mirror of
https://github.com/gryf/coach.git
synced 2025-12-17 19:20:19 +01:00
379 lines
22 KiB
HTML
379 lines
22 KiB
HTML
|
|
|
|
<!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.agents.agent_interface — Reinforcement Learning Coach 0.12.0 documentation</title>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<script type="text/javascript" src="../../../_static/js/modernizr.min.js"></script>
|
|
|
|
|
|
<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 type="text/javascript" src="../../../_static/language_data.js"></script>
|
|
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
|
|
|
|
<script type="text/javascript" src="../../../_static/js/theme.js"></script>
|
|
|
|
|
|
|
|
|
|
<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">
|
|
|
|
</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="../../../dist_usage.html">Usage - Distributed Coach</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>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../design/horizontal_scaling.html">Distributed Coach - Horizontal Scale-Out</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/data_stores/index.html">Data Stores</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/memory_backends/index.html">Memory Backends</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../components/orchestrators/index.html">Orchestrators</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.agents.agent_interface</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.agents.agent_interface</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">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">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.core_types</span> <span class="k">import</span> <span class="n">EnvResponse</span><span class="p">,</span> <span class="n">ActionInfo</span><span class="p">,</span> <span class="n">RunPhase</span><span class="p">,</span> <span class="n">PredictionType</span><span class="p">,</span> <span class="n">ActionType</span><span class="p">,</span> <span class="n">Transition</span>
|
|
<span class="kn">from</span> <span class="nn">rl_coach.saver</span> <span class="k">import</span> <span class="n">SaverCollection</span>
|
|
|
|
|
|
<span class="k">class</span> <span class="nc">AgentInterface</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="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="bp">self</span><span class="o">.</span><span class="n">_parent</span> <span class="o">=</span> <span class="kc">None</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">spaces</span> <span class="o">=</span> <span class="kc">None</span>
|
|
|
|
<span class="nd">@property</span>
|
|
<span class="k">def</span> <span class="nf">parent</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="sd">"""</span>
|
|
<span class="sd"> Get the parent class of the agent</span>
|
|
<span class="sd"> :return: the current phase</span>
|
|
<span class="sd"> """</span>
|
|
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_parent</span>
|
|
|
|
<span class="nd">@parent</span><span class="o">.</span><span class="n">setter</span>
|
|
<span class="k">def</span> <span class="nf">parent</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="sd">"""</span>
|
|
<span class="sd"> Change the parent class of the agent</span>
|
|
<span class="sd"> :param val: the new parent</span>
|
|
<span class="sd"> :return: None</span>
|
|
<span class="sd"> """</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">_parent</span> <span class="o">=</span> <span class="n">val</span>
|
|
|
|
<span class="nd">@property</span>
|
|
<span class="k">def</span> <span class="nf">phase</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">RunPhase</span><span class="p">:</span>
|
|
<span class="sd">"""</span>
|
|
<span class="sd"> Get the phase of the agent</span>
|
|
<span class="sd"> :return: the current phase</span>
|
|
<span class="sd"> """</span>
|
|
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_phase</span>
|
|
|
|
<span class="nd">@phase</span><span class="o">.</span><span class="n">setter</span>
|
|
<span class="k">def</span> <span class="nf">phase</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">RunPhase</span><span class="p">):</span>
|
|
<span class="sd">"""</span>
|
|
<span class="sd"> Change the phase of the agent</span>
|
|
<span class="sd"> :param val: the new phase</span>
|
|
<span class="sd"> :return: None</span>
|
|
<span class="sd"> """</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">_phase</span> <span class="o">=</span> <span class="n">val</span>
|
|
|
|
<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="o">-></span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="sd">"""</span>
|
|
<span class="sd"> Reset the episode parameters for the agent</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">train</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="nb">float</span><span class="p">,</span> <span class="n">List</span><span class="p">]:</span>
|
|
<span class="sd">"""</span>
|
|
<span class="sd"> Train the agents network</span>
|
|
<span class="sd"> :return: The loss of the training</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">act</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">ActionInfo</span><span class="p">:</span>
|
|
<span class="sd">"""</span>
|
|
<span class="sd"> Get a decision of the next action to take.</span>
|
|
<span class="sd"> The action is dependent on the current state which the agent holds from resetting the environment or from</span>
|
|
<span class="sd"> the observe function.</span>
|
|
<span class="sd"> :return: A tuple containing the actual action and additional info on the action</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">observe</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">env_response</span><span class="p">:</span> <span class="n">EnvResponse</span><span class="p">)</span> <span class="o">-></span> <span class="nb">bool</span><span class="p">:</span>
|
|
<span class="sd">"""</span>
|
|
<span class="sd"> Gets a response from the environment.</span>
|
|
<span class="sd"> Processes this information for later use. For example, create a transition and store it in memory.</span>
|
|
<span class="sd"> The action info (a class containing any info the agent wants to store regarding its action decision process) is</span>
|
|
<span class="sd"> stored by the agent itself when deciding on the action.</span>
|
|
<span class="sd"> :param env_response: a EnvResponse containing the response from the environment</span>
|
|
<span class="sd"> :return: a done signal which is based on the agent knowledge. This can be different from the done signal from</span>
|
|
<span class="sd"> the environment. For example, an agent can decide to finish the episode each time it gets some</span>
|
|
<span class="sd"> intrinsic reward</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">save_checkpoint</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">checkpoint_prefix</span><span class="p">:</span> <span class="nb">str</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"> Save the model of the agent to the disk. This can contain the network parameters, the memory of the agent, etc.</span>
|
|
<span class="sd"> :param checkpoint_prefix: The prefix of the checkpoint file to save</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">get_predictions</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">states</span><span class="p">:</span> <span class="n">Dict</span><span class="p">,</span> <span class="n">prediction_type</span><span class="p">:</span> <span class="n">PredictionType</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"> Get a prediction from the agent with regard to the requested prediction_type. If the agent cannot predict this</span>
|
|
<span class="sd"> type of prediction_type, or if there is more than possible way to do so, raise a ValueException.</span>
|
|
<span class="sd"> :param states:</span>
|
|
<span class="sd"> :param prediction_type:</span>
|
|
<span class="sd"> :return: the agent's prediction</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">set_incoming_directive</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="kc">None</span><span class="p">:</span>
|
|
<span class="sd">"""</span>
|
|
<span class="sd"> Pass a higher level command (directive) to the agent.</span>
|
|
<span class="sd"> For example, a higher level agent can set the goal of the agent.</span>
|
|
<span class="sd"> :param action: the directive to pass to the agent</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">collect_savers</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">parent_path_suffix</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="n">SaverCollection</span><span class="p">:</span>
|
|
<span class="sd">"""</span>
|
|
<span class="sd"> Collect all of agent savers</span>
|
|
<span class="sd"> :param parent_path_suffix: path suffix of the parent of the agent</span>
|
|
<span class="sd"> (could be name of level manager or composite agent)</span>
|
|
<span class="sd"> :return: collection of all agent savers</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">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"> Make any changes needed when each episode is ended.</span>
|
|
<span class="sd"> This includes incrementing counters, updating full episode dependent values, updating logs, etc.</span>
|
|
<span class="sd"> This function is called right after each episode is ended.</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">run_off_policy_evaluation</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"> Run off-policy evaluation estimators to evaluate the trained policy performance against a dataset.</span>
|
|
<span class="sd"> Should only be implemented for off-policy RL algorithms.</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>
|
|
</pre></div>
|
|
|
|
</div>
|
|
|
|
</div>
|
|
<footer>
|
|
|
|
|
|
<hr/>
|
|
|
|
<div role="contentinfo">
|
|
<p>
|
|
© Copyright 2018-2019, 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">
|
|
jQuery(function () {
|
|
SphinxRtdTheme.Navigation.enable(true);
|
|
});
|
|
</script>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
</body>
|
|
</html> |