mirror of
https://github.com/gryf/coach.git
synced 2025-12-17 19:20:19 +01:00
* 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
332 lines
15 KiB
HTML
332 lines
15 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>Adding a New 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 rel="next" title="Agents" href="../components/agents/index.html" />
|
||
<link rel="prev" title="Adding a New Agent" href="add_agent.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 class="current">
|
||
<li class="toctree-l1"><a class="reference internal" href="add_agent.html">Adding a New Agent</a></li>
|
||
<li class="toctree-l1 current"><a class="current reference internal" href="#">Adding a New Environment</a><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="#using-the-openai-gym-api">Using the OpenAI Gym API</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="#using-the-coach-api">Using the Coach API</a></li>
|
||
</ul>
|
||
</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>Adding a New Environment</li>
|
||
|
||
|
||
<li class="wy-breadcrumbs-aside">
|
||
|
||
|
||
<a href="../_sources/contributing/add_env.rst.txt" rel="nofollow"> View page source</a>
|
||
|
||
|
||
</li>
|
||
|
||
</ul>
|
||
|
||
|
||
<hr/>
|
||
</div>
|
||
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
|
||
<div itemprop="articleBody">
|
||
|
||
<div class="section" id="adding-a-new-environment">
|
||
<h1>Adding a New Environment<a class="headerlink" href="#adding-a-new-environment" title="Permalink to this headline">¶</a></h1>
|
||
<p>Adding a new environment to Coach is as easy as solving CartPole.</p>
|
||
<p>There are essentially two ways to integrate new environments to Coach:</p>
|
||
<div class="section" id="using-the-openai-gym-api">
|
||
<h2>Using the OpenAI Gym API<a class="headerlink" href="#using-the-openai-gym-api" title="Permalink to this headline">¶</a></h2>
|
||
<p>If your environment is already using the OpenAI Gym API, you are already good to go.
|
||
When selecting the environment parameters in the preset, use <code class="code docutils literal notranslate"><span class="pre">GymEnvironmentParameters()</span></code>,
|
||
and pass the path to your environment source code using the level parameter.
|
||
You can specify additional parameters for your environment using the additional_simulator_parameters parameter.
|
||
Take for example the definition used in the <code class="code docutils literal notranslate"><span class="pre">Pendulum_HAC</span></code> preset:</p>
|
||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">env_params</span> <span class="o">=</span> <span class="n">GymEnvironmentParameters</span><span class="p">()</span>
|
||
<span class="n">env_params</span><span class="o">.</span><span class="n">level</span> <span class="o">=</span> <span class="s2">"rl_coach.environments.mujoco.pendulum_with_goals:PendulumWithGoals"</span>
|
||
<span class="n">env_params</span><span class="o">.</span><span class="n">additional_simulator_parameters</span> <span class="o">=</span> <span class="p">{</span><span class="s2">"time_limit"</span><span class="p">:</span> <span class="mi">1000</span><span class="p">}</span>
|
||
</pre></div>
|
||
</div>
|
||
</div>
|
||
<div class="section" id="using-the-coach-api">
|
||
<h2>Using the Coach API<a class="headerlink" href="#using-the-coach-api" title="Permalink to this headline">¶</a></h2>
|
||
<p>There are a few simple steps to follow, and we will walk through them one by one.
|
||
As an alternative, we highly recommend following the corresponding
|
||
<a class="reference external" href="https://github.com/NervanaSystems/coach/blob/master/tutorials/2.%20Adding%20an%20Environment.ipynb">tutorial</a>
|
||
in the GitHub repo.</p>
|
||
<ol class="arabic">
|
||
<li><p class="first">Create a new class for your environment, and inherit the Environment class.</p>
|
||
</li>
|
||
<li><p class="first">Coach defines a simple API for implementing a new environment, which are defined in environment/environment.py.
|
||
There are several functions to implement, but only some of them are mandatory.</p>
|
||
<p>Here are the important ones:</p>
|
||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></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="bp">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">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="bp">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">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="bp">False</span><span class="p">)</span> <span class="o">-></span> <span class="bp">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">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="bp">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">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>
|
||
</pre></div>
|
||
</div>
|
||
</li>
|
||
<li><p class="first">Create a new parameters class for your environment, which inherits the EnvironmentParameters class.
|
||
In the __init__ of your class, define all the parameters you used in your Environment class.
|
||
Additionally, fill the path property of the class with the path to your Environment class.
|
||
For example, take a look at the EnvironmentParameters class used for Doom:</p>
|
||
<blockquote>
|
||
<div><div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="k">class</span> <span class="nc">DoomEnvironmentParameters</span><span class="p">(</span><span class="n">EnvironmentParameters</span><span class="p">):</span>
|
||
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</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">default_input_filter</span> <span class="o">=</span> <span class="n">DoomInputFilter</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">default_output_filter</span> <span class="o">=</span> <span class="n">DoomOutputFilter</span>
|
||
<span class="bp">self</span><span class="o">.</span><span class="n">cameras</span> <span class="o">=</span> <span class="p">[</span><span class="n">DoomEnvironment</span><span class="o">.</span><span class="n">CameraTypes</span><span class="o">.</span><span class="n">OBSERVATION</span><span class="p">]</span>
|
||
|
||
<span class="nd">@property</span>
|
||
<span class="k">def</span> <span class="nf">path</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="k">return</span> <span class="s1">'rl_coach.environments.doom_environment:DoomEnvironment'</span>
|
||
</pre></div>
|
||
</div>
|
||
</div></blockquote>
|
||
</li>
|
||
<li><p class="first">And that’s it, you’re done. Now just add a new preset with your newly created environment, and start training an agent on top of it.</p>
|
||
</li>
|
||
</ol>
|
||
</div>
|
||
</div>
|
||
|
||
|
||
</div>
|
||
|
||
</div>
|
||
<footer>
|
||
|
||
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
|
||
|
||
<a href="../components/agents/index.html" class="btn btn-neutral float-right" title="Agents" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a>
|
||
|
||
|
||
<a href="add_agent.html" class="btn btn-neutral" title="Adding a New Agent" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left"></span> Previous</a>
|
||
|
||
</div>
|
||
|
||
|
||
<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> |