mirror of
https://github.com/gryf/coach.git
synced 2025-12-17 19:20:19 +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
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>
|
||||
Reference in New Issue
Block a user