshold</span><span class="p">,</span> <span class="n">visualization_parameters</span><span class="p">,</span> <span class="n">target_success_rate</span><span class="p">)</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">cameras</span> <span class="o">=</span> <span class="n">cameras</span>
|
||||
|
||||
<span class="c1"># load the emulator with the required level</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">level</span> <span class="o">=</span> <span class="n">DoomLevel</span><span class="p">[</span><span class="n">level</span><span class="o">.</span><span class="n">upper</span><span class="p">()]</span>
|
||||
<span class="n">local_scenarios_path</span> <span class="o">=</span> <span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">dirname</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">realpath</span><span class="p">(</span><span class="vm">__file__</span><span class="p">)),</span> <span class="s1">'doom'</span><span class="p">)</span>
|
||||
<span class="k">if</span> <span class="s1">'COACH_LOCAL'</span> <span class="ow">in</span> <span class="n">level</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">scenarios_dir</span> <span class="o">=</span> <span class="n">local_scenarios_path</span>
|
||||
<span class="k">elif</span> <span class="s1">'VIZDOOM_ROOT'</span> <span class="ow">in</span> <span class="n">environ</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">scenarios_dir</span> <span class="o">=</span> <span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">environ</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'VIZDOOM_ROOT'</span><span class="p">),</span> <span class="s1">'scenarios'</span><span class="p">)</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">scenarios_dir</span> <span class="o">=</span> <span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">dirname</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">realpath</span><span class="p">(</span><span class="n">vizdoom</span><span class="o">.</span><span class="vm">__file__</span><span class="p">)),</span> <span class="s1">'scenarios'</span><span class="p">)</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">game</span> <span class="o">=</span> <span class="n">vizdoom</span><span class="o">.</span><span class="n">DoomGame</span><span class="p">()</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="o">.</span><span class="n">load_config</span><span class="p">(</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">scenarios_dir</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">level</span><span class="o">.</span><span class="n">value</span><span class="p">))</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="o">.</span><span class="n">set_window_visible</span><span class="p">(</span><span class="kc">False</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="o">.</span><span class="n">add_game_args</span><span class="p">(</span><span class="s2">"+vid_forcesurface 1"</span><span class="p">)</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">wait_for_explicit_human_action</span> <span class="o">=</span> <span class="kc">True</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">human_control</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="o">.</span><span class="n">set_screen_resolution</span><span class="p">(</span><span class="n">vizdoom</span><span class="o">.</span><span class="n">ScreenResolution</span><span class="o">.</span><span class="n">RES_640X480</span><span class="p">)</span>
|
||||
<span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_rendered</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="o">.</span><span class="n">set_screen_resolution</span><span class="p">(</span><span class="n">vizdoom</span><span class="o">.</span><span class="n">ScreenResolution</span><span class="o">.</span><span class="n">RES_320X240</span><span class="p">)</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="c1"># lower resolution since we actually take only 76x60 and we don't need to render</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="o">.</span><span class="n">set_screen_resolution</span><span class="p">(</span><span class="n">vizdoom</span><span class="o">.</span><span class="n">ScreenResolution</span><span class="o">.</span><span class="n">RES_160X120</span><span class="p">)</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="o">.</span><span class="n">set_render_hud</span><span class="p">(</span><span class="kc">False</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="o">.</span><span class="n">set_render_crosshair</span><span class="p">(</span><span class="kc">False</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="o">.</span><span class="n">set_render_decals</span><span class="p">(</span><span class="kc">False</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="o">.</span><span class="n">set_render_particles</span><span class="p">(</span><span class="kc">False</span><span class="p">)</span>
|
||||
<span class="k">for</span> <span class="n">camera</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">cameras</span><span class="p">:</span>
|
||||
<span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="p">,</span> <span class="s1">'set_</span><span class="si">{}</span><span class="s1">_enabled'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">camera</span><span class="o">.</span><span class="n">value</span><span class="p">[</span><span class="mi">1</span><span class="p">])):</span>
|
||||
<span class="nb">getattr</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="p">,</span> <span class="s1">'set_</span><span class="si">{}</span><span class="s1">_enabled'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">camera</span><span class="o">.</span><span class="n">value</span><span class="p">[</span><span class="mi">1</span><span class="p">]))(</span><span class="kc">True</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="o">.</span><span class="n">init</span><span class="p">()</span>
|
||||
|
||||
<span class="c1"># actions</span>
|
||||
<span class="n">actions_description</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'NO-OP'</span><span class="p">]</span>
|
||||
<span class="n">actions_description</span> <span class="o">+=</span> <span class="p">[</span><span class="nb">str</span><span class="p">(</span><span class="n">action</span><span class="p">)</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">"."</span><span class="p">)[</span><span class="mi">1</span><span class="p">]</span> <span class="k">for</span> <span class="n">action</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="o">.</span><span class="n">get_available_buttons</span><span class="p">()]</span>
|
||||
<span class="n">actions_description</span> <span class="o">=</span> <span class="n">actions_description</span><span class="p">[::</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">action_space</span> <span class="o">=</span> <span class="n">MultiSelectActionSpace</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="o">.</span><span class="n">get_available_buttons_size</span><span class="p">(),</span>
|
||||
<span class="n">max_simultaneous_selected_actions</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span>
|
||||
<span class="n">descriptions</span><span class="o">=</span><span class="n">actions_description</span><span class="p">,</span>
|
||||
<span class="n">allow_no_action_to_be_selected</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># human control</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">human_control</span><span class="p">:</span>
|
||||
<span class="c1"># TODO: add this to the action space</span>
|
||||
<span class="c1"># map keyboard keys to actions</span>
|
||||
<span class="k">for</span> <span class="n">idx</span><span class="p">,</span> <span class="n">action</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">action_space</span><span class="o">.</span><span class="n">descriptions</span><span class="p">):</span>
|
||||
<span class="k">if</span> <span class="n">action</span> <span class="ow">in</span> <span class="n">key_map</span><span class="o">.</span><span class="n">keys</span><span class="p">():</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">key_to_action</span><span class="p">[(</span><span class="n">key_map</span><span class="p">[</span><span class="n">action</span><span class="p">],)]</span> <span class="o">=</span> <span class="n">idx</span>
|
||||
|
||||
<span class="c1"># states</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">state_space</span> <span class="o">=</span> <span class="n">StateSpace</span><span class="p">({</span>
|
||||
<span class="s2">"measurements"</span><span class="p">:</span> <span class="n">VectorObservationSpace</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="o">.</span><span class="n">get_state</span><span class="p">()</span><span class="o">.</span><span class="n">game_variables</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span>
|
||||
<span class="n">measurements_names</span><span class="o">=</span><span class="p">[</span><span class="nb">str</span><span class="p">(</span><span class="n">m</span><span class="p">)</span> <span class="k">for</span> <span class="n">m</span> <span class="ow">in</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="o">.</span><span class="n">get_available_game_variables</span><span class="p">()])</span>
|
||||
<span class="p">})</span>
|
||||
<span class="k">for</span> <span class="n">camera</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">cameras</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">state_space</span><span class="p">[</span><span class="n">camera</span><span class="o">.</span><span class="n">value</span><span class="p">[</span><span class="mi">0</span><span class="p">]]</span> <span class="o">=</span> <span class="n">ImageObservationSpace</span><span class="p">(</span>
|
||||
<span class="n">shape</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="o">.</span><span class="n">get_screen_height</span><span class="p">(),</span> <span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="o">.</span><span class="n">get_screen_width</span><span class="p">(),</span> <span class="mi">3</span><span class="p">]),</span>
|
||||
<span class="n">high</span><span class="o">=</span><span class="mi">255</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># seed</span>
|
||||
<span class="k">if</span> <span class="n">seed</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="o">.</span><span class="n">set_seed</span><span class="p">(</span><span class="n">seed</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reset_internal_state</span><span class="p">()</span>
|
||||
|
||||
<span class="c1"># render</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_rendered</span><span class="p">:</span>
|
||||
<span class="n">image</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_rendered_image</span><span class="p">()</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">renderer</span><span class="o">.</span><span class="n">create_screen</span><span class="p">(</span><span class="n">image</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n">image</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">target_success_rate</span> <span class="o">=</span> <span class="n">target_success_rate</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_update_state</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="c1"># extract all data from the current state</span>
|
||||
<span class="n">state</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="o">.</span><span class="n">get_state</span><span class="p">()</span>
|
||||
<span class="k">if</span> <span class="n">state</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">state</span><span class="o">.</span><span class="n">screen_buffer</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">measurements</span> <span class="o">=</span> <span class="n">state</span><span class="o">.</span><span class="n">game_variables</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">state</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'measurements'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">measurements</span><span class="p">}</span>
|
||||
<span class="k">for</span> <span class="n">camera</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">cameras</span><span class="p">:</span>
|
||||
<span class="n">observation</span> <span class="o">=</span> <span class="nb">getattr</span><span class="p">(</span><span class="n">state</span><span class="p">,</span> <span class="n">camera</span><span class="o">.</span><span class="n">value</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span>
|
||||
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">observation</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span> <span class="o">==</span> <span class="mi">3</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">state</span><span class="p">[</span><span class="n">camera</span><span class="o">.</span><span class="n">value</span><span class="p">[</span><span class="mi">0</span><span class="p">]]</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">transpose</span><span class="p">(</span><span class="n">observation</span><span class="p">,</span> <span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">0</span><span class="p">))</span>
|
||||
<span class="k">elif</span> <span class="nb">len</span><span class="p">(</span><span class="n">observation</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span> <span class="o">==</span> <span class="mi">2</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">state</span><span class="p">[</span><span class="n">camera</span><span class="o">.</span><span class="n">value</span><span class="p">[</span><span class="mi">0</span><span class="p">]]</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">repeat</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">expand_dims</span><span class="p">(</span><span class="n">observation</span><span class="p">,</span> <span class="o">-</span><span class="mi">1</span><span class="p">),</span> <span class="mi">3</span><span class="p">,</span> <span class="n">axis</span><span class="o">=-</span><span class="mi">1</span><span class="p">)</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reward</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="o">.</span><span class="n">get_last_reward</span><span class="p">()</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">done</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="o">.</span><span class="n">is_episode_finished</span><span class="p">()</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_take_action</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">action</span><span class="p">):</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="o">.</span><span class="n">make_action</span><span class="p">(</span><span class="nb">list</span><span class="p">(</span><span class="n">action</span><span class="p">),</span> <span class="bp">self</span><span class="o">.</span><span class="n">frame_skip</span><span class="p">)</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_restart_environment_episode</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">force_environment_reset</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">game</span><span class="o">.</span><span class="n">new_episode</span><span class="p">()</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">get_rendered_image</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Return a numpy array containing the image that will be rendered to the screen.</span>
|
||||
<span class="sd"> This can be different from the observation. For example, mujoco's observation is a measurements vector.</span>
|
||||
<span class="sd"> :return: numpy array containing the image that will be rendered to the screen</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="n">image</span> <span class="o">=</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">state</span><span class="p">[</span><span class="n">camera</span><span class="o">.</span><span class="n">value</span><span class="p">[</span><span class="mi">0</span><span class="p">]]</span> <span class="k">for</span> <span class="n">camera</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">cameras</span><span class="p">]</span>
|
||||
<span class="n">image</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">vstack</span><span class="p">(</span><span class="n">image</span><span class="p">)</span>
|
||||
<span class="k">return</span> <span class="n">image</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">get_target_success_rate</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span>
|
||||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">target_success_rate</span></div>
|
||||
</pre></div>
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
<footer>
|
||||
|
||||
|
||||
<hr/>
|
||||
|
||||
<div role="contentinfo">
|
||||
<p>
|
||||
© Copyright 2018, Intel AI Lab
|
||||
|
||||
</p>
|
||||
</div>
|
||||
Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
|
||||
|
||||
</footer>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
|
||||
</section>
|
||||
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<script type="text/javascript" id="documentation_options" data-url_root="../../../" src="../../../_static/documentation_options.js"></script>
|
||||
<script type="text/javascript" src="../../../_static/jquery.js"></script>
|
||||
<script type="text/javascript" src="../../../_static/underscore.js"></script>
|
||||
<script type="text/javascript" src="../../../_static/doctools.js"></script>
|
||||
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></script>
|
||||
|
||||
|
||||
|
||||
|
||||
<script type="text/javascript" src="../../../_static/js/theme.js"></script>
|
||||
|
||||
<script type="text/javascript">
|
||||
jQuery(function () {
|
||||
SphinxRtdTheme.Navigation.enable(true);
|
||||
});
|
||||
</script>
|
||||
|
||||
</body>
|
||||
</html>
|
||||
721
docs/_modules/rl_coach/environments/environment.html
Normal file
721
docs/_modules/rl_coach/environments/environment.html
Normal file
@@ -0,0 +1,721 @@
|
||||
|
||||
|
||||
<!DOCTYPE html>
|
||||
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
|
||||
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
|
||||
<head>
|
||||
<meta charset="utf-8">
|
||||
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
|
||||
<title>rl_coach.environments.environment — Reinforcement Learning Coach 0.11.0 documentation</title>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
|
||||
<link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
|
||||
<link rel="stylesheet" href="../../../_static/css/custom.css" type="text/css" />
|
||||
<link rel="index" title="Index" href="../../../genindex.html" />
|
||||
<link rel="search" title="Search" href="../../../search.html" />
|
||||
<link href="../../../_static/css/custom.css" rel="stylesheet" type="text/css">
|
||||
|
||||
|
||||
|
||||
<script src="../../../_static/js/modernizr.min.js"></script>
|
||||
|
||||
</head>
|
||||
|
||||
<body class="wy-body-for-nav">
|
||||
|
||||
|
||||
<div class="wy-grid-for-nav">
|
||||
|
||||
|
||||
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
|
||||
<div class="wy-side-scroll">
|
||||
<div class="wy-side-nav-search">
|
||||
|
||||
|
||||
|
||||
<a href="../../../index.html" class="icon icon-home"> Reinforcement Learning Coach
|
||||
|
||||
|
||||
|
||||
|
||||
<img src="../../../_static/dark_logo.png" class="logo" alt="Logo"/>
|
||||
|
||||
</a>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<div role="search">
|
||||
<form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get">
|
||||
<input type="text" name="q" placeholder="Search docs" />
|
||||
<input type="hidden" name="check_keywords" value="yes" />
|
||||
<input type="hidden" name="area" value="default" />
|
||||
</form>
|
||||
</div>
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<p class="caption"><span class="caption-text">Intro</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../usage.html">Usage</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../features/index.html">Features</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../selecting_an_algorithm.html">Selecting an Algorithm</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../dashboard.html">Coach Dashboard</a></li>
|
||||
</ul>
|
||||
<p class="caption"><span class="caption-text">Design</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../design/control_flow.html">Control Flow</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../design/network.html">Network Design</a></li>
|
||||
</ul>
|
||||
<p class="caption"><span class="caption-text">Contributing</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../contributing/add_agent.html">Adding a New Agent</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../contributing/add_env.html">Adding a New Environment</a></li>
|
||||
</ul>
|
||||
<p class="caption"><span class="caption-text">Components</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/agents/index.html">Agents</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/architectures/index.html">Architectures</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/environments/index.html">Environments</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/exploration_policies/index.html">Exploration Policies</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/filters/index.html">Filters</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/memories/index.html">Memories</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/core_types.html">Core Types</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/spaces.html">Spaces</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/additional_parameters.html">Additional Parameters</a></li>
|
||||
</ul>
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
</nav>
|
||||
|
||||
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
|
||||
|
||||
|
||||
<nav class="wy-nav-top" aria-label="top navigation">
|
||||
|
||||
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
|
||||
<a href="../../../index.html">Reinforcement Learning Coach</a>
|
||||
|
||||
</nav>
|
||||
|
||||
|
||||
<div class="wy-nav-content">
|
||||
|
||||
<div class="rst-content">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<div role="navigation" aria-label="breadcrumbs navigation">
|
||||
|
||||
<ul class="wy-breadcrumbs">
|
||||
|
||||
<li><a href="../../../index.html">Docs</a> »</li>
|
||||
|
||||
<li><a href="../../index.html">Module code</a> »</li>
|
||||
|
||||
<li>rl_coach.environments.environment</li>
|
||||
|
||||
|
||||
<li class="wy-breadcrumbs-aside">
|
||||
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
|
||||
|
||||
<hr/>
|
||||
</div>
|
||||
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
|
||||
<div itemprop="articleBody">
|
||||
|
||||
<h1>Source code for rl_coach.environments.environment</h1><div class="highlight"><pre>
|
||||
<span></span><span class="c1">#</span>
|
||||
<span class="c1"># Copyright (c) 2017 Intel Corporation</span>
|
||||
<span class="c1">#</span>
|
||||
<span class="c1"># Licensed under the Apache License, Version 2.0 (the "License");</span>
|
||||
<span class="c1"># you may not use this file except in compliance with the License.</span>
|
||||
<span class="c1"># You may obtain a copy of the License at</span>
|
||||
<span class="c1">#</span>
|
||||
<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
|
||||
<span class="c1">#</span>
|
||||
<span class="c1"># Unless required by applicable law or agreed to in writing, software</span>
|
||||
<span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span>
|
||||
<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
|
||||
<span class="c1"># See the License for the specific language governing permissions and</span>
|
||||
<span class="c1"># limitations under the License.</span>
|
||||
<span class="c1">#</span>
|
||||
|
||||
<span class="kn">import</span> <span class="nn">operator</span>
|
||||
<span class="kn">import</span> <span class="nn">time</span>
|
||||
<span class="kn">from</span> <span class="nn">collections</span> <span class="k">import</span> <span class="n">OrderedDict</span>
|
||||
<span class="kn">from</span> <span class="nn">typing</span> <span class="k">import</span> <span class="n">Union</span><span class="p">,</span> <span class="n">List</span><span class="p">,</span> <span class="n">Tuple</span><span class="p">,</span> <span class="n">Dict</span>
|
||||
|
||||
<span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
|
||||
|
||||
<span class="kn">from</span> <span class="nn">rl_coach</span> <span class="k">import</span> <span class="n">logger</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.base_parameters</span> <span class="k">import</span> <span class="n">Parameters</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.base_parameters</span> <span class="k">import</span> <span class="n">VisualizationParameters</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.core_types</span> <span class="k">import</span> <span class="n">GoalType</span><span class="p">,</span> <span class="n">ActionType</span><span class="p">,</span> <span class="n">EnvResponse</span><span class="p">,</span> <span class="n">RunPhase</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.environments.environment_interface</span> <span class="k">import</span> <span class="n">EnvironmentInterface</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.logger</span> <span class="k">import</span> <span class="n">screen</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.renderer</span> <span class="k">import</span> <span class="n">Renderer</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.spaces</span> <span class="k">import</span> <span class="n">ActionSpace</span><span class="p">,</span> <span class="n">ObservationSpace</span><span class="p">,</span> <span class="n">DiscreteActionSpace</span><span class="p">,</span> <span class="n">RewardSpace</span><span class="p">,</span> <span class="n">StateSpace</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.utils</span> <span class="k">import</span> <span class="n">squeeze_list</span><span class="p">,</span> <span class="n">force_list</span>
|
||||
|
||||
|
||||
<span class="k">class</span> <span class="nc">LevelSelection</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
|
||||
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">level</span><span class="p">:</span> <span class="nb">str</span><span class="p">):</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">selected_level</span> <span class="o">=</span> <span class="n">level</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">select</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">level</span><span class="p">:</span> <span class="nb">str</span><span class="p">):</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">selected_level</span> <span class="o">=</span> <span class="n">level</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">__str__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">selected_level</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="n">logger</span><span class="o">.</span><span class="n">screen</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="s2">"No level has been selected. Please select a level using the -lvl command line flag, "</span>
|
||||
<span class="s2">"or change the level in the preset."</span><span class="p">,</span> <span class="n">crash</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">selected_level</span>
|
||||
|
||||
|
||||
<span class="k">class</span> <span class="nc">SingleLevelSelection</span><span class="p">(</span><span class="n">LevelSelection</span><span class="p">):</span>
|
||||
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">levels</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">List</span><span class="p">[</span><span class="nb">str</span><span class="p">],</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">str</span><span class="p">]]):</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="kc">None</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">levels</span> <span class="o">=</span> <span class="n">levels</span>
|
||||
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">levels</span><span class="p">,</span> <span class="nb">list</span><span class="p">):</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">levels</span> <span class="o">=</span> <span class="p">{</span><span class="n">level</span><span class="p">:</span> <span class="n">level</span> <span class="k">for</span> <span class="n">level</span> <span class="ow">in</span> <span class="n">levels</span><span class="p">}</span>
|
||||
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">levels</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">levels</span> <span class="o">=</span> <span class="p">{</span><span class="n">levels</span><span class="p">:</span> <span class="n">levels</span><span class="p">}</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">__str__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">selected_level</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="n">logger</span><span class="o">.</span><span class="n">screen</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="s2">"No level has been selected. Please select a level using the -lvl command line flag, "</span>
|
||||
<span class="s2">"or change the level in the preset. </span><span class="se">\n</span><span class="s2">The available levels are: </span><span class="se">\n</span><span class="si">{}</span><span class="s2">"</span>
|
||||
<span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="s1">', '</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="nb">sorted</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">levels</span><span class="o">.</span><span class="n">keys</span><span class="p">()))),</span> <span class="n">crash</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">selected_level</span> <span class="ow">not</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">levels</span><span class="o">.</span><span class="n">keys</span><span class="p">():</span>
|
||||
<span class="n">logger</span><span class="o">.</span><span class="n">screen</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="s2">"The selected level (</span><span class="si">{}</span><span class="s2">) is not part of the available levels (</span><span class="si">{}</span><span class="s2">)"</span>
|
||||
<span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">selected_level</span><span class="p">,</span> <span class="s1">', '</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">levels</span><span class="o">.</span><span class="n">keys</span><span class="p">())),</span> <span class="n">crash</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">levels</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">selected_level</span><span class="p">]</span>
|
||||
|
||||
|
||||
<span class="c1"># class SingleLevelPerPhase(LevelSelection):</span>
|
||||
<span class="c1"># def __init__(self, levels: Dict[RunPhase, str]):</span>
|
||||
<span class="c1"># super().__init__(None)</span>
|
||||
<span class="c1"># self.levels = levels</span>
|
||||
<span class="c1">#</span>
|
||||
<span class="c1"># def __str__(self):</span>
|
||||
<span class="c1"># super().__str__()</span>
|
||||
<span class="c1"># if self.selected_level not in self.levels.keys():</span>
|
||||
<span class="c1"># logger.screen.error("The selected level ({}) is not part of the available levels ({})"</span>
|
||||
<span class="c1"># .format(self.selected_level, self.levels.keys()), crash=True)</span>
|
||||
<span class="c1"># return self.levels[self.selected_level]</span>
|
||||
|
||||
|
||||
<span class="k">class</span> <span class="nc">CustomWrapper</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
|
||||
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">environment</span><span class="p">):</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">environment</span> <span class="o">=</span> <span class="n">environment</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">__getattr__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">attr</span><span class="p">):</span>
|
||||
<span class="k">if</span> <span class="n">attr</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="vm">__dict__</span><span class="p">:</span>
|
||||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="vm">__dict__</span><span class="p">[</span><span class="n">attr</span><span class="p">]</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="k">return</span> <span class="nb">getattr</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">environment</span><span class="p">,</span> <span class="n">attr</span><span class="p">,</span> <span class="kc">False</span><span class="p">)</span>
|
||||
|
||||
|
||||
<span class="k">class</span> <span class="nc">EnvironmentParameters</span><span class="p">(</span><span class="n">Parameters</span><span class="p">):</span>
|
||||
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">level</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">level</span> <span class="o">=</span> <span class="n">level</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">frame_skip</span> <span class="o">=</span> <span class="mi">4</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">seed</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">human_control</span> <span class="o">=</span> <span class="kc">False</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">custom_reward_threshold</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">default_input_filter</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">default_output_filter</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">experiment_path</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
|
||||
<span class="c1"># Set target reward and target_success if present</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">target_success_rate</span> <span class="o">=</span> <span class="mf">1.0</span>
|
||||
|
||||
<span class="nd">@property</span>
|
||||
<span class="k">def</span> <span class="nf">path</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="k">return</span> <span class="s1">'rl_coach.environments.environment:Environment'</span>
|
||||
|
||||
|
||||
<div class="viewcode-block" id="Environment"><a class="viewcode-back" href="../../../components/environments/index.html#rl_coach.environments.environment.Environment">[docs]</a><span class="k">class</span> <span class="nc">Environment</span><span class="p">(</span><span class="n">EnvironmentInterface</span><span class="p">):</span>
|
||||
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">level</span><span class="p">:</span> <span class="n">LevelSelection</span><span class="p">,</span> <span class="n">seed</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">frame_skip</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">human_control</span><span class="p">:</span> <span class="nb">bool</span><span class="p">,</span>
|
||||
<span class="n">custom_reward_threshold</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">],</span> <span class="n">visualization_parameters</span><span class="p">:</span> <span class="n">VisualizationParameters</span><span class="p">,</span>
|
||||
<span class="n">target_success_rate</span><span class="p">:</span> <span class="nb">float</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> :param level: The environment level. Each environment can have multiple levels</span>
|
||||
<span class="sd"> :param seed: a seed for the random number generator of the environment</span>
|
||||
<span class="sd"> :param frame_skip: number of frames to skip (while repeating the same action) between each two agent directives</span>
|
||||
<span class="sd"> :param human_control: human should control the environment</span>
|
||||
<span class="sd"> :param visualization_parameters: a blob of parameters used for visualization of the environment</span>
|
||||
<span class="sd"> :param **kwargs: as the class is instantiated by EnvironmentParameters, this is used to support having</span>
|
||||
<span class="sd"> additional arguments which will be ignored by this class, but might be used by others</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
|
||||
|
||||
<span class="c1"># env initialization</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">game</span> <span class="o">=</span> <span class="p">[]</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">state</span> <span class="o">=</span> <span class="p">{}</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">observation</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">goal</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reward</span> <span class="o">=</span> <span class="mi">0</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">done</span> <span class="o">=</span> <span class="kc">False</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">info</span> <span class="o">=</span> <span class="p">{}</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_last_env_response</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">last_action</span> <span class="o">=</span> <span class="mi">0</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">episode_idx</span> <span class="o">=</span> <span class="mi">0</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">total_steps_counter</span> <span class="o">=</span> <span class="mi">0</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">current_episode_steps_counter</span> <span class="o">=</span> <span class="mi">0</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">last_episode_time</span> <span class="o">=</span> <span class="n">time</span><span class="o">.</span><span class="n">time</span><span class="p">()</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">key_to_action</span> <span class="o">=</span> <span class="p">{}</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">last_episode_images</span> <span class="o">=</span> <span class="p">[]</span>
|
||||
|
||||
<span class="c1"># rewards</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">total_reward_in_current_episode</span> <span class="o">=</span> <span class="mi">0</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">max_reward_achieved</span> <span class="o">=</span> <span class="o">-</span><span class="n">np</span><span class="o">.</span><span class="n">inf</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reward_success_threshold</span> <span class="o">=</span> <span class="n">custom_reward_threshold</span>
|
||||
|
||||
<span class="c1"># spaces</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">state_space</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_state_space</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">goal_space</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_goal_space</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">action_space</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_action_space</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reward_space</span> <span class="o">=</span> <span class="n">RewardSpace</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="n">reward_success_threshold</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">reward_success_threshold</span><span class="p">)</span> <span class="c1"># TODO: add a getter and setter</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">env_id</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">level</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">seed</span> <span class="o">=</span> <span class="n">seed</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">frame_skip</span> <span class="o">=</span> <span class="n">frame_skip</span>
|
||||
|
||||
<span class="c1"># human interaction and visualization</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">human_control</span> <span class="o">=</span> <span class="n">human_control</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">wait_for_explicit_human_action</span> <span class="o">=</span> <span class="kc">False</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">is_rendered</span> <span class="o">=</span> <span class="n">visualization_parameters</span><span class="o">.</span><span class="n">render</span> <span class="ow">or</span> <span class="bp">self</span><span class="o">.</span><span class="n">human_control</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">native_rendering</span> <span class="o">=</span> <span class="n">visualization_parameters</span><span class="o">.</span><span class="n">native_rendering</span> <span class="ow">and</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">human_control</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">visualization_parameters</span> <span class="o">=</span> <span class="n">visualization_parameters</span>
|
||||
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">native_rendering</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">renderer</span> <span class="o">=</span> <span class="n">Renderer</span><span class="p">()</span>
|
||||
|
||||
<span class="c1"># Set target reward and target_success if present</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">target_success_rate</span> <span class="o">=</span> <span class="n">target_success_rate</span>
|
||||
|
||||
<span class="nd">@property</span>
|
||||
<span class="k">def</span> <span class="nf">action_space</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">Union</span><span class="p">[</span><span class="n">List</span><span class="p">[</span><span class="n">ActionSpace</span><span class="p">],</span> <span class="n">ActionSpace</span><span class="p">]:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Get the action space of the environment</span>
|
||||
|
||||
<span class="sd"> :return: the action space</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_action_space</span>
|
||||
|
||||
<span class="nd">@action_space</span><span class="o">.</span><span class="n">setter</span>
|
||||
<span class="k">def</span> <span class="nf">action_space</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">val</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="n">List</span><span class="p">[</span><span class="n">ActionSpace</span><span class="p">],</span> <span class="n">ActionSpace</span><span class="p">]):</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Set the action space of the environment</span>
|
||||
|
||||
<span class="sd"> :return: None</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_action_space</span> <span class="o">=</span> <span class="n">val</span>
|
||||
|
||||
<span class="nd">@property</span>
|
||||
<span class="k">def</span> <span class="nf">state_space</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">Union</span><span class="p">[</span><span class="n">List</span><span class="p">[</span><span class="n">StateSpace</span><span class="p">],</span> <span class="n">StateSpace</span><span class="p">]:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Get the state space of the environment</span>
|
||||
|
||||
<span class="sd"> :return: the observation space</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_state_space</span>
|
||||
|
||||
<span class="nd">@state_space</span><span class="o">.</span><span class="n">setter</span>
|
||||
<span class="k">def</span> <span class="nf">state_space</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">val</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="n">List</span><span class="p">[</span><span class="n">StateSpace</span><span class="p">],</span> <span class="n">StateSpace</span><span class="p">]):</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Set the state space of the environment</span>
|
||||
|
||||
<span class="sd"> :return: None</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_state_space</span> <span class="o">=</span> <span class="n">val</span>
|
||||
|
||||
<span class="nd">@property</span>
|
||||
<span class="k">def</span> <span class="nf">goal_space</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">Union</span><span class="p">[</span><span class="n">List</span><span class="p">[</span><span class="n">ObservationSpace</span><span class="p">],</span> <span class="n">ObservationSpace</span><span class="p">]:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Get the state space of the environment</span>
|
||||
|
||||
<span class="sd"> :return: the observation space</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_goal_space</span>
|
||||
|
||||
<span class="nd">@goal_space</span><span class="o">.</span><span class="n">setter</span>
|
||||
<span class="k">def</span> <span class="nf">goal_space</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">val</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="n">List</span><span class="p">[</span><span class="n">ObservationSpace</span><span class="p">],</span> <span class="n">ObservationSpace</span><span class="p">]):</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Set the goal space of the environment</span>
|
||||
|
||||
<span class="sd"> :return: None</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_goal_space</span> <span class="o">=</span> <span class="n">val</span>
|
||||
|
||||
<div class="viewcode-block" id="Environment.get_action_from_user"><a class="viewcode-back" href="../../../components/environments/index.html#rl_coach.environments.environment.Environment.get_action_from_user">[docs]</a> <span class="k">def</span> <span class="nf">get_action_from_user</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">ActionType</span><span class="p">:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Get an action from the user keyboard</span>
|
||||
|
||||
<span class="sd"> :return: action index</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">wait_for_explicit_human_action</span><span class="p">:</span>
|
||||
<span class="k">while</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">renderer</span><span class="o">.</span><span class="n">pressed_keys</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">renderer</span><span class="o">.</span><span class="n">get_events</span><span class="p">()</span>
|
||||
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">key_to_action</span> <span class="o">==</span> <span class="p">{}:</span>
|
||||
<span class="c1"># the keys are the numbers on the keyboard corresponding to the action index</span>
|
||||
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">renderer</span><span class="o">.</span><span class="n">pressed_keys</span><span class="p">)</span> <span class="o">></span> <span class="mi">0</span><span class="p">:</span>
|
||||
<span class="n">action_idx</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">renderer</span><span class="o">.</span><span class="n">pressed_keys</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">-</span> <span class="nb">ord</span><span class="p">(</span><span class="s2">"1"</span><span class="p">)</span>
|
||||
<span class="k">if</span> <span class="mi">0</span> <span class="o"><=</span> <span class="n">action_idx</span> <span class="o"><</span> <span class="bp">self</span><span class="o">.</span><span class="n">action_space</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]:</span>
|
||||
<span class="k">return</span> <span class="n">action_idx</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="c1"># the keys are mapped through the environment to more intuitive keyboard keys</span>
|
||||
<span class="c1"># key = tuple(self.renderer.pressed_keys)</span>
|
||||
<span class="c1"># for key in self.renderer.pressed_keys:</span>
|
||||
<span class="k">for</span> <span class="n">env_keys</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">key_to_action</span><span class="o">.</span><span class="n">keys</span><span class="p">():</span>
|
||||
<span class="k">if</span> <span class="nb">set</span><span class="p">(</span><span class="n">env_keys</span><span class="p">)</span> <span class="o">==</span> <span class="nb">set</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">renderer</span><span class="o">.</span><span class="n">pressed_keys</span><span class="p">):</span>
|
||||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">action_space</span><span class="o">.</span><span class="n">actions</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">key_to_action</span><span class="p">[</span><span class="n">env_keys</span><span class="p">]]</span>
|
||||
|
||||
<span class="c1"># return the default action 0 so that the environment will continue running</span>
|
||||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">action_space</span><span class="o">.</span><span class="n">default_action</span></div>
|
||||
|
||||
<span class="nd">@property</span>
|
||||
<span class="k">def</span> <span class="nf">last_env_response</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">Union</span><span class="p">[</span><span class="n">List</span><span class="p">[</span><span class="n">EnvResponse</span><span class="p">],</span> <span class="n">EnvResponse</span><span class="p">]:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Get the last environment response</span>
|
||||
|
||||
<span class="sd"> :return: a dictionary that contains the state, reward, etc.</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="k">return</span> <span class="n">squeeze_list</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_last_env_response</span><span class="p">)</span>
|
||||
|
||||
<span class="nd">@last_env_response</span><span class="o">.</span><span class="n">setter</span>
|
||||
<span class="k">def</span> <span class="nf">last_env_response</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">val</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="n">List</span><span class="p">[</span><span class="n">EnvResponse</span><span class="p">],</span> <span class="n">EnvResponse</span><span class="p">]):</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Set the last environment response</span>
|
||||
|
||||
<span class="sd"> :param val: the last environment response</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_last_env_response</span> <span class="o">=</span> <span class="n">force_list</span><span class="p">(</span><span class="n">val</span><span class="p">)</span>
|
||||
|
||||
<div class="viewcode-block" id="Environment.step"><a class="viewcode-back" href="../../../components/environments/index.html#rl_coach.environments.environment.Environment.step">[docs]</a> <span class="k">def</span> <span class="nf">step</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">action</span><span class="p">:</span> <span class="n">ActionType</span><span class="p">)</span> <span class="o">-></span> <span class="n">EnvResponse</span><span class="p">:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Make a single step in the environment using the given action</span>
|
||||
|
||||
<span class="sd"> :param action: an action to use for stepping the environment. Should follow the definition of the action space.</span>
|
||||
<span class="sd"> :return: the environment response as returned in get_last_env_response</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="n">action</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">action_space</span><span class="o">.</span><span class="n">clip_action_to_space</span><span class="p">(</span><span class="n">action</span><span class="p">)</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">action_space</span> <span class="ow">and</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">action_space</span><span class="o">.</span><span class="n">val_matches_space_definition</span><span class="p">(</span><span class="n">action</span><span class="p">):</span>
|
||||
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"The given action does not match the action space definition. "</span>
|
||||
<span class="s2">"Action = </span><span class="si">{}</span><span class="s2">, action space definition = </span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">action</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">action_space</span><span class="p">))</span>
|
||||
|
||||
<span class="c1"># store the last agent action done and allow passing None actions to repeat the previously done action</span>
|
||||
<span class="k">if</span> <span class="n">action</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="n">action</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">last_action</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">last_action</span> <span class="o">=</span> <span class="n">action</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">visualization_parameters</span><span class="o">.</span><span class="n">add_rendered_image_to_env_response</span><span class="p">:</span>
|
||||
<span class="n">current_rendered_image</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_rendered_image</span><span class="p">()</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">current_episode_steps_counter</span> <span class="o">+=</span> <span class="mi">1</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">phase</span> <span class="o">!=</span> <span class="n">RunPhase</span><span class="o">.</span><span class="n">UNDEFINED</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">total_steps_counter</span> <span class="o">+=</span> <span class="mi">1</span>
|
||||
|
||||
<span class="c1"># act</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_take_action</span><span class="p">(</span><span class="n">action</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># observe</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_update_state</span><span class="p">()</span>
|
||||
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_rendered</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">render</span><span class="p">()</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">total_reward_in_current_episode</span> <span class="o">+=</span> <span class="bp">self</span><span class="o">.</span><span class="n">reward</span>
|
||||
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">visualization_parameters</span><span class="o">.</span><span class="n">add_rendered_image_to_env_response</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">info</span><span class="p">[</span><span class="s1">'image'</span><span class="p">]</span> <span class="o">=</span> <span class="n">current_rendered_image</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">last_env_response</span> <span class="o">=</span> \
|
||||
<span class="n">EnvResponse</span><span class="p">(</span>
|
||||
<span class="n">reward</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">reward</span><span class="p">,</span>
|
||||
<span class="n">next_state</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">state</span><span class="p">,</span>
|
||||
<span class="n">goal</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">goal</span><span class="p">,</span>
|
||||
<span class="n">game_over</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">done</span><span class="p">,</span>
|
||||
<span class="n">info</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">info</span>
|
||||
<span class="p">)</span>
|
||||
|
||||
<span class="c1"># store observations for video / gif dumping</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">should_dump_video_of_the_current_episode</span><span class="p">(</span><span class="n">episode_terminated</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span> <span class="ow">and</span> \
|
||||
<span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">visualization_parameters</span><span class="o">.</span><span class="n">dump_mp4</span> <span class="ow">or</span> <span class="bp">self</span><span class="o">.</span><span class="n">visualization_parameters</span><span class="o">.</span><span class="n">dump_gifs</span><span class="p">):</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">last_episode_images</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">get_rendered_image</span><span class="p">())</span>
|
||||
|
||||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">last_env_response</span></div>
|
||||
|
||||
<div class="viewcode-block" id="Environment.render"><a class="viewcode-back" href="../../../components/environments/index.html#rl_coach.environments.environment.Environment.render">[docs]</a> <span class="k">def</span> <span class="nf">render</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Call the environment function for rendering to the screen</span>
|
||||
|
||||
<span class="sd"> :return: None</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">native_rendering</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_render</span><span class="p">()</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">renderer</span><span class="o">.</span><span class="n">render_image</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">get_rendered_image</span><span class="p">())</span></div>
|
||||
|
||||
<div class="viewcode-block" id="Environment.handle_episode_ended"><a class="viewcode-back" href="../../../components/environments/index.html#rl_coach.environments.environment.Environment.handle_episode_ended">[docs]</a> <span class="k">def</span> <span class="nf">handle_episode_ended</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> End an episode</span>
|
||||
|
||||
<span class="sd"> :return: None</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">dump_video_of_last_episode_if_needed</span><span class="p">()</span></div>
|
||||
|
||||
<div class="viewcode-block" id="Environment.reset_internal_state"><a class="viewcode-back" href="../../../components/environments/index.html#rl_coach.environments.environment.Environment.reset_internal_state">[docs]</a> <span class="k">def</span> <span class="nf">reset_internal_state</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">force_environment_reset</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span> <span class="o">-></span> <span class="n">EnvResponse</span><span class="p">:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Reset the environment and all the variable of the wrapper</span>
|
||||
|
||||
<span class="sd"> :param force_environment_reset: forces environment reset even when the game did not end</span>
|
||||
<span class="sd"> :return: A dictionary containing the observation, reward, done flag, action and measurements</span>
|
||||
<span class="sd"> """</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_restart_environment_episode</span><span class="p">(</span><span class="n">force_environment_reset</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">last_episode_time</span> <span class="o">=</span> <span class="n">time</span><span class="o">.</span><span class="n">time</span><span class="p">()</span>
|
||||
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">current_episode_steps_counter</span> <span class="o">></span> <span class="mi">0</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">phase</span> <span class="o">!=</span> <span class="n">RunPhase</span><span class="o">.</span><span class="n">UNDEFINED</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">episode_idx</span> <span class="o">+=</span> <span class="mi">1</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">done</span> <span class="o">=</span> <span class="kc">False</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">total_reward_in_current_episode</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">reward</span> <span class="o">=</span> <span class="mf">0.0</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">last_action</span> <span class="o">=</span> <span class="mi">0</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">current_episode_steps_counter</span> <span class="o">=</span> <span class="mi">0</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">last_episode_images</span> <span class="o">=</span> <span class="p">[]</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_update_state</span><span class="p">()</span>
|
||||
|
||||
<span class="c1"># render before the preprocessing of the observation, so that the image will be in its original quality</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_rendered</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">render</span><span class="p">()</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">last_env_response</span> <span class="o">=</span> \
|
||||
<span class="n">EnvResponse</span><span class="p">(</span>
|
||||
<span class="n">reward</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">reward</span><span class="p">,</span>
|
||||
<span class="n">next_state</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">state</span><span class="p">,</span>
|
||||
<span class="n">goal</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">goal</span><span class="p">,</span>
|
||||
<span class="n">game_over</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">done</span><span class="p">,</span>
|
||||
<span class="n">info</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">info</span>
|
||||
<span class="p">)</span>
|
||||
|
||||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">last_env_response</span></div>
|
||||
|
||||
<div class="viewcode-block" id="Environment.get_random_action"><a class="viewcode-back" href="../../../components/environments/index.html#rl_coach.environments.environment.Environment.get_random_action">[docs]</a> <span class="k">def</span> <span class="nf">get_random_action</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">ActionType</span><span class="p">:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Returns an action picked uniformly from the available actions</span>
|
||||
|
||||
<span class="sd"> :return: a numpy array with a random action</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">action_space</span><span class="o">.</span><span class="n">sample</span><span class="p">()</span></div>
|
||||
|
||||
<div class="viewcode-block" id="Environment.get_available_keys"><a class="viewcode-back" href="../../../components/environments/index.html#rl_coach.environments.environment.Environment.get_available_keys">[docs]</a> <span class="k">def</span> <span class="nf">get_available_keys</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">List</span><span class="p">[</span><span class="n">Tuple</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">ActionType</span><span class="p">]]:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Return a list of tuples mapping between action names and the keyboard key that triggers them</span>
|
||||
|
||||
<span class="sd"> :return: a list of tuples mapping between action names and the keyboard key that triggers them</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="n">available_keys</span> <span class="o">=</span> <span class="p">[]</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">key_to_action</span> <span class="o">!=</span> <span class="p">{}:</span>
|
||||
<span class="k">for</span> <span class="n">key</span><span class="p">,</span> <span class="n">idx</span> <span class="ow">in</span> <span class="nb">sorted</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">key_to_action</span><span class="o">.</span><span class="n">items</span><span class="p">(),</span> <span class="n">key</span><span class="o">=</span><span class="n">operator</span><span class="o">.</span><span class="n">itemgetter</span><span class="p">(</span><span class="mi">1</span><span class="p">)):</span>
|
||||
<span class="k">if</span> <span class="n">key</span> <span class="o">!=</span> <span class="p">():</span>
|
||||
<span class="n">key_names</span> <span class="o">=</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">renderer</span><span class="o">.</span><span class="n">get_key_names</span><span class="p">([</span><span class="n">k</span><span class="p">])[</span><span class="mi">0</span><span class="p">]</span> <span class="k">for</span> <span class="n">k</span> <span class="ow">in</span> <span class="n">key</span><span class="p">]</span>
|
||||
<span class="n">available_keys</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="bp">self</span><span class="o">.</span><span class="n">action_space</span><span class="o">.</span><span class="n">descriptions</span><span class="p">[</span><span class="n">idx</span><span class="p">],</span> <span class="s1">' + '</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">key_names</span><span class="p">)))</span>
|
||||
<span class="k">elif</span> <span class="nb">type</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">action_space</span><span class="p">)</span> <span class="o">==</span> <span class="n">DiscreteActionSpace</span><span class="p">:</span>
|
||||
<span class="k">for</span> <span class="n">action</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">action_space</span><span class="o">.</span><span class="n">shape</span><span class="p">):</span>
|
||||
<span class="n">available_keys</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="s2">"Action </span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">action</span> <span class="o">+</span> <span class="mi">1</span><span class="p">),</span> <span class="n">action</span> <span class="o">+</span> <span class="mi">1</span><span class="p">))</span>
|
||||
<span class="k">return</span> <span class="n">available_keys</span></div>
|
||||
|
||||
<div class="viewcode-block" id="Environment.get_goal"><a class="viewcode-back" href="../../../components/environments/index.html#rl_coach.environments.environment.Environment.get_goal">[docs]</a> <span class="k">def</span> <span class="nf">get_goal</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">GoalType</span><span class="p">:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Get the current goal that the agents needs to achieve in the environment</span>
|
||||
|
||||
<span class="sd"> :return: The goal</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">goal</span></div>
|
||||
|
||||
<div class="viewcode-block" id="Environment.set_goal"><a class="viewcode-back" href="../../../components/environments/index.html#rl_coach.environments.environment.Environment.set_goal">[docs]</a> <span class="k">def</span> <span class="nf">set_goal</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">goal</span><span class="p">:</span> <span class="n">GoalType</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Set the current goal that the agent needs to achieve in the environment</span>
|
||||
|
||||
<span class="sd"> :param goal: the goal that needs to be achieved</span>
|
||||
<span class="sd"> :return: None</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">goal</span> <span class="o">=</span> <span class="n">goal</span></div>
|
||||
|
||||
<span class="k">def</span> <span class="nf">should_dump_video_of_the_current_episode</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">episode_terminated</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">visualization_parameters</span><span class="o">.</span><span class="n">video_dump_filters</span><span class="p">:</span>
|
||||
<span class="k">for</span> <span class="n">video_dump_filter</span> <span class="ow">in</span> <span class="n">force_list</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">visualization_parameters</span><span class="o">.</span><span class="n">video_dump_filters</span><span class="p">):</span>
|
||||
<span class="k">if</span> <span class="ow">not</span> <span class="n">video_dump_filter</span><span class="o">.</span><span class="n">should_dump</span><span class="p">(</span><span class="n">episode_terminated</span><span class="p">,</span> <span class="o">**</span><span class="bp">self</span><span class="o">.</span><span class="vm">__dict__</span><span class="p">):</span>
|
||||
<span class="k">return</span> <span class="kc">False</span>
|
||||
<span class="k">return</span> <span class="kc">True</span>
|
||||
<span class="k">return</span> <span class="kc">True</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">dump_video_of_last_episode_if_needed</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">last_episode_images</span> <span class="o">!=</span> <span class="p">[]</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">should_dump_video_of_the_current_episode</span><span class="p">(</span><span class="n">episode_terminated</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">dump_video_of_last_episode</span><span class="p">()</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">dump_video_of_last_episode</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="n">frame_skipping</span> <span class="o">=</span> <span class="nb">max</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="nb">int</span><span class="p">(</span><span class="mi">5</span> <span class="o">/</span> <span class="bp">self</span><span class="o">.</span><span class="n">frame_skip</span><span class="p">))</span>
|
||||
<span class="n">file_name</span> <span class="o">=</span> <span class="s1">'episode-</span><span class="si">{}</span><span class="s1">_score-</span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">episode_idx</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">total_reward_in_current_episode</span><span class="p">)</span>
|
||||
<span class="n">fps</span> <span class="o">=</span> <span class="mi">10</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">visualization_parameters</span><span class="o">.</span><span class="n">dump_gifs</span><span class="p">:</span>
|
||||
<span class="n">logger</span><span class="o">.</span><span class="n">create_gif</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">last_episode_images</span><span class="p">[::</span><span class="n">frame_skipping</span><span class="p">],</span> <span class="n">name</span><span class="o">=</span><span class="n">file_name</span><span class="p">,</span> <span class="n">fps</span><span class="o">=</span><span class="n">fps</span><span class="p">)</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">visualization_parameters</span><span class="o">.</span><span class="n">dump_mp4</span><span class="p">:</span>
|
||||
<span class="n">logger</span><span class="o">.</span><span class="n">create_mp4</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">last_episode_images</span><span class="p">[::</span><span class="n">frame_skipping</span><span class="p">],</span> <span class="n">name</span><span class="o">=</span><span class="n">file_name</span><span class="p">,</span> <span class="n">fps</span><span class="o">=</span><span class="n">fps</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># The following functions define the interaction with the environment.</span>
|
||||
<span class="c1"># Any new environment that inherits the Environment class should use these signatures.</span>
|
||||
<span class="c1"># Some of these functions are optional - please read their description for more details.</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_take_action</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">action_idx</span><span class="p">:</span> <span class="n">ActionType</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> An environment dependent function that sends an action to the simulator.</span>
|
||||
|
||||
<span class="sd"> :param action_idx: the action to perform on the environment</span>
|
||||
<span class="sd"> :return: None</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">(</span><span class="s2">""</span><span class="p">)</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_update_state</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Updates the state from the environment.</span>
|
||||
<span class="sd"> Should update self.observation, self.reward, self.done, self.measurements and self.info</span>
|
||||
|
||||
<span class="sd"> :return: None</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">(</span><span class="s2">""</span><span class="p">)</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_restart_environment_episode</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">force_environment_reset</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Restarts the simulator episode</span>
|
||||
|
||||
<span class="sd"> :param force_environment_reset: Force the environment to reset even if the episode is not done yet.</span>
|
||||
<span class="sd"> :return: None</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">(</span><span class="s2">""</span><span class="p">)</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_render</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Renders the environment using the native simulator renderer</span>
|
||||
|
||||
<span class="sd"> :return: None</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="k">pass</span>
|
||||
|
||||
<div class="viewcode-block" id="Environment.get_rendered_image"><a class="viewcode-back" href="../../../components/environments/index.html#rl_coach.environments.environment.Environment.get_rendered_image">[docs]</a> <span class="k">def</span> <span class="nf">get_rendered_image</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Return a numpy array containing the image that will be rendered to the screen.</span>
|
||||
<span class="sd"> This can be different from the observation. For example, mujoco's observation is a measurements vector.</span>
|
||||
|
||||
<span class="sd"> :return: numpy array containing the image that will be rendered to the screen</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="n">transpose</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">state</span><span class="p">[</span><span class="s1">'observation'</span><span class="p">],</span> <span class="p">[</span><span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">0</span><span class="p">])</span></div>
|
||||
|
||||
<span class="k">def</span> <span class="nf">get_target_success_rate</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span>
|
||||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">target_success_rate</span></div>
|
||||
</pre></div>
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
<footer>
|
||||
|
||||
|
||||
<hr/>
|
||||
|
||||
<div role="contentinfo">
|
||||
<p>
|
||||
© Copyright 2018, Intel AI Lab
|
||||
|
||||
</p>
|
||||
</div>
|
||||
Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
|
||||
|
||||
</footer>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
|
||||
</section>
|
||||
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<script type="text/javascript" id="documentation_options" data-url_root="../../../" src="../../../_static/documentation_options.js"></script>
|
||||
<script type="text/javascript" src="../../../_static/jquery.js"></script>
|
||||
<script type="text/javascript" src="../../../_static/underscore.js"></script>
|
||||
<script type="text/javascript" src="../../../_static/doctools.js"></script>
|
||||
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></script>
|
||||
|
||||
|
||||
|
||||
|
||||
<script type="text/javascript" src="../../../_static/js/theme.js"></script>
|
||||
|
||||
<script type="text/javascript">
|
||||
jQuery(function () {
|
||||
SphinxRtdTheme.Navigation.enable(true);
|
||||
});
|
||||
</script>
|
||||
|
||||
</body>
|
||||
</html>
|
||||
703
docs/_modules/rl_coach/environments/gym_environment.html
Normal file
703
docs/_modules/rl_coach/environments/gym_environment.html
Normal file
@@ -0,0 +1,703 @@
|
||||
|
||||
|
||||
<!DOCTYPE html>
|
||||
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
|
||||
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
|
||||
<head>
|
||||
<meta charset="utf-8">
|
||||
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
|
||||
<title>rl_coach.environments.gym_environment — Reinforcement Learning Coach 0.11.0 documentation</title>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
|
||||
<link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
|
||||
<link rel="stylesheet" href="../../../_static/css/custom.css" type="text/css" />
|
||||
<link rel="index" title="Index" href="../../../genindex.html" />
|
||||
<link rel="search" title="Search" href="../../../search.html" />
|
||||
<link href="../../../_static/css/custom.css" rel="stylesheet" type="text/css">
|
||||
|
||||
|
||||
|
||||
<script src="../../../_static/js/modernizr.min.js"></script>
|
||||
|
||||
</head>
|
||||
|
||||
<body class="wy-body-for-nav">
|
||||
|
||||
|
||||
<div class="wy-grid-for-nav">
|
||||
|
||||
|
||||
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
|
||||
<div class="wy-side-scroll">
|
||||
<div class="wy-side-nav-search">
|
||||
|
||||
|
||||
|
||||
<a href="../../../index.html" class="icon icon-home"> Reinforcement Learning Coach
|
||||
|
||||
|
||||
|
||||
|
||||
<img src="../../../_static/dark_logo.png" class="logo" alt="Logo"/>
|
||||
|
||||
</a>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<div role="search">
|
||||
<form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get">
|
||||
<input type="text" name="q" placeholder="Search docs" />
|
||||
<input type="hidden" name="check_keywords" value="yes" />
|
||||
<input type="hidden" name="area" value="default" />
|
||||
</form>
|
||||
</div>
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<p class="caption"><span class="caption-text">Intro</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../usage.html">Usage</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../features/index.html">Features</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../selecting_an_algorithm.html">Selecting an Algorithm</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../dashboard.html">Coach Dashboard</a></li>
|
||||
</ul>
|
||||
<p class="caption"><span class="caption-text">Design</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../design/control_flow.html">Control Flow</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../design/network.html">Network Design</a></li>
|
||||
</ul>
|
||||
<p class="caption"><span class="caption-text">Contributing</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../contributing/add_agent.html">Adding a New Agent</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../contributing/add_env.html">Adding a New Environment</a></li>
|
||||
</ul>
|
||||
<p class="caption"><span class="caption-text">Components</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/agents/index.html">Agents</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/architectures/index.html">Architectures</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/environments/index.html">Environments</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/exploration_policies/index.html">Exploration Policies</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/filters/index.html">Filters</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/memories/index.html">Memories</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/core_types.html">Core Types</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/spaces.html">Spaces</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/additional_parameters.html">Additional Parameters</a></li>
|
||||
</ul>
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
</nav>
|
||||
|
||||
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
|
||||
|
||||
|
||||
<nav class="wy-nav-top" aria-label="top navigation">
|
||||
|
||||
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
|
||||
<a href="../../../index.html">Reinforcement Learning Coach</a>
|
||||
|
||||
</nav>
|
||||
|
||||
|
||||
<div class="wy-nav-content">
|
||||
|
||||
<div class="rst-content">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<div role="navigation" aria-label="breadcrumbs navigation">
|
||||
|
||||
<ul class="wy-breadcrumbs">
|
||||
|
||||
<li><a href="../../../index.html">Docs</a> »</li>
|
||||
|
||||
<li><a href="../../index.html">Module code</a> »</li>
|
||||
|
||||
<li>rl_coach.environments.gym_environment</li>
|
||||
|
||||
|
||||
<li class="wy-breadcrumbs-aside">
|
||||
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
|
||||
|
||||
<hr/>
|
||||
</div>
|
||||
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
|
||||
<div itemprop="articleBody">
|
||||
|
||||
<h1>Source code for rl_coach.environments.gym_environment</h1><div class="highlight"><pre>
|
||||
<span></span><span class="c1">#</span>
|
||||
<span class="c1"># Copyright (c) 2017 Intel Corporation</span>
|
||||
<span class="c1">#</span>
|
||||
<span class="c1"># Licensed under the Apache License, Version 2.0 (the "License");</span>
|
||||
<span class="c1"># you may not use this file except in compliance with the License.</span>
|
||||
<span class="c1"># You may obtain a copy of the License at</span>
|
||||
<span class="c1">#</span>
|
||||
<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
|
||||
<span class="c1">#</span>
|
||||
<span class="c1"># Unless required by applicable law or agreed to in writing, software</span>
|
||||
<span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span>
|
||||
<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
|
||||
<span class="c1"># See the License for the specific language governing permissions and</span>
|
||||
<span class="c1"># limitations under the License.</span>
|
||||
<span class="c1">#</span>
|
||||
|
||||
<span class="kn">import</span> <span class="nn">gym</span>
|
||||
<span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
|
||||
<span class="kn">import</span> <span class="nn">scipy.ndimage</span>
|
||||
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.graph_managers.graph_manager</span> <span class="k">import</span> <span class="n">ScheduleParameters</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.utils</span> <span class="k">import</span> <span class="n">lower_under_to_upper</span><span class="p">,</span> <span class="n">short_dynamic_import</span>
|
||||
|
||||
<span class="k">try</span><span class="p">:</span>
|
||||
<span class="kn">import</span> <span class="nn">roboschool</span>
|
||||
<span class="kn">from</span> <span class="nn">OpenGL</span> <span class="k">import</span> <span class="n">GL</span>
|
||||
<span class="k">except</span> <span class="ne">ImportError</span><span class="p">:</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.logger</span> <span class="k">import</span> <span class="n">failed_imports</span>
|
||||
<span class="n">failed_imports</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s2">"RoboSchool"</span><span class="p">)</span>
|
||||
|
||||
<span class="k">try</span><span class="p">:</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.gym_extensions.continuous</span> <span class="k">import</span> <span class="n">mujoco</span>
|
||||
<span class="k">except</span><span class="p">:</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.logger</span> <span class="k">import</span> <span class="n">failed_imports</span>
|
||||
<span class="n">failed_imports</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s2">"GymExtensions"</span><span class="p">)</span>
|
||||
|
||||
<span class="k">try</span><span class="p">:</span>
|
||||
<span class="kn">import</span> <span class="nn">pybullet_envs</span>
|
||||
<span class="k">except</span> <span class="ne">ImportError</span><span class="p">:</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.logger</span> <span class="k">import</span> <span class="n">failed_imports</span>
|
||||
<span class="n">failed_imports</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s2">"PyBullet"</span><span class="p">)</span>
|
||||
|
||||
<span class="kn">from</span> <span class="nn">typing</span> <span class="k">import</span> <span class="n">Dict</span><span class="p">,</span> <span class="n">Any</span><span class="p">,</span> <span class="n">Union</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.core_types</span> <span class="k">import</span> <span class="n">RunPhase</span><span class="p">,</span> <span class="n">EnvironmentSteps</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.environments.environment</span> <span class="k">import</span> <span class="n">Environment</span><span class="p">,</span> <span class="n">EnvironmentParameters</span><span class="p">,</span> <span class="n">LevelSelection</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.spaces</span> <span class="k">import</span> <span class="n">DiscreteActionSpace</span><span class="p">,</span> <span class="n">BoxActionSpace</span><span class="p">,</span> <span class="n">ImageObservationSpace</span><span class="p">,</span> <span class="n">VectorObservationSpace</span><span class="p">,</span> \
|
||||
<span class="n">StateSpace</span><span class="p">,</span> <span class="n">RewardSpace</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.filters.filter</span> <span class="k">import</span> <span class="n">NoInputFilter</span><span class="p">,</span> <span class="n">NoOutputFilter</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.filters.reward.reward_clipping_filter</span> <span class="k">import</span> <span class="n">RewardClippingFilter</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.filters.observation.observation_rescale_to_size_filter</span> <span class="k">import</span> <span class="n">ObservationRescaleToSizeFilter</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.filters.observation.observation_stacking_filter</span> <span class="k">import</span> <span class="n">ObservationStackingFilter</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.filters.observation.observation_rgb_to_y_filter</span> <span class="k">import</span> <span class="n">ObservationRGBToYFilter</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.filters.observation.observation_to_uint8_filter</span> <span class="k">import</span> <span class="n">ObservationToUInt8Filter</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.filters.filter</span> <span class="k">import</span> <span class="n">InputFilter</span>
|
||||
<span class="kn">import</span> <span class="nn">random</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.base_parameters</span> <span class="k">import</span> <span class="n">VisualizationParameters</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.logger</span> <span class="k">import</span> <span class="n">screen</span>
|
||||
|
||||
|
||||
<span class="c1"># Parameters</span>
|
||||
<span class="k">class</span> <span class="nc">GymEnvironmentParameters</span><span class="p">(</span><span class="n">EnvironmentParameters</span><span class="p">):</span>
|
||||
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">level</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">level</span><span class="o">=</span><span class="n">level</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">random_initialization_steps</span> <span class="o">=</span> <span class="mi">0</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">max_over_num_frames</span> <span class="o">=</span> <span class="mi">1</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">additional_simulator_parameters</span> <span class="o">=</span> <span class="p">{}</span>
|
||||
|
||||
<span class="nd">@property</span>
|
||||
<span class="k">def</span> <span class="nf">path</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="k">return</span> <span class="s1">'rl_coach.environments.gym_environment:GymEnvironment'</span>
|
||||
|
||||
|
||||
<span class="c1"># Generic parameters for vector environments such as mujoco, roboschool, bullet, etc.</span>
|
||||
<span class="k">class</span> <span class="nc">GymVectorEnvironment</span><span class="p">(</span><span class="n">GymEnvironmentParameters</span><span class="p">):</span>
|
||||
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">level</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">level</span><span class="o">=</span><span class="n">level</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">frame_skip</span> <span class="o">=</span> <span class="mi">1</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">default_input_filter</span> <span class="o">=</span> <span class="n">NoInputFilter</span><span class="p">()</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">default_output_filter</span> <span class="o">=</span> <span class="n">NoOutputFilter</span><span class="p">()</span>
|
||||
|
||||
|
||||
<span class="c1"># Roboschool</span>
|
||||
<span class="n">gym_roboschool_envs</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'inverted_pendulum'</span><span class="p">,</span> <span class="s1">'inverted_pendulum_swingup'</span><span class="p">,</span> <span class="s1">'inverted_double_pendulum'</span><span class="p">,</span> <span class="s1">'reacher'</span><span class="p">,</span>
|
||||
<span class="s1">'hopper'</span><span class="p">,</span> <span class="s1">'walker2d'</span><span class="p">,</span> <span class="s1">'half_cheetah'</span><span class="p">,</span> <span class="s1">'ant'</span><span class="p">,</span> <span class="s1">'humanoid'</span><span class="p">,</span> <span class="s1">'humanoid_flagrun'</span><span class="p">,</span>
|
||||
<span class="s1">'humanoid_flagrun_harder'</span><span class="p">,</span> <span class="s1">'pong'</span><span class="p">]</span>
|
||||
<span class="n">roboschool_v0</span> <span class="o">=</span> <span class="p">{</span><span class="n">e</span><span class="p">:</span> <span class="s2">"</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">lower_under_to_upper</span><span class="p">(</span><span class="n">e</span><span class="p">)</span> <span class="o">+</span> <span class="s1">'-v0'</span><span class="p">)</span> <span class="k">for</span> <span class="n">e</span> <span class="ow">in</span> <span class="n">gym_roboschool_envs</span><span class="p">}</span>
|
||||
|
||||
<span class="c1"># Mujoco</span>
|
||||
<span class="n">gym_mujoco_envs</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'inverted_pendulum'</span><span class="p">,</span> <span class="s1">'inverted_double_pendulum'</span><span class="p">,</span> <span class="s1">'reacher'</span><span class="p">,</span> <span class="s1">'hopper'</span><span class="p">,</span> <span class="s1">'walker2d'</span><span class="p">,</span> <span class="s1">'half_cheetah'</span><span class="p">,</span>
|
||||
<span class="s1">'ant'</span><span class="p">,</span> <span class="s1">'swimmer'</span><span class="p">,</span> <span class="s1">'humanoid'</span><span class="p">,</span> <span class="s1">'humanoid_standup'</span><span class="p">,</span> <span class="s1">'pusher'</span><span class="p">,</span> <span class="s1">'thrower'</span><span class="p">,</span> <span class="s1">'striker'</span><span class="p">]</span>
|
||||
|
||||
<span class="n">mujoco_v2</span> <span class="o">=</span> <span class="p">{</span><span class="n">e</span><span class="p">:</span> <span class="s2">"</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">lower_under_to_upper</span><span class="p">(</span><span class="n">e</span><span class="p">)</span> <span class="o">+</span> <span class="s1">'-v2'</span><span class="p">)</span> <span class="k">for</span> <span class="n">e</span> <span class="ow">in</span> <span class="n">gym_mujoco_envs</span><span class="p">}</span>
|
||||
<span class="n">mujoco_v2</span><span class="p">[</span><span class="s1">'walker2d'</span><span class="p">]</span> <span class="o">=</span> <span class="s1">'Walker2d-v2'</span>
|
||||
|
||||
<span class="c1"># Fetch</span>
|
||||
<span class="n">gym_fetch_envs</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'reach'</span><span class="p">,</span> <span class="s1">'slide'</span><span class="p">,</span> <span class="s1">'push'</span><span class="p">,</span> <span class="s1">'pick_and_place'</span><span class="p">]</span>
|
||||
<span class="n">fetch_v1</span> <span class="o">=</span> <span class="p">{</span><span class="n">e</span><span class="p">:</span> <span class="s2">"</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="s1">'Fetch'</span> <span class="o">+</span> <span class="n">lower_under_to_upper</span><span class="p">(</span><span class="n">e</span><span class="p">)</span> <span class="o">+</span> <span class="s1">'-v1'</span><span class="p">)</span> <span class="k">for</span> <span class="n">e</span> <span class="ow">in</span> <span class="n">gym_fetch_envs</span><span class="p">}</span>
|
||||
|
||||
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd">Atari Environment Components</span>
|
||||
<span class="sd">"""</span>
|
||||
|
||||
<span class="n">AtariInputFilter</span> <span class="o">=</span> <span class="n">InputFilter</span><span class="p">(</span><span class="n">is_a_reference_filter</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||||
<span class="n">AtariInputFilter</span><span class="o">.</span><span class="n">add_reward_filter</span><span class="p">(</span><span class="s1">'clipping'</span><span class="p">,</span> <span class="n">RewardClippingFilter</span><span class="p">(</span><span class="o">-</span><span class="mf">1.0</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">))</span>
|
||||
<span class="n">AtariInputFilter</span><span class="o">.</span><span class="n">add_observation_filter</span><span class="p">(</span><span class="s1">'observation'</span><span class="p">,</span> <span class="s1">'rescaling'</span><span class="p">,</span>
|
||||
<span class="n">ObservationRescaleToSizeFilter</span><span class="p">(</span><span class="n">ImageObservationSpace</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="mi">84</span><span class="p">,</span> <span class="mi">84</span><span class="p">,</span> <span class="mi">3</span><span class="p">]),</span>
|
||||
<span class="n">high</span><span class="o">=</span><span class="mi">255</span><span class="p">)))</span>
|
||||
<span class="n">AtariInputFilter</span><span class="o">.</span><span class="n">add_observation_filter</span><span class="p">(</span><span class="s1">'observation'</span><span class="p">,</span> <span class="s1">'to_grayscale'</span><span class="p">,</span> <span class="n">ObservationRGBToYFilter</span><span class="p">())</span>
|
||||
<span class="n">AtariInputFilter</span><span class="o">.</span><span class="n">add_observation_filter</span><span class="p">(</span><span class="s1">'observation'</span><span class="p">,</span> <span class="s1">'to_uint8'</span><span class="p">,</span> <span class="n">ObservationToUInt8Filter</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">255</span><span class="p">))</span>
|
||||
<span class="n">AtariInputFilter</span><span class="o">.</span><span class="n">add_observation_filter</span><span class="p">(</span><span class="s1">'observation'</span><span class="p">,</span> <span class="s1">'stacking'</span><span class="p">,</span> <span class="n">ObservationStackingFilter</span><span class="p">(</span><span class="mi">4</span><span class="p">))</span>
|
||||
<span class="n">AtariOutputFilter</span> <span class="o">=</span> <span class="n">NoOutputFilter</span><span class="p">()</span>
|
||||
|
||||
|
||||
<span class="k">class</span> <span class="nc">Atari</span><span class="p">(</span><span class="n">GymEnvironmentParameters</span><span class="p">):</span>
|
||||
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">level</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">level</span><span class="o">=</span><span class="n">level</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">frame_skip</span> <span class="o">=</span> <span class="mi">4</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">max_over_num_frames</span> <span class="o">=</span> <span class="mi">2</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">random_initialization_steps</span> <span class="o">=</span> <span class="mi">30</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">default_input_filter</span> <span class="o">=</span> <span class="n">AtariInputFilter</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">default_output_filter</span> <span class="o">=</span> <span class="n">AtariOutputFilter</span>
|
||||
|
||||
|
||||
<span class="n">gym_atari_envs</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'air_raid'</span><span class="p">,</span> <span class="s1">'alien'</span><span class="p">,</span> <span class="s1">'amidar'</span><span class="p">,</span> <span class="s1">'assault'</span><span class="p">,</span> <span class="s1">'asterix'</span><span class="p">,</span> <span class="s1">'asteroids'</span><span class="p">,</span> <span class="s1">'atlantis'</span><span class="p">,</span>
|
||||
<span class="s1">'bank_heist'</span><span class="p">,</span> <span class="s1">'battle_zone'</span><span class="p">,</span> <span class="s1">'beam_rider'</span><span class="p">,</span> <span class="s1">'berzerk'</span><span class="p">,</span> <span class="s1">'bowling'</span><span class="p">,</span> <span class="s1">'boxing'</span><span class="p">,</span> <span class="s1">'breakout'</span><span class="p">,</span> <span class="s1">'carnival'</span><span class="p">,</span>
|
||||
<span class="s1">'centipede'</span><span class="p">,</span> <span class="s1">'chopper_command'</span><span class="p">,</span> <span class="s1">'crazy_climber'</span><span class="p">,</span> <span class="s1">'demon_attack'</span><span class="p">,</span> <span class="s1">'double_dunk'</span><span class="p">,</span>
|
||||
<span class="s1">'elevator_action'</span><span class="p">,</span> <span class="s1">'enduro'</span><span class="p">,</span> <span class="s1">'fishing_derby'</span><span class="p">,</span> <span class="s1">'freeway'</span><span class="p">,</span> <span class="s1">'frostbite'</span><span class="p">,</span> <span class="s1">'gopher'</span><span class="p">,</span> <span class="s1">'gravitar'</span><span class="p">,</span>
|
||||
<span class="s1">'hero'</span><span class="p">,</span> <span class="s1">'ice_hockey'</span><span class="p">,</span> <span class="s1">'jamesbond'</span><span class="p">,</span> <span class="s1">'journey_escape'</span><span class="p">,</span> <span class="s1">'kangaroo'</span><span class="p">,</span> <span class="s1">'krull'</span><span class="p">,</span> <span class="s1">'kung_fu_master'</span><span class="p">,</span>
|
||||
<span class="s1">'montezuma_revenge'</span><span class="p">,</span> <span class="s1">'ms_pacman'</span><span class="p">,</span> <span class="s1">'name_this_game'</span><span class="p">,</span> <span class="s1">'phoenix'</span><span class="p">,</span> <span class="s1">'pitfall'</span><span class="p">,</span> <span class="s1">'pong'</span><span class="p">,</span> <span class="s1">'pooyan'</span><span class="p">,</span>
|
||||
<span class="s1">'private_eye'</span><span class="p">,</span> <span class="s1">'qbert'</span><span class="p">,</span> <span class="s1">'riverraid'</span><span class="p">,</span> <span class="s1">'road_runner'</span><span class="p">,</span> <span class="s1">'robotank'</span><span class="p">,</span> <span class="s1">'seaquest'</span><span class="p">,</span> <span class="s1">'skiing'</span><span class="p">,</span>
|
||||
<span class="s1">'solaris'</span><span class="p">,</span> <span class="s1">'space_invaders'</span><span class="p">,</span> <span class="s1">'star_gunner'</span><span class="p">,</span> <span class="s1">'tennis'</span><span class="p">,</span> <span class="s1">'time_pilot'</span><span class="p">,</span> <span class="s1">'tutankham'</span><span class="p">,</span> <span class="s1">'up_n_down'</span><span class="p">,</span>
|
||||
<span class="s1">'venture'</span><span class="p">,</span> <span class="s1">'video_pinball'</span><span class="p">,</span> <span class="s1">'wizard_of_wor'</span><span class="p">,</span> <span class="s1">'yars_revenge'</span><span class="p">,</span> <span class="s1">'zaxxon'</span><span class="p">]</span>
|
||||
<span class="n">atari_deterministic_v4</span> <span class="o">=</span> <span class="p">{</span><span class="n">e</span><span class="p">:</span> <span class="s2">"</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">lower_under_to_upper</span><span class="p">(</span><span class="n">e</span><span class="p">)</span> <span class="o">+</span> <span class="s1">'Deterministic-v4'</span><span class="p">)</span> <span class="k">for</span> <span class="n">e</span> <span class="ow">in</span> <span class="n">gym_atari_envs</span><span class="p">}</span>
|
||||
<span class="n">atari_no_frameskip_v4</span> <span class="o">=</span> <span class="p">{</span><span class="n">e</span><span class="p">:</span> <span class="s2">"</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">lower_under_to_upper</span><span class="p">(</span><span class="n">e</span><span class="p">)</span> <span class="o">+</span> <span class="s1">'NoFrameskip-v4'</span><span class="p">)</span> <span class="k">for</span> <span class="n">e</span> <span class="ow">in</span> <span class="n">gym_atari_envs</span><span class="p">}</span>
|
||||
|
||||
|
||||
<span class="c1"># default atari schedule used in the DeepMind papers</span>
|
||||
<span class="n">atari_schedule</span> <span class="o">=</span> <span class="n">ScheduleParameters</span><span class="p">()</span>
|
||||
<span class="n">atari_schedule</span><span class="o">.</span><span class="n">improve_steps</span> <span class="o">=</span> <span class="n">EnvironmentSteps</span><span class="p">(</span><span class="mi">50000000</span><span class="p">)</span>
|
||||
<span class="n">atari_schedule</span><span class="o">.</span><span class="n">steps_between_evaluation_periods</span> <span class="o">=</span> <span class="n">EnvironmentSteps</span><span class="p">(</span><span class="mi">250000</span><span class="p">)</span>
|
||||
<span class="n">atari_schedule</span><span class="o">.</span><span class="n">evaluation_steps</span> <span class="o">=</span> <span class="n">EnvironmentSteps</span><span class="p">(</span><span class="mi">135000</span><span class="p">)</span>
|
||||
<span class="n">atari_schedule</span><span class="o">.</span><span class="n">heatup_steps</span> <span class="o">=</span> <span class="n">EnvironmentSteps</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span>
|
||||
|
||||
|
||||
<span class="k">class</span> <span class="nc">MaxOverFramesAndFrameskipEnvWrapper</span><span class="p">(</span><span class="n">gym</span><span class="o">.</span><span class="n">Wrapper</span><span class="p">):</span>
|
||||
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">env</span><span class="p">,</span> <span class="n">frameskip</span><span class="o">=</span><span class="mi">4</span><span class="p">,</span> <span class="n">max_over_num_frames</span><span class="o">=</span><span class="mi">2</span><span class="p">):</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">env</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">max_over_num_frames</span> <span class="o">=</span> <span class="n">max_over_num_frames</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">observations_stack</span> <span class="o">=</span> <span class="p">[]</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">frameskip</span> <span class="o">=</span> <span class="n">frameskip</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">first_frame_to_max_over</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">frameskip</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">max_over_num_frames</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">reset</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">reset</span><span class="p">()</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">step</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">action</span><span class="p">):</span>
|
||||
<span class="n">total_reward</span> <span class="o">=</span> <span class="mf">0.0</span>
|
||||
<span class="n">done</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
<span class="n">info</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">observations_stack</span> <span class="o">=</span> <span class="p">[]</span>
|
||||
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">frameskip</span><span class="p">):</span>
|
||||
<span class="n">observation</span><span class="p">,</span> <span class="n">reward</span><span class="p">,</span> <span class="n">done</span><span class="p">,</span> <span class="n">info</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">step</span><span class="p">(</span><span class="n">action</span><span class="p">)</span>
|
||||
<span class="k">if</span> <span class="n">i</span> <span class="o">>=</span> <span class="bp">self</span><span class="o">.</span><span class="n">first_frame_to_max_over</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">observations_stack</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">observation</span><span class="p">)</span>
|
||||
<span class="n">total_reward</span> <span class="o">+=</span> <span class="n">reward</span>
|
||||
<span class="k">if</span> <span class="n">done</span><span class="p">:</span>
|
||||
<span class="c1"># deal with last state in episode</span>
|
||||
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">observations_stack</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">observations_stack</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">observation</span><span class="p">)</span>
|
||||
<span class="k">break</span>
|
||||
|
||||
<span class="n">max_over_frames_observation</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">max</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">observations_stack</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
|
||||
|
||||
<span class="k">return</span> <span class="n">max_over_frames_observation</span><span class="p">,</span> <span class="n">total_reward</span><span class="p">,</span> <span class="n">done</span><span class="p">,</span> <span class="n">info</span>
|
||||
|
||||
|
||||
<span class="c1"># Environment</span>
|
||||
<div class="viewcode-block" id="GymEnvironment"><a class="viewcode-back" href="../../../components/environments/index.html#rl_coach.environments.gym_environment.GymEnvironment">[docs]</a><span class="k">class</span> <span class="nc">GymEnvironment</span><span class="p">(</span><span class="n">Environment</span><span class="p">):</span>
|
||||
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">level</span><span class="p">:</span> <span class="n">LevelSelection</span><span class="p">,</span> <span class="n">frame_skip</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">visualization_parameters</span><span class="p">:</span> <span class="n">VisualizationParameters</span><span class="p">,</span>
|
||||
<span class="n">target_success_rate</span><span class="p">:</span> <span class="nb">float</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span> <span class="n">additional_simulator_parameters</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]</span> <span class="o">=</span> <span class="p">{},</span> <span class="n">seed</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="kc">None</span><span class="p">,</span> <span class="nb">int</span><span class="p">]</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
|
||||
<span class="n">human_control</span><span class="p">:</span> <span class="nb">bool</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">custom_reward_threshold</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">]</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
|
||||
<span class="n">random_initialization_steps</span><span class="p">:</span> <span class="nb">int</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">max_over_num_frames</span><span class="p">:</span> <span class="nb">int</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> :param level: (str)</span>
|
||||
<span class="sd"> A string representing the gym level to run. This can also be a LevelSelection object.</span>
|
||||
<span class="sd"> For example, BreakoutDeterministic-v0</span>
|
||||
|
||||
<span class="sd"> :param frame_skip: (int)</span>
|
||||
<span class="sd"> The number of frames to skip between any two actions given by the agent. The action will be repeated</span>
|
||||
<span class="sd"> for all the skipped frames.</span>
|
||||
|
||||
<span class="sd"> :param visualization_parameters: (VisualizationParameters)</span>
|
||||
<span class="sd"> The parameters used for visualizing the environment, such as the render flag, storing videos etc.</span>
|
||||
|
||||
<span class="sd"> :param additional_simulator_parameters: (Dict[str, Any])</span>
|
||||
<span class="sd"> Any additional parameters that the user can pass to the Gym environment. These parameters should be</span>
|
||||
<span class="sd"> accepted by the __init__ function of the implemented Gym environment.</span>
|
||||
|
||||
<span class="sd"> :param seed: (int)</span>
|
||||
<span class="sd"> A seed to use for the random number generator when running the environment.</span>
|
||||
|
||||
<span class="sd"> :param human_control: (bool)</span>
|
||||
<span class="sd"> A flag that allows controlling the environment using the keyboard keys.</span>
|
||||
|
||||
<span class="sd"> :param custom_reward_threshold: (float)</span>
|
||||
<span class="sd"> Allows defining a custom reward that will be used to decide when the agent succeeded in passing the environment.</span>
|
||||
<span class="sd"> If not set, this value will be taken from the Gym environment definition.</span>
|
||||
|
||||
<span class="sd"> :param random_initialization_steps: (int)</span>
|
||||
<span class="sd"> The number of random steps that will be taken in the environment after each reset.</span>
|
||||
<span class="sd"> This is a feature presented in the DQN paper, which improves the variability of the episodes the agent sees.</span>
|
||||
|
||||
<span class="sd"> :param max_over_num_frames: (int)</span>
|
||||
<span class="sd"> This value will be used for merging multiple frames into a single frame by taking the maximum value for each</span>
|
||||
<span class="sd"> of the pixels in the frame. This is particularly used in Atari games, where the frames flicker, and objects</span>
|
||||
<span class="sd"> can be seen in one frame but disappear in the next.</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">level</span><span class="p">,</span> <span class="n">seed</span><span class="p">,</span> <span class="n">frame_skip</span><span class="p">,</span> <span class="n">human_control</span><span class="p">,</span> <span class="n">custom_reward_threshold</span><span class="p">,</span>
|
||||
<span class="n">visualization_parameters</span><span class="p">,</span> <span class="n">target_success_rate</span><span class="p">)</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">random_initialization_steps</span> <span class="o">=</span> <span class="n">random_initialization_steps</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">max_over_num_frames</span> <span class="o">=</span> <span class="n">max_over_num_frames</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">additional_simulator_parameters</span> <span class="o">=</span> <span class="n">additional_simulator_parameters</span>
|
||||
|
||||
<span class="c1"># hide warnings</span>
|
||||
<span class="n">gym</span><span class="o">.</span><span class="n">logger</span><span class="o">.</span><span class="n">set_level</span><span class="p">(</span><span class="mi">40</span><span class="p">)</span>
|
||||
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> load and initialize environment</span>
|
||||
<span class="sd"> environment ids can be defined in 3 ways:</span>
|
||||
<span class="sd"> 1. Native gym environments like BreakoutDeterministic-v0 for example</span>
|
||||
<span class="sd"> 2. Custom gym environments written and installed as python packages.</span>
|
||||
<span class="sd"> This environments should have a python module with a class inheriting gym.Env, implementing the</span>
|
||||
<span class="sd"> relevant functions (_reset, _step, _render) and defining the observation and action space</span>
|
||||
<span class="sd"> For example: my_environment_package:MyEnvironmentClass will run an environment defined in the</span>
|
||||
<span class="sd"> MyEnvironmentClass class</span>
|
||||
<span class="sd"> 3. Custom gym environments written as an independent module which is not installed.</span>
|
||||
<span class="sd"> This environments should have a python module with a class inheriting gym.Env, implementing the</span>
|
||||
<span class="sd"> relevant functions (_reset, _step, _render) and defining the observation and action space.</span>
|
||||
<span class="sd"> For example: path_to_my_environment.sub_directory.my_module:MyEnvironmentClass will run an</span>
|
||||
<span class="sd"> environment defined in the MyEnvironmentClass class which is located in the module in the relative path</span>
|
||||
<span class="sd"> path_to_my_environment.sub_directory.my_module</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="k">if</span> <span class="s1">':'</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">env_id</span><span class="p">:</span>
|
||||
<span class="c1"># custom environments</span>
|
||||
<span class="k">if</span> <span class="s1">'/'</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">env_id</span> <span class="ow">or</span> <span class="s1">'.'</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">env_id</span><span class="p">:</span>
|
||||
<span class="c1"># environment in a an absolute path module written as a unix path or in a relative path module</span>
|
||||
<span class="c1"># written as a python import path</span>
|
||||
<span class="n">env_class</span> <span class="o">=</span> <span class="n">short_dynamic_import</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">env_id</span><span class="p">)</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="c1"># environment in a python package</span>
|
||||
<span class="n">env_class</span> <span class="o">=</span> <span class="n">gym</span><span class="o">.</span><span class="n">envs</span><span class="o">.</span><span class="n">registration</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">env_id</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># instantiate the environment</span>
|
||||
<span class="k">try</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">env</span> <span class="o">=</span> <span class="n">env_class</span><span class="p">(</span><span class="o">**</span><span class="bp">self</span><span class="o">.</span><span class="n">additional_simulator_parameters</span><span class="p">)</span>
|
||||
<span class="k">except</span><span class="p">:</span>
|
||||
<span class="n">screen</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="s2">"Failed to instantiate Gym environment class </span><span class="si">%s</span><span class="s2"> with arguments </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span>
|
||||
<span class="p">(</span><span class="n">env_class</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">additional_simulator_parameters</span><span class="p">),</span> <span class="n">crash</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
|
||||
<span class="k">raise</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">env</span> <span class="o">=</span> <span class="n">gym</span><span class="o">.</span><span class="n">make</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">env_id</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># for classic control we want to use the native renderer because otherwise we will get 2 renderer windows</span>
|
||||
<span class="n">environment_to_always_use_with_native_rendering</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'classic_control'</span><span class="p">,</span> <span class="s1">'mujoco'</span><span class="p">,</span> <span class="s1">'robotics'</span><span class="p">]</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">native_rendering</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">native_rendering</span> <span class="ow">or</span> \
|
||||
<span class="nb">any</span><span class="p">([</span><span class="n">env</span> <span class="ow">in</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="vm">__class__</span><span class="p">)</span>
|
||||
<span class="k">for</span> <span class="n">env</span> <span class="ow">in</span> <span class="n">environment_to_always_use_with_native_rendering</span><span class="p">])</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">native_rendering</span><span class="p">:</span>
|
||||
<span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s1">'renderer'</span><span class="p">):</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">renderer</span><span class="o">.</span><span class="n">close</span><span class="p">()</span>
|
||||
|
||||
<span class="c1"># seed</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">seed</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">seed</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">seed</span><span class="p">)</span>
|
||||
<span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">seed</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">seed</span><span class="p">)</span>
|
||||
<span class="n">random</span><span class="o">.</span><span class="n">seed</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">seed</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># frame skip and max between consecutive frames</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">is_robotics_env</span> <span class="o">=</span> <span class="s1">'robotics'</span> <span class="ow">in</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="vm">__class__</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">is_mujoco_env</span> <span class="o">=</span> <span class="s1">'mujoco'</span> <span class="ow">in</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="vm">__class__</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">is_atari_env</span> <span class="o">=</span> <span class="s1">'Atari'</span> <span class="ow">in</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="vm">__class__</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">timelimit_env_wrapper</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_atari_env</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="n">frameskip</span> <span class="o">=</span> <span class="mi">1</span> <span class="c1"># this accesses the atari env that is wrapped with a timelimit wrapper env</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">env_id</span> <span class="o">==</span> <span class="s2">"SpaceInvadersDeterministic-v4"</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">frame_skip</span> <span class="o">==</span> <span class="mi">4</span><span class="p">:</span>
|
||||
<span class="n">screen</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span><span class="s2">"Warning: The frame-skip for Space Invaders was automatically updated from 4 to 3. "</span>
|
||||
<span class="s2">"This is following the DQN paper where it was noticed that a frame-skip of 3 makes the "</span>
|
||||
<span class="s2">"laser rays disappear. To force frame-skip of 4, please use SpaceInvadersNoFrameskip-v4."</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">frame_skip</span> <span class="o">=</span> <span class="mi">3</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">env</span> <span class="o">=</span> <span class="n">MaxOverFramesAndFrameskipEnvWrapper</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="p">,</span>
|
||||
<span class="n">frameskip</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">frame_skip</span><span class="p">,</span>
|
||||
<span class="n">max_over_num_frames</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">max_over_num_frames</span><span class="p">)</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="n">frameskip</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">frame_skip</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">state_space</span> <span class="o">=</span> <span class="n">StateSpace</span><span class="p">({})</span>
|
||||
|
||||
<span class="c1"># observations</span>
|
||||
<span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">observation_space</span><span class="p">,</span> <span class="n">gym</span><span class="o">.</span><span class="n">spaces</span><span class="o">.</span><span class="n">dict_space</span><span class="o">.</span><span class="n">Dict</span><span class="p">):</span>
|
||||
<span class="n">state_space</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'observation'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">observation_space</span><span class="p">}</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="n">state_space</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">observation_space</span><span class="o">.</span><span class="n">spaces</span>
|
||||
|
||||
<span class="k">for</span> <span class="n">observation_space_name</span><span class="p">,</span> <span class="n">observation_space</span> <span class="ow">in</span> <span class="n">state_space</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
|
||||
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">observation_space</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span> <span class="o">==</span> <span class="mi">3</span><span class="p">:</span>
|
||||
<span class="c1"># we assume gym has image observations (with arbitrary number of channels) where their values are</span>
|
||||
<span class="c1"># within 0-255, and where the channel dimension is the last dimension</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">state_space</span><span class="p">[</span><span class="n">observation_space_name</span><span class="p">]</span> <span class="o">=</span> <span class="n">ImageObservationSpace</span><span class="p">(</span>
|
||||
<span class="n">shape</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">observation_space</span><span class="o">.</span><span class="n">shape</span><span class="p">),</span>
|
||||
<span class="n">high</span><span class="o">=</span><span class="mi">255</span><span class="p">,</span>
|
||||
<span class="n">channels_axis</span><span class="o">=-</span><span class="mi">1</span>
|
||||
<span class="p">)</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">state_space</span><span class="p">[</span><span class="n">observation_space_name</span><span class="p">]</span> <span class="o">=</span> <span class="n">VectorObservationSpace</span><span class="p">(</span>
|
||||
<span class="n">shape</span><span class="o">=</span><span class="n">observation_space</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span>
|
||||
<span class="n">low</span><span class="o">=</span><span class="n">observation_space</span><span class="o">.</span><span class="n">low</span><span class="p">,</span>
|
||||
<span class="n">high</span><span class="o">=</span><span class="n">observation_space</span><span class="o">.</span><span class="n">high</span>
|
||||
<span class="p">)</span>
|
||||
<span class="k">if</span> <span class="s1">'desired_goal'</span> <span class="ow">in</span> <span class="n">state_space</span><span class="o">.</span><span class="n">keys</span><span class="p">():</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">goal_space</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">state_space</span><span class="p">[</span><span class="s1">'desired_goal'</span><span class="p">]</span>
|
||||
|
||||
<span class="c1"># actions</span>
|
||||
<span class="k">if</span> <span class="nb">type</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">action_space</span><span class="p">)</span> <span class="o">==</span> <span class="n">gym</span><span class="o">.</span><span class="n">spaces</span><span class="o">.</span><span class="n">box</span><span class="o">.</span><span class="n">Box</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">action_space</span> <span class="o">=</span> <span class="n">BoxActionSpace</span><span class="p">(</span>
|
||||
<span class="n">shape</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">action_space</span><span class="o">.</span><span class="n">shape</span><span class="p">,</span>
|
||||
<span class="n">low</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">action_space</span><span class="o">.</span><span class="n">low</span><span class="p">,</span>
|
||||
<span class="n">high</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">action_space</span><span class="o">.</span><span class="n">high</span>
|
||||
<span class="p">)</span>
|
||||
<span class="k">elif</span> <span class="nb">type</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">action_space</span><span class="p">)</span> <span class="o">==</span> <span class="n">gym</span><span class="o">.</span><span class="n">spaces</span><span class="o">.</span><span class="n">discrete</span><span class="o">.</span><span class="n">Discrete</span><span class="p">:</span>
|
||||
<span class="n">actions_description</span> <span class="o">=</span> <span class="p">[]</span>
|
||||
<span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="p">,</span> <span class="s1">'get_action_meanings'</span><span class="p">):</span>
|
||||
<span class="n">actions_description</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="n">get_action_meanings</span><span class="p">()</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">action_space</span> <span class="o">=</span> <span class="n">DiscreteActionSpace</span><span class="p">(</span>
|
||||
<span class="n">num_actions</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">action_space</span><span class="o">.</span><span class="n">n</span><span class="p">,</span>
|
||||
<span class="n">descriptions</span><span class="o">=</span><span class="n">actions_description</span>
|
||||
<span class="p">)</span>
|
||||
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">human_control</span><span class="p">:</span>
|
||||
<span class="c1"># TODO: add this to the action space</span>
|
||||
<span class="c1"># map keyboard keys to actions</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">key_to_action</span> <span class="o">=</span> <span class="p">{}</span>
|
||||
<span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="p">,</span> <span class="s1">'get_keys_to_action'</span><span class="p">):</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">key_to_action</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="n">get_keys_to_action</span><span class="p">()</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="n">screen</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="s2">"Error: Environment </span><span class="si">{}</span><span class="s2"> does not support human control."</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="p">),</span> <span class="n">crash</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># initialize the state by getting a new state from the environment</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reset_internal_state</span><span class="p">(</span><span class="kc">True</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># render</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_rendered</span><span class="p">:</span>
|
||||
<span class="n">image</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_rendered_image</span><span class="p">()</span>
|
||||
<span class="n">scale</span> <span class="o">=</span> <span class="mi">1</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">human_control</span><span class="p">:</span>
|
||||
<span class="n">scale</span> <span class="o">=</span> <span class="mi">2</span>
|
||||
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">native_rendering</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">renderer</span><span class="o">.</span><span class="n">create_screen</span><span class="p">(</span><span class="n">image</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span><span class="o">*</span><span class="n">scale</span><span class="p">,</span> <span class="n">image</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">*</span><span class="n">scale</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># measurements</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">spec</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">timestep_limit</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">spec</span><span class="o">.</span><span class="n">timestep_limit</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">timestep_limit</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
|
||||
<span class="c1"># the info is only updated after the first step</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">state</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">step</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">action_space</span><span class="o">.</span><span class="n">default_action</span><span class="p">)</span><span class="o">.</span><span class="n">next_state</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">state_space</span><span class="p">[</span><span class="s1">'measurements'</span><span class="p">]</span> <span class="o">=</span> <span class="n">VectorObservationSpace</span><span class="p">(</span><span class="n">shape</span><span class="o">=</span><span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">info</span><span class="o">.</span><span class="n">keys</span><span class="p">()))</span>
|
||||
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">spec</span> <span class="ow">and</span> <span class="n">custom_reward_threshold</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reward_success_threshold</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">spec</span><span class="o">.</span><span class="n">reward_threshold</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reward_space</span> <span class="o">=</span> <span class="n">RewardSpace</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="n">reward_success_threshold</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">reward_success_threshold</span><span class="p">)</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">target_success_rate</span> <span class="o">=</span> <span class="n">target_success_rate</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_wrap_state</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">state</span><span class="p">):</span>
|
||||
<span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">observation_space</span><span class="p">,</span> <span class="n">gym</span><span class="o">.</span><span class="n">spaces</span><span class="o">.</span><span class="n">Dict</span><span class="p">):</span>
|
||||
<span class="k">return</span> <span class="p">{</span><span class="s1">'observation'</span><span class="p">:</span> <span class="n">state</span><span class="p">}</span>
|
||||
<span class="k">return</span> <span class="n">state</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_update_state</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_atari_env</span> <span class="ow">and</span> <span class="nb">hasattr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s1">'current_ale_lives'</span><span class="p">)</span> \
|
||||
<span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">current_ale_lives</span> <span class="o">!=</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="n">ale</span><span class="o">.</span><span class="n">lives</span><span class="p">():</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">phase</span> <span class="o">==</span> <span class="n">RunPhase</span><span class="o">.</span><span class="n">TRAIN</span> <span class="ow">or</span> <span class="bp">self</span><span class="o">.</span><span class="n">phase</span> <span class="o">==</span> <span class="n">RunPhase</span><span class="o">.</span><span class="n">HEATUP</span><span class="p">:</span>
|
||||
<span class="c1"># signal termination for life loss</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">done</span> <span class="o">=</span> <span class="kc">True</span>
|
||||
<span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">phase</span> <span class="o">==</span> <span class="n">RunPhase</span><span class="o">.</span><span class="n">TEST</span> <span class="ow">and</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">done</span><span class="p">:</span>
|
||||
<span class="c1"># the episode is not terminated in evaluation, but we need to press fire again</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_press_fire</span><span class="p">()</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_update_ale_lives</span><span class="p">()</span>
|
||||
<span class="c1"># TODO: update the measurements</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">state</span> <span class="ow">and</span> <span class="s2">"desired_goal"</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">state</span><span class="o">.</span><span class="n">keys</span><span class="p">():</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">goal</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">state</span><span class="p">[</span><span class="s1">'desired_goal'</span><span class="p">]</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_take_action</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">action</span><span class="p">):</span>
|
||||
<span class="k">if</span> <span class="nb">type</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">action_space</span><span class="p">)</span> <span class="o">==</span> <span class="n">BoxActionSpace</span><span class="p">:</span>
|
||||
<span class="n">action</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">action_space</span><span class="o">.</span><span class="n">clip_action_to_space</span><span class="p">(</span><span class="n">action</span><span class="p">)</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">state</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">reward</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">done</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">info</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">step</span><span class="p">(</span><span class="n">action</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">state</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_wrap_state</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">state</span><span class="p">)</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_random_noop</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="c1"># simulate a random initial environment state by stepping for a random number of times between 0 and 30</span>
|
||||
<span class="n">step_count</span> <span class="o">=</span> <span class="mi">0</span>
|
||||
<span class="n">random_initialization_steps</span> <span class="o">=</span> <span class="n">random</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">random_initialization_steps</span><span class="p">)</span>
|
||||
<span class="k">while</span> <span class="bp">self</span><span class="o">.</span><span class="n">action_space</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">state</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">step_count</span> <span class="o"><</span> <span class="n">random_initialization_steps</span><span class="p">):</span>
|
||||
<span class="n">step_count</span> <span class="o">+=</span> <span class="mi">1</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">step</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">action_space</span><span class="o">.</span><span class="n">default_action</span><span class="p">)</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_press_fire</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="n">fire_action</span> <span class="o">=</span> <span class="mi">1</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_atari_env</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="n">get_action_meanings</span><span class="p">()[</span><span class="n">fire_action</span><span class="p">]</span> <span class="o">==</span> <span class="s1">'FIRE'</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">current_ale_lives</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="n">ale</span><span class="o">.</span><span class="n">lives</span><span class="p">()</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">step</span><span class="p">(</span><span class="n">fire_action</span><span class="p">)</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">done</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reset_internal_state</span><span class="p">()</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_update_ale_lives</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_atari_env</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">current_ale_lives</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="n">ale</span><span class="o">.</span><span class="n">lives</span><span class="p">()</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_restart_environment_episode</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">force_environment_reset</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
|
||||
<span class="c1"># prevent reset of environment if there are ale lives left</span>
|
||||
<span class="k">if</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">is_atari_env</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="n">ale</span><span class="o">.</span><span class="n">lives</span><span class="p">()</span> <span class="o">></span> <span class="mi">0</span><span class="p">)</span> \
|
||||
<span class="ow">and</span> <span class="ow">not</span> <span class="n">force_environment_reset</span> <span class="ow">and</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">timelimit_env_wrapper</span><span class="o">.</span><span class="n">_past_limit</span><span class="p">():</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">step</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">action_space</span><span class="o">.</span><span class="n">default_action</span><span class="p">)</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">state</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">reset</span><span class="p">()</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">state</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_wrap_state</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">state</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_update_ale_lives</span><span class="p">()</span>
|
||||
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_atari_env</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_random_noop</span><span class="p">()</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_press_fire</span><span class="p">()</span>
|
||||
|
||||
<span class="c1"># initialize the number of lives</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_update_ale_lives</span><span class="p">()</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_set_mujoco_camera</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">camera_idx</span><span class="p">:</span> <span class="nb">int</span><span class="p">):</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> This function can be used to set the camera for rendering the mujoco simulator</span>
|
||||
<span class="sd"> :param camera_idx: The index of the camera to use. Should be defined in the model</span>
|
||||
<span class="sd"> :return: None</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="n">viewer</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="n">viewer</span><span class="o">.</span><span class="n">cam</span><span class="o">.</span><span class="n">fixedcamid</span> <span class="o">!=</span> <span class="n">camera_idx</span> <span class="ow">and</span>\
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="n">viewer</span><span class="o">.</span><span class="n">_ncam</span> <span class="o">></span> <span class="n">camera_idx</span><span class="p">:</span>
|
||||
<span class="kn">from</span> <span class="nn">mujoco_py.generated</span> <span class="k">import</span> <span class="n">const</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="n">viewer</span><span class="o">.</span><span class="n">cam</span><span class="o">.</span><span class="n">type</span> <span class="o">=</span> <span class="n">const</span><span class="o">.</span><span class="n">CAMERA_FIXED</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="n">viewer</span><span class="o">.</span><span class="n">cam</span><span class="o">.</span><span class="n">fixedcamid</span> <span class="o">=</span> <span class="n">camera_idx</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_get_robotics_image</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">render</span><span class="p">()</span>
|
||||
<span class="n">image</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="n">_get_viewer</span><span class="p">()</span><span class="o">.</span><span class="n">read_pixels</span><span class="p">(</span><span class="mi">1600</span><span class="p">,</span> <span class="mi">900</span><span class="p">,</span> <span class="n">depth</span><span class="o">=</span><span class="kc">False</span><span class="p">)[::</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="p">:,</span> <span class="p">:]</span>
|
||||
<span class="n">image</span> <span class="o">=</span> <span class="n">scipy</span><span class="o">.</span><span class="n">misc</span><span class="o">.</span><span class="n">imresize</span><span class="p">(</span><span class="n">image</span><span class="p">,</span> <span class="p">(</span><span class="mi">270</span><span class="p">,</span> <span class="mi">480</span><span class="p">,</span> <span class="mi">3</span><span class="p">))</span>
|
||||
<span class="k">return</span> <span class="n">image</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_render</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">render</span><span class="p">(</span><span class="n">mode</span><span class="o">=</span><span class="s1">'human'</span><span class="p">)</span>
|
||||
<span class="c1"># required for setting up a fixed camera for mujoco</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_mujoco_env</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_set_mujoco_camera</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">get_rendered_image</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_robotics_env</span><span class="p">:</span>
|
||||
<span class="c1"># necessary for fetch since the rendered image is cropped to an irrelevant part of the simulator</span>
|
||||
<span class="n">image</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_robotics_image</span><span class="p">()</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="n">image</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">render</span><span class="p">(</span><span class="n">mode</span><span class="o">=</span><span class="s1">'rgb_array'</span><span class="p">)</span>
|
||||
<span class="c1"># required for setting up a fixed camera for mujoco</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_mujoco_env</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_set_mujoco_camera</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
|
||||
<span class="k">return</span> <span class="n">image</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">get_target_success_rate</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">float</span><span class="p">:</span>
|
||||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">target_success_rate</span></div>
|
||||
</pre></div>
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
<footer>
|
||||
|
||||
|
||||
<hr/>
|
||||
|
||||
<div role="contentinfo">
|
||||
<p>
|
||||
© Copyright 2018, Intel AI Lab
|
||||
|
||||
</p>
|
||||
</div>
|
||||
Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
|
||||
|
||||
</footer>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
|
||||
</section>
|
||||
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<script type="text/javascript" id="documentation_options" data-url_root="../../../" src="../../../_static/documentation_options.js"></script>
|
||||
<script type="text/javascript" src="../../../_static/jquery.js"></script>
|
||||
<script type="text/javascript" src="../../../_static/underscore.js"></script>
|
||||
<script type="text/javascript" src="../../../_static/doctools.js"></script>
|
||||
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></script>
|
||||
|
||||
|
||||
|
||||
|
||||
<script type="text/javascript" src="../../../_static/js/theme.js"></script>
|
||||
|
||||
<script type="text/javascript">
|
||||
jQuery(function () {
|
||||
SphinxRtdTheme.Navigation.enable(true);
|
||||
});
|
||||
</script>
|
||||
|
||||
</body>
|
||||
</html>
|
||||
478
docs/_modules/rl_coach/environments/starcraft2_environment.html
Normal file
478
docs/_modules/rl_coach/environments/starcraft2_environment.html
Normal file
@@ -0,0 +1,478 @@
|
||||
|
||||
|
||||
<!DOCTYPE html>
|
||||
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
|
||||
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
|
||||
<head>
|
||||
<meta charset="utf-8">
|
||||
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
|
||||
<title>rl_coach.environments.starcraft2_environment — Reinforcement Learning Coach 0.11.0 documentation</title>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
|
||||
<link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
|
||||
<link rel="stylesheet" href="../../../_static/css/custom.css" type="text/css" />
|
||||
<link rel="index" title="Index" href="../../../genindex.html" />
|
||||
<link rel="search" title="Search" href="../../../search.html" />
|
||||
<link href="../../../_static/css/custom.css" rel="stylesheet" type="text/css">
|
||||
|
||||
|
||||
|
||||
<script src="../../../_static/js/modernizr.min.js"></script>
|
||||
|
||||
</head>
|
||||
|
||||
<body class="wy-body-for-nav">
|
||||
|
||||
|
||||
<div class="wy-grid-for-nav">
|
||||
|
||||
|
||||
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
|
||||
<div class="wy-side-scroll">
|
||||
<div class="wy-side-nav-search">
|
||||
|
||||
|
||||
|
||||
<a href="../../../index.html" class="icon icon-home"> Reinforcement Learning Coach
|
||||
|
||||
|
||||
|
||||
|
||||
<img src="../../../_static/dark_logo.png" class="logo" alt="Logo"/>
|
||||
|
||||
</a>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<div role="search">
|
||||
<form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get">
|
||||
<input type="text" name="q" placeholder="Search docs" />
|
||||
<input type="hidden" name="check_keywords" value="yes" />
|
||||
<input type="hidden" name="area" value="default" />
|
||||
</form>
|
||||
</div>
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<p class="caption"><span class="caption-text">Intro</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../usage.html">Usage</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../features/index.html">Features</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../selecting_an_algorithm.html">Selecting an Algorithm</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../dashboard.html">Coach Dashboard</a></li>
|
||||
</ul>
|
||||
<p class="caption"><span class="caption-text">Design</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../design/control_flow.html">Control Flow</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../design/network.html">Network Design</a></li>
|
||||
</ul>
|
||||
<p class="caption"><span class="caption-text">Contributing</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../contributing/add_agent.html">Adding a New Agent</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../contributing/add_env.html">Adding a New Environment</a></li>
|
||||
</ul>
|
||||
<p class="caption"><span class="caption-text">Components</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/agents/index.html">Agents</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/architectures/index.html">Architectures</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/environments/index.html">Environments</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/exploration_policies/index.html">Exploration Policies</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/filters/index.html">Filters</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/memories/index.html">Memories</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/core_types.html">Core Types</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/spaces.html">Spaces</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../components/additional_parameters.html">Additional Parameters</a></li>
|
||||
</ul>
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
</nav>
|
||||
|
||||
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
|
||||
|
||||
|
||||
<nav class="wy-nav-top" aria-label="top navigation">
|
||||
|
||||
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
|
||||
<a href="../../../index.html">Reinforcement Learning Coach</a>
|
||||
|
||||
</nav>
|
||||
|
||||
|
||||
<div class="wy-nav-content">
|
||||
|
||||
<div class="rst-content">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<div role="navigation" aria-label="breadcrumbs navigation">
|
||||
|
||||
<ul class="wy-breadcrumbs">
|
||||
|
||||
<li><a href="../../../index.html">Docs</a> »</li>
|
||||
|
||||
<li><a href="../../index.html">Module code</a> »</li>
|
||||
|
||||
<li>rl_coach.environments.starcraft2_environment</li>
|
||||
|
||||
|
||||
<li class="wy-breadcrumbs-aside">
|
||||
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
|
||||
|
||||
<hr/>
|
||||
</div>
|
||||
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
|
||||
<div itemprop="articleBody">
|
||||
|
||||
<h1>Source code for rl_coach.environments.starcraft2_environment</h1><div class="highlight"><pre>
|
||||
<span></span><span class="c1">#</span>
|
||||
<span class="c1"># Copyright (c) 2017 Intel Corporation</span>
|
||||
<span class="c1">#</span>
|
||||
<span class="c1"># Licensed under the Apache License, Version 2.0 (the "License");</span>
|
||||
<span class="c1"># you may not use this file except in compliance with the License.</span>
|
||||
<span class="c1"># You may obtain a copy of the License at</span>
|
||||
<span class="c1">#</span>
|
||||
<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
|
||||
<span class="c1">#</span>
|
||||
<span class="c1"># Unless required by applicable law or agreed to in writing, software</span>
|
||||
<span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span>
|
||||
<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
|
||||
<span class="c1"># See the License for the specific language governing permissions and</span>
|
||||
<span class="c1"># limitations under the License.</span>
|
||||
<span class="c1">#</span>
|
||||
|
||||
|
||||
<span class="kn">from</span> <span class="nn">enum</span> <span class="k">import</span> <span class="n">Enum</span>
|
||||
<span class="kn">from</span> <span class="nn">typing</span> <span class="k">import</span> <span class="n">Union</span><span class="p">,</span> <span class="n">List</span>
|
||||
|
||||
<span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
|
||||
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.filters.observation.observation_move_axis_filter</span> <span class="k">import</span> <span class="n">ObservationMoveAxisFilter</span>
|
||||
|
||||
<span class="k">try</span><span class="p">:</span>
|
||||
<span class="kn">from</span> <span class="nn">pysc2</span> <span class="k">import</span> <span class="n">maps</span>
|
||||
<span class="kn">from</span> <span class="nn">pysc2.env</span> <span class="k">import</span> <span class="n">sc2_env</span>
|
||||
<span class="kn">from</span> <span class="nn">pysc2.env</span> <span class="k">import</span> <span class="n">available_actions_printer</span>
|
||||
<span class="kn">from</span> <span class="nn">pysc2.lib</span> <span class="k">import</span> <span class="n">actions</span>
|
||||
<span class="kn">from</span> <span class="nn">pysc2.lib</span> <span class="k">import</span> <span class="n">features</span>
|
||||
<span class="kn">from</span> <span class="nn">pysc2.env</span> <span class="k">import</span> <span class="n">environment</span>
|
||||
<span class="kn">from</span> <span class="nn">absl</span> <span class="k">import</span> <span class="n">app</span>
|
||||
<span class="kn">from</span> <span class="nn">absl</span> <span class="k">import</span> <span class="n">flags</span>
|
||||
<span class="k">except</span> <span class="ne">ImportError</span><span class="p">:</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.logger</span> <span class="k">import</span> <span class="n">failed_imports</span>
|
||||
<span class="n">failed_imports</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s2">"PySc2"</span><span class="p">)</span>
|
||||
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.environments.environment</span> <span class="k">import</span> <span class="n">Environment</span><span class="p">,</span> <span class="n">EnvironmentParameters</span><span class="p">,</span> <span class="n">LevelSelection</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.base_parameters</span> <span class="k">import</span> <span class="n">VisualizationParameters</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.spaces</span> <span class="k">import</span> <span class="n">BoxActionSpace</span><span class="p">,</span> <span class="n">VectorObservationSpace</span><span class="p">,</span> <span class="n">PlanarMapsObservationSpace</span><span class="p">,</span> <span class="n">StateSpace</span><span class="p">,</span> <span class="n">CompoundActionSpace</span><span class="p">,</span> \
|
||||
<span class="n">DiscreteActionSpace</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.filters.filter</span> <span class="k">import</span> <span class="n">InputFilter</span><span class="p">,</span> <span class="n">OutputFilter</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.filters.observation.observation_rescale_to_size_filter</span> <span class="k">import</span> <span class="n">ObservationRescaleToSizeFilter</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.filters.action.linear_box_to_box_map</span> <span class="k">import</span> <span class="n">LinearBoxToBoxMap</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.filters.observation.observation_to_uint8_filter</span> <span class="k">import</span> <span class="n">ObservationToUInt8Filter</span>
|
||||
|
||||
<span class="n">FLAGS</span> <span class="o">=</span> <span class="n">flags</span><span class="o">.</span><span class="n">FLAGS</span>
|
||||
<span class="n">FLAGS</span><span class="p">([</span><span class="s1">'coach.py'</span><span class="p">])</span>
|
||||
|
||||
<span class="n">SCREEN_SIZE</span> <span class="o">=</span> <span class="mi">84</span> <span class="c1"># will also impact the action space size</span>
|
||||
|
||||
<span class="c1"># Starcraft Constants</span>
|
||||
<span class="n">_NOOP</span> <span class="o">=</span> <span class="n">actions</span><span class="o">.</span><span class="n">FUNCTIONS</span><span class="o">.</span><span class="n">no_op</span><span class="o">.</span><span class="n">id</span>
|
||||
<span class="n">_MOVE_SCREEN</span> <span class="o">=</span> <span class="n">actions</span><span class="o">.</span><span class="n">FUNCTIONS</span><span class="o">.</span><span class="n">Move_screen</span><span class="o">.</span><span class="n">id</span>
|
||||
<span class="n">_SELECT_ARMY</span> <span class="o">=</span> <span class="n">actions</span><span class="o">.</span><span class="n">FUNCTIONS</span><span class="o">.</span><span class="n">select_army</span><span class="o">.</span><span class="n">id</span>
|
||||
<span class="n">_PLAYER_RELATIVE</span> <span class="o">=</span> <span class="n">features</span><span class="o">.</span><span class="n">SCREEN_FEATURES</span><span class="o">.</span><span class="n">player_relative</span><span class="o">.</span><span class="n">index</span>
|
||||
<span class="n">_NOT_QUEUED</span> <span class="o">=</span> <span class="p">[</span><span class="mi">0</span><span class="p">]</span>
|
||||
<span class="n">_SELECT_ALL</span> <span class="o">=</span> <span class="p">[</span><span class="mi">0</span><span class="p">]</span>
|
||||
|
||||
|
||||
<span class="k">class</span> <span class="nc">StarcraftObservationType</span><span class="p">(</span><span class="n">Enum</span><span class="p">):</span>
|
||||
<span class="n">Features</span> <span class="o">=</span> <span class="mi">0</span>
|
||||
<span class="n">RGB</span> <span class="o">=</span> <span class="mi">1</span>
|
||||
|
||||
|
||||
<span class="n">StarcraftInputFilter</span> <span class="o">=</span> <span class="n">InputFilter</span><span class="p">(</span><span class="n">is_a_reference_filter</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||||
<span class="n">StarcraftInputFilter</span><span class="o">.</span><span class="n">add_observation_filter</span><span class="p">(</span><span class="s1">'screen'</span><span class="p">,</span> <span class="s1">'move_axis'</span><span class="p">,</span> <span class="n">ObservationMoveAxisFilter</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="o">-</span><span class="mi">1</span><span class="p">))</span>
|
||||
<span class="n">StarcraftInputFilter</span><span class="o">.</span><span class="n">add_observation_filter</span><span class="p">(</span><span class="s1">'screen'</span><span class="p">,</span> <span class="s1">'rescaling'</span><span class="p">,</span>
|
||||
<span class="n">ObservationRescaleToSizeFilter</span><span class="p">(</span>
|
||||
<span class="n">PlanarMapsObservationSpace</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="mi">84</span><span class="p">,</span> <span class="mi">84</span><span class="p">,</span> <span class="mi">1</span><span class="p">]),</span>
|
||||
<span class="n">low</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">high</span><span class="o">=</span><span class="mi">255</span><span class="p">,</span> <span class="n">channels_axis</span><span class="o">=-</span><span class="mi">1</span><span class="p">)))</span>
|
||||
<span class="n">StarcraftInputFilter</span><span class="o">.</span><span class="n">add_observation_filter</span><span class="p">(</span><span class="s1">'screen'</span><span class="p">,</span> <span class="s1">'to_uint8'</span><span class="p">,</span> <span class="n">ObservationToUInt8Filter</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">255</span><span class="p">))</span>
|
||||
|
||||
<span class="n">StarcraftInputFilter</span><span class="o">.</span><span class="n">add_observation_filter</span><span class="p">(</span><span class="s1">'minimap'</span><span class="p">,</span> <span class="s1">'move_axis'</span><span class="p">,</span> <span class="n">ObservationMoveAxisFilter</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="o">-</span><span class="mi">1</span><span class="p">))</span>
|
||||
<span class="n">StarcraftInputFilter</span><span class="o">.</span><span class="n">add_observation_filter</span><span class="p">(</span><span class="s1">'minimap'</span><span class="p">,</span> <span class="s1">'rescaling'</span><span class="p">,</span>
|
||||
<span class="n">ObservationRescaleToSizeFilter</span><span class="p">(</span>
|
||||
<span class="n">PlanarMapsObservationSpace</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="mi">64</span><span class="p">,</span> <span class="mi">64</span><span class="p">,</span> <span class="mi">1</span><span class="p">]),</span>
|
||||
<span class="n">low</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">high</span><span class="o">=</span><span class="mi">255</span><span class="p">,</span> <span class="n">channels_axis</span><span class="o">=-</span><span class="mi">1</span><span class="p">)))</span>
|
||||
<span class="n">StarcraftInputFilter</span><span class="o">.</span><span class="n">add_observation_filter</span><span class="p">(</span><span class="s1">'minimap'</span><span class="p">,</span> <span class="s1">'to_uint8'</span><span class="p">,</span> <span class="n">ObservationToUInt8Filter</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">255</span><span class="p">))</span>
|
||||
|
||||
|
||||
<span class="n">StarcraftNormalizingOutputFilter</span> <span class="o">=</span> <span class="n">OutputFilter</span><span class="p">(</span><span class="n">is_a_reference_filter</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||||
<span class="n">StarcraftNormalizingOutputFilter</span><span class="o">.</span><span class="n">add_action_filter</span><span class="p">(</span>
|
||||
<span class="s1">'normalization'</span><span class="p">,</span> <span class="n">LinearBoxToBoxMap</span><span class="p">(</span><span class="n">input_space_low</span><span class="o">=-</span><span class="n">SCREEN_SIZE</span> <span class="o">/</span> <span class="mi">2</span><span class="p">,</span> <span class="n">input_space_high</span><span class="o">=</span><span class="n">SCREEN_SIZE</span> <span class="o">/</span> <span class="mi">2</span> <span class="o">-</span> <span class="mi">1</span><span class="p">))</span>
|
||||
|
||||
|
||||
<span class="k">class</span> <span class="nc">StarCraft2EnvironmentParameters</span><span class="p">(</span><span class="n">EnvironmentParameters</span><span class="p">):</span>
|
||||
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">level</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">level</span><span class="o">=</span><span class="n">level</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">screen_size</span> <span class="o">=</span> <span class="mi">84</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">minimap_size</span> <span class="o">=</span> <span class="mi">64</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">feature_minimap_maps_to_use</span> <span class="o">=</span> <span class="nb">range</span><span class="p">(</span><span class="mi">7</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">feature_screen_maps_to_use</span> <span class="o">=</span> <span class="nb">range</span><span class="p">(</span><span class="mi">17</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">observation_type</span> <span class="o">=</span> <span class="n">StarcraftObservationType</span><span class="o">.</span><span class="n">Features</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">disable_fog</span> <span class="o">=</span> <span class="kc">False</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">auto_select_all_army</span> <span class="o">=</span> <span class="kc">True</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">default_input_filter</span> <span class="o">=</span> <span class="n">StarcraftInputFilter</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">default_output_filter</span> <span class="o">=</span> <span class="n">StarcraftNormalizingOutputFilter</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">use_full_action_space</span> <span class="o">=</span> <span class="kc">False</span>
|
||||
|
||||
|
||||
<span class="nd">@property</span>
|
||||
<span class="k">def</span> <span class="nf">path</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="k">return</span> <span class="s1">'rl_coach.environments.starcraft2_environment:StarCraft2Environment'</span>
|
||||
|
||||
|
||||
<span class="c1"># Environment</span>
|
||||
<div class="viewcode-block" id="StarCraft2Environment"><a class="viewcode-back" href="../../../components/environments/index.html#rl_coach.environments.starcraft2_environment.StarCraft2Environment">[docs]</a><span class="k">class</span> <span class="nc">StarCraft2Environment</span><span class="p">(</span><span class="n">Environment</span><span class="p">):</span>
|
||||
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">level</span><span class="p">:</span> <span class="n">LevelSelection</span><span class="p">,</span> <span class="n">frame_skip</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">visualization_parameters</span><span class="p">:</span> <span class="n">VisualizationParameters</span><span class="p">,</span>
|
||||
<span class="n">target_success_rate</span><span class="p">:</span> <span class="nb">float</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span> <span class="n">seed</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="kc">None</span><span class="p">,</span> <span class="nb">int</span><span class="p">]</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">human_control</span><span class="p">:</span> <span class="nb">bool</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||||
<span class="n">custom_reward_threshold</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">]</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
|
||||
<span class="n">screen_size</span><span class="p">:</span> <span class="nb">int</span><span class="o">=</span><span class="mi">84</span><span class="p">,</span> <span class="n">minimap_size</span><span class="p">:</span> <span class="nb">int</span><span class="o">=</span><span class="mi">64</span><span class="p">,</span>
|
||||
<span class="n">feature_minimap_maps_to_use</span><span class="p">:</span> <span class="n">List</span><span class="o">=</span><span class="nb">range</span><span class="p">(</span><span class="mi">7</span><span class="p">),</span> <span class="n">feature_screen_maps_to_use</span><span class="p">:</span> <span class="n">List</span><span class="o">=</span><span class="nb">range</span><span class="p">(</span><span class="mi">17</span><span class="p">),</span>
|
||||
<span class="n">observation_type</span><span class="p">:</span> <span class="n">StarcraftObservationType</span><span class="o">=</span><span class="n">StarcraftObservationType</span><span class="o">.</span><span class="n">Features</span><span class="p">,</span>
|
||||
<span class="n">disable_fog</span><span class="p">:</span> <span class="nb">bool</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">auto_select_all_army</span><span class="p">:</span> <span class="nb">bool</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
|
||||
<span class="n">use_full_action_space</span><span class="p">:</span> <span class="nb">bool</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">level</span><span class="p">,</span> <span class="n">seed</span><span class="p">,</span> <span class="n">frame_skip</span><span class="p">,</span> <span class="n">human_control</span><span class="p">,</span> <span class="n">custom_reward_threshold</span><span class="p">,</span> <span class="n">visualization_parameters</span><span class="p">,</span> <span class="n">target_success_rate</span><span class="p">)</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">screen_size</span> <span class="o">=</span> <span class="n">screen_size</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">minimap_size</span> <span class="o">=</span> <span class="n">minimap_size</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">feature_minimap_maps_to_use</span> <span class="o">=</span> <span class="n">feature_minimap_maps_to_use</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">feature_screen_maps_to_use</span> <span class="o">=</span> <span class="n">feature_screen_maps_to_use</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">observation_type</span> <span class="o">=</span> <span class="n">observation_type</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">features_screen_size</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">feature_minimap_size</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">rgb_screen_size</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">rgb_minimap_size</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">observation_type</span> <span class="o">==</span> <span class="n">StarcraftObservationType</span><span class="o">.</span><span class="n">Features</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">features_screen_size</span> <span class="o">=</span> <span class="n">screen_size</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">feature_minimap_size</span> <span class="o">=</span> <span class="n">minimap_size</span>
|
||||
<span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">observation_type</span> <span class="o">==</span> <span class="n">StarcraftObservationType</span><span class="o">.</span><span class="n">RGB</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">rgb_screen_size</span> <span class="o">=</span> <span class="n">screen_size</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">rgb_minimap_size</span> <span class="o">=</span> <span class="n">minimap_size</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">disable_fog</span> <span class="o">=</span> <span class="n">disable_fog</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">auto_select_all_army</span> <span class="o">=</span> <span class="n">auto_select_all_army</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">use_full_action_space</span> <span class="o">=</span> <span class="n">use_full_action_space</span>
|
||||
|
||||
<span class="c1"># step_mul is the equivalent to frame skipping. Not sure if it repeats actions in between or not though.</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">env</span> <span class="o">=</span> <span class="n">sc2_env</span><span class="o">.</span><span class="n">SC2Env</span><span class="p">(</span><span class="n">map_name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">env_id</span><span class="p">,</span> <span class="n">step_mul</span><span class="o">=</span><span class="n">frame_skip</span><span class="p">,</span>
|
||||
<span class="n">visualize</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">is_rendered</span><span class="p">,</span>
|
||||
<span class="n">agent_interface_format</span><span class="o">=</span><span class="n">sc2_env</span><span class="o">.</span><span class="n">AgentInterfaceFormat</span><span class="p">(</span>
|
||||
<span class="n">feature_dimensions</span><span class="o">=</span><span class="n">sc2_env</span><span class="o">.</span><span class="n">Dimensions</span><span class="p">(</span>
|
||||
<span class="n">screen</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">features_screen_size</span><span class="p">,</span>
|
||||
<span class="n">minimap</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">feature_minimap_size</span>
|
||||
<span class="p">)</span>
|
||||
<span class="c1"># rgb_dimensions=sc2_env.Dimensions(</span>
|
||||
<span class="c1"># screen=self.rgb_screen_size,</span>
|
||||
<span class="c1"># minimap=self.rgb_screen_size</span>
|
||||
<span class="c1"># )</span>
|
||||
<span class="p">),</span>
|
||||
<span class="c1"># feature_screen_size=self.features_screen_size,</span>
|
||||
<span class="c1"># feature_minimap_size=self.feature_minimap_size,</span>
|
||||
<span class="c1"># rgb_screen_size=self.rgb_screen_size,</span>
|
||||
<span class="c1"># rgb_minimap_size=self.rgb_screen_size,</span>
|
||||
<span class="n">disable_fog</span><span class="o">=</span><span class="n">disable_fog</span><span class="p">,</span>
|
||||
<span class="n">random_seed</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">seed</span>
|
||||
<span class="p">)</span>
|
||||
|
||||
<span class="c1"># print all the available actions</span>
|
||||
<span class="c1"># self.env = available_actions_printer.AvailableActionsPrinter(self.env)</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reset_internal_state</span><span class="p">(</span><span class="kc">True</span><span class="p">)</span>
|
||||
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> feature_screen: [height_map, visibility_map, creep, power, player_id, player_relative, unit_type, selected,</span>
|
||||
<span class="sd"> unit_hit_points, unit_hit_points_ratio, unit_energy, unit_energy_ratio, unit_shields,</span>
|
||||
<span class="sd"> unit_shields_ratio, unit_density, unit_density_aa, effects]</span>
|
||||
<span class="sd"> feature_minimap: [height_map, visibility_map, creep, camera, player_id, player_relative, selecte</span>
|
||||
<span class="sd"> d]</span>
|
||||
<span class="sd"> player: [player_id, minerals, vespene, food_cap, food_army, food_workers, idle_worker_dount,</span>
|
||||
<span class="sd"> army_count, warp_gate_count, larva_count]</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">screen_shape</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">observation_spec</span><span class="p">()[</span><span class="mi">0</span><span class="p">][</span><span class="s1">'feature_screen'</span><span class="p">])</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">screen_shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">feature_screen_maps_to_use</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">minimap_shape</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">observation_spec</span><span class="p">()[</span><span class="mi">0</span><span class="p">][</span><span class="s1">'feature_minimap'</span><span class="p">])</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">minimap_shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">feature_minimap_maps_to_use</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">state_space</span> <span class="o">=</span> <span class="n">StateSpace</span><span class="p">({</span>
|
||||
<span class="s2">"screen"</span><span class="p">:</span> <span class="n">PlanarMapsObservationSpace</span><span class="p">(</span><span class="n">shape</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">screen_shape</span><span class="p">,</span> <span class="n">low</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">high</span><span class="o">=</span><span class="mi">255</span><span class="p">,</span> <span class="n">channels_axis</span><span class="o">=</span><span class="mi">0</span><span class="p">),</span>
|
||||
<span class="s2">"minimap"</span><span class="p">:</span> <span class="n">PlanarMapsObservationSpace</span><span class="p">(</span><span class="n">shape</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">minimap_shape</span><span class="p">,</span> <span class="n">low</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">high</span><span class="o">=</span><span class="mi">255</span><span class="p">,</span> <span class="n">channels_axis</span><span class="o">=</span><span class="mi">0</span><span class="p">),</span>
|
||||
<span class="s2">"measurements"</span><span class="p">:</span> <span class="n">VectorObservationSpace</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">observation_spec</span><span class="p">()[</span><span class="mi">0</span><span class="p">][</span><span class="s2">"player"</span><span class="p">][</span><span class="mi">0</span><span class="p">])</span>
|
||||
<span class="p">})</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">use_full_action_space</span><span class="p">:</span>
|
||||
<span class="n">action_identifiers</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">action_spec</span><span class="p">()[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">functions</span><span class="p">)</span>
|
||||
<span class="n">num_action_identifiers</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">action_identifiers</span><span class="p">)</span>
|
||||
<span class="n">action_arguments</span> <span class="o">=</span> <span class="p">[(</span><span class="n">arg</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> <span class="n">arg</span><span class="o">.</span><span class="n">sizes</span><span class="p">)</span> <span class="k">for</span> <span class="n">arg</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">action_spec</span><span class="p">()[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">types</span><span class="p">]</span>
|
||||
<span class="n">sub_action_spaces</span> <span class="o">=</span> <span class="p">[</span><span class="n">DiscreteActionSpace</span><span class="p">(</span><span class="n">num_action_identifiers</span><span class="p">)]</span>
|
||||
<span class="k">for</span> <span class="n">argument</span> <span class="ow">in</span> <span class="n">action_arguments</span><span class="p">:</span>
|
||||
<span class="k">for</span> <span class="n">dimension</span> <span class="ow">in</span> <span class="n">argument</span><span class="p">[</span><span class="mi">1</span><span class="p">]:</span>
|
||||
<span class="n">sub_action_spaces</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">DiscreteActionSpace</span><span class="p">(</span><span class="n">dimension</span><span class="p">))</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">action_space</span> <span class="o">=</span> <span class="n">CompoundActionSpace</span><span class="p">(</span><span class="n">sub_action_spaces</span><span class="p">)</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">action_space</span> <span class="o">=</span> <span class="n">BoxActionSpace</span><span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">screen_size</span> <span class="o">-</span> <span class="mi">1</span><span class="p">,</span> <span class="p">[</span><span class="s2">"X-Axis, Y-Axis"</span><span class="p">],</span>
|
||||
<span class="n">default_action</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="bp">self</span><span class="o">.</span><span class="n">screen_size</span><span class="o">/</span><span class="mi">2</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">screen_size</span><span class="o">/</span><span class="mi">2</span><span class="p">]))</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">target_success_rate</span> <span class="o">=</span> <span class="n">target_success_rate</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_update_state</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="n">timestep</span> <span class="o">=</span> <span class="mi">0</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">screen</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">last_result</span><span class="p">[</span><span class="n">timestep</span><span class="p">]</span><span class="o">.</span><span class="n">observation</span><span class="o">.</span><span class="n">feature_screen</span>
|
||||
<span class="c1"># extract only the requested segmentation maps from the observation</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">screen</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">take</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">screen</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">feature_screen_maps_to_use</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">minimap</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">last_result</span><span class="p">[</span><span class="n">timestep</span><span class="p">]</span><span class="o">.</span><span class="n">observation</span><span class="o">.</span><span class="n">feature_minimap</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">measurements</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">last_result</span><span class="p">[</span><span class="n">timestep</span><span class="p">]</span><span class="o">.</span><span class="n">observation</span><span class="o">.</span><span class="n">player</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reward</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">last_result</span><span class="p">[</span><span class="n">timestep</span><span class="p">]</span><span class="o">.</span><span class="n">reward</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">done</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">last_result</span><span class="p">[</span><span class="n">timestep</span><span class="p">]</span><span class="o">.</span><span class="n">step_type</span> <span class="o">==</span> <span class="n">environment</span><span class="o">.</span><span class="n">StepType</span><span class="o">.</span><span class="n">LAST</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">state</span> <span class="o">=</span> <span class="p">{</span>
|
||||
<span class="s1">'screen'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">screen</span><span class="p">,</span>
|
||||
<span class="s1">'minimap'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">minimap</span><span class="p">,</span>
|
||||
<span class="s1">'measurements'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">measurements</span>
|
||||
<span class="p">}</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_take_action</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">action</span><span class="p">):</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">use_full_action_space</span><span class="p">:</span>
|
||||
<span class="n">action_identifier</span> <span class="o">=</span> <span class="n">action</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
|
||||
<span class="n">action_arguments</span> <span class="o">=</span> <span class="n">action</span><span class="p">[</span><span class="mi">1</span><span class="p">:]</span>
|
||||
<span class="n">action</span> <span class="o">=</span> <span class="n">actions</span><span class="o">.</span><span class="n">FunctionCall</span><span class="p">(</span><span class="n">action_identifier</span><span class="p">,</span> <span class="n">action_arguments</span><span class="p">)</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="n">coord</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">action</span><span class="p">[</span><span class="mi">0</span><span class="p">:</span><span class="mi">2</span><span class="p">])</span>
|
||||
<span class="n">noop</span> <span class="o">=</span> <span class="kc">False</span>
|
||||
<span class="n">coord</span> <span class="o">=</span> <span class="n">coord</span><span class="o">.</span><span class="n">round</span><span class="p">()</span>
|
||||
<span class="n">coord</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">clip</span><span class="p">(</span><span class="n">coord</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="n">SCREEN_SIZE</span> <span class="o">-</span> <span class="mi">1</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">last_action_idx</span> <span class="o">=</span> <span class="n">coord</span>
|
||||
|
||||
<span class="k">if</span> <span class="n">noop</span><span class="p">:</span>
|
||||
<span class="n">action</span> <span class="o">=</span> <span class="n">actions</span><span class="o">.</span><span class="n">FunctionCall</span><span class="p">(</span><span class="n">_NOOP</span><span class="p">,</span> <span class="p">[])</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="n">action</span> <span class="o">=</span> <span class="n">actions</span><span class="o">.</span><span class="n">FunctionCall</span><span class="p">(</span><span class="n">_MOVE_SCREEN</span><span class="p">,</span> <span class="p">[</span><span class="n">_NOT_QUEUED</span><span class="p">,</span> <span class="n">coord</span><span class="p">])</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">last_result</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">step</span><span class="p">(</span><span class="n">actions</span><span class="o">=</span><span class="p">[</span><span class="n">action</span><span class="p">])</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_restart_environment_episode</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">force_environment_reset</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
|
||||
<span class="c1"># reset the environment</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">last_result</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">reset</span><span class="p">()</span>
|
||||
|
||||
<span class="c1"># select all the units on the screen</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">auto_select_all_army</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">step</span><span class="p">(</span><span class="n">actions</span><span class="o">=</span><span class="p">[</span><span class="n">actions</span><span class="o">.</span><span class="n">FunctionCall</span><span class="p">(</span><span class="n">_SELECT_ARMY</span><span class="p">,</span> <span class="p">[</span><span class="n">_SELECT_ALL</span><span class="p">])])</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">get_rendered_image</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="n">screen</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">squeeze</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">tile</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">expand_dims</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">screen</span><span class="p">,</span> <span class="o">-</span><span class="mi">1</span><span class="p">),</span> <span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">3</span><span class="p">)))</span>
|
||||
<span class="n">screen</span> <span class="o">=</span> <span class="n">screen</span> <span class="o">/</span> <span class="n">np</span><span class="o">.</span><span class="n">max</span><span class="p">(</span><span class="n">screen</span><span class="p">)</span> <span class="o">*</span> <span class="mi">255</span>
|
||||
<span class="k">return</span> <span class="n">screen</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="s1">'uint8'</span><span class="p">)</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">dump_video_of_last_episode</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.logger</span> <span class="k">import</span> <span class="n">experiment_path</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">_run_config</span><span class="o">.</span><span class="n">replay_dir</span> <span class="o">=</span> <span class="n">experiment_path</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">save_replay</span><span class="p">(</span><span class="s1">'replays'</span><span class="p">)</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">dump_video_of_last_episode</span><span class="p">()</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">get_target_success_rate</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">target_success_rate</span></div>
|
||||
</pre></div>
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
<footer>
|
||||
|
||||
|
||||
<hr/>
|
||||
|
||||
<div role="contentinfo">
|
||||
<p>
|
||||
© Copyright 2018, Intel AI Lab
|
||||
|
||||
</p>
|
||||
</div>
|
||||
Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
|
||||
|
||||
</footer>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
|
||||
</section>
|
||||
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<script type="text/javascript" id="documentation_options" data-url_root="../../../" src="../../../_static/documentation_options.js"></script>
|
||||
<script type="text/javascript" src="../../../_static/jquery.js"></script>
|
||||
<script type="text/javascript" src="../../../_static/underscore.js"></script>
|
||||
<script type="text/javascript" src="../../../_static/doctools.js"></script>
|
||||
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></script>
|
||||
|
||||
|
||||
|
||||
|
||||
<script type="text/javascript" src="../../../_static/js/theme.js"></script>
|
||||
|
||||
<script type="text/javascript">
|
||||
jQuery(function () {
|
||||
SphinxRtdTheme.Navigation.enable(true);
|
||||
});
|
||||
</script>
|
||||
|
||||
</body>
|
||||
</html>
|
||||
Reference in New Issue
Block a user