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
313
docs/contributing/add_agent.html
Normal file
313
docs/contributing/add_agent.html
Normal file
@@ -0,0 +1,313 @@
|
||||
|
||||
|
||||
<!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 Agent — 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="Adding a New Environment" href="add_env.html" />
|
||||
<link rel="prev" title="Network Design" href="../design/network.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 current"><a class="current reference internal" href="#">Adding a New Agent</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="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>Adding a New Agent</li>
|
||||
|
||||
|
||||
<li class="wy-breadcrumbs-aside">
|
||||
|
||||
|
||||
<a href="../_sources/contributing/add_agent.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-agent">
|
||||
<h1>Adding a New Agent<a class="headerlink" href="#adding-a-new-agent" title="Permalink to this headline">¶</a></h1>
|
||||
<p>Coach’s modularity makes adding an agent a simple and clean task.
|
||||
We suggest using the following
|
||||
<a class="reference external" href="https://github.com/NervanaSystems/coach/blob/master/tutorials/1.%20Implementing%20an%20Algorithm.ipynb">Jupyter notebook tutorial</a>
|
||||
to ramp up on this process. In general, it involves the following steps:</p>
|
||||
<ol class="arabic">
|
||||
<li><p class="first">Implement your algorithm in a new file. The agent can inherit base classes such as <strong>ValueOptimizationAgent</strong> or
|
||||
<strong>ActorCriticAgent</strong>, or the more generic <strong>Agent</strong> base class.</p>
|
||||
<div class="admonition note">
|
||||
<p class="first admonition-title">Note</p>
|
||||
<p class="last"><strong>ValueOptimizationAgent</strong>, <strong>PolicyOptimizationAgent</strong> and <strong>Agent</strong> are abstract classes.
|
||||
<code class="code docutils literal notranslate"><span class="pre">learn_from_batch()</span></code> should be overriden with the desired behavior for the algorithm being implemented.
|
||||
If deciding to inherit from <strong>Agent</strong>, also <code class="code docutils literal notranslate"><span class="pre">choose_action()</span></code> should be overriden.</p>
|
||||
</div>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="k">def</span> <span class="nf">learn_from_batch</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">batch</span><span class="p">)</span> <span class="o">-></span> <span class="n">Tuple</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="n">List</span><span class="p">]:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Given a batch of transitions, calculates their target values and updates the network.</span>
|
||||
<span class="sd"> :param batch: A list of transitions</span>
|
||||
<span class="sd"> :return: The total loss of the training, the loss per head and the unclipped gradients</span>
|
||||
<span class="sd"> """</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">choose_action</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">curr_state</span><span class="p">):</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> choose an action to act with in the current episode being played. Different behavior might be exhibited when training</span>
|
||||
<span class="sd"> or testing.</span>
|
||||
|
||||
<span class="sd"> :param curr_state: the current state to act upon.</span>
|
||||
<span class="sd"> :return: chosen action, some action value describing the action (q-value, probability, etc)</span>
|
||||
<span class="sd"> """</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
</li>
|
||||
<li><p class="first">Implement your agent’s specific network head, if needed, at the implementation for the framework of your choice.
|
||||
For example <strong>architectures/neon_components/heads.py</strong>. The head will inherit the generic base class Head.
|
||||
A new output type should be added to configurations.py, and a mapping between the new head and output type should
|
||||
be defined in the get_output_head() function at <strong>architectures/neon_components/general_network.py</strong></p>
|
||||
</li>
|
||||
<li><p class="first">Define a new parameters class that inherits AgentParameters.
|
||||
The parameters class defines all the hyperparameters for the agent, and is initialized with 4 main components:</p>
|
||||
<ul class="simple">
|
||||
<li><strong>algorithm</strong>: A class inheriting AlgorithmParameters which defines any algorithm specific parameters</li>
|
||||
<li><strong>exploration</strong>: A class inheriting ExplorationParameters which defines the exploration policy parameters.
|
||||
There are several common exploration policies built-in which you can use, and are defined under
|
||||
the exploration sub directory. You can also define your own custom exploration policy.</li>
|
||||
<li><strong>memory</strong>: A class inheriting MemoryParameters which defined the memory parameters.
|
||||
There are several common memory types built-in which you can use, and are defined under the memories
|
||||
sub directory. You can also define your own custom memory.</li>
|
||||
<li><strong>networks</strong>: A dictionary defining all the networks that will be used by the agent. The keys of the dictionary
|
||||
define the network name and will be used to access each network through the agent class.
|
||||
The dictionary values are a class inheriting NetworkParameters, which define the network structure
|
||||
and parameters.</li>
|
||||
</ul>
|
||||
<p>Additionally, set the path property to return the path to your agent class in the following format:</p>
|
||||
<p><code class="code docutils literal notranslate"><span class="pre"><path</span> <span class="pre">to</span> <span class="pre">python</span> <span class="pre">module>:<name</span> <span class="pre">of</span> <span class="pre">agent</span> <span class="pre">class></span></code></p>
|
||||
<p>For example,</p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="k">class</span> <span class="nc">RainbowAgentParameters</span><span class="p">(</span><span class="n">AgentParameters</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="n">algorithm</span><span class="o">=</span><span class="n">RainbowAlgorithmParameters</span><span class="p">(),</span>
|
||||
<span class="n">exploration</span><span class="o">=</span><span class="n">RainbowExplorationParameters</span><span class="p">(),</span>
|
||||
<span class="n">memory</span><span class="o">=</span><span class="n">RainbowMemoryParameters</span><span class="p">(),</span>
|
||||
<span class="n">networks</span><span class="o">=</span><span class="p">{</span><span class="s2">"main"</span><span class="p">:</span> <span class="n">RainbowNetworkParameters</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">'rainbow.rainbow_agent:RainbowAgent'</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
</li>
|
||||
<li><p class="first">(Optional) Define a preset using the new agent type with a given environment, and the hyper-parameters that should
|
||||
be used for training on that environment.</p>
|
||||
</li>
|
||||
</ol>
|
||||
</div>
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
<footer>
|
||||
|
||||
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
|
||||
|
||||
<a href="add_env.html" class="btn btn-neutral float-right" title="Adding a New Environment" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a>
|
||||
|
||||
|
||||
<a href="../design/network.html" class="btn btn-neutral" title="Network Design" 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>
|
||||
@@ -1,340 +0,0 @@
|
||||
<!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 http-equiv="X-UA-Compatible" content="IE=edge">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
|
||||
|
||||
<link rel="shortcut icon" href="../../img/favicon.ico">
|
||||
<title>Adding a New Agent - Reinforcement Learning Coach</title>
|
||||
<link href='https://fonts.googleapis.com/css?family=Lato:400,700|Roboto+Slab:400,700|Inconsolata:400,700' rel='stylesheet' type='text/css'>
|
||||
|
||||
<link rel="stylesheet" href="../../css/theme.css" type="text/css" />
|
||||
<link rel="stylesheet" href="../../css/theme_extra.css" type="text/css" />
|
||||
<link rel="stylesheet" href="../../css/highlight.css">
|
||||
<link href="../../extra.css" rel="stylesheet">
|
||||
|
||||
<script>
|
||||
// Current page data
|
||||
var mkdocs_page_name = "Adding a New Agent";
|
||||
var mkdocs_page_input_path = "contributing/add_agent.md";
|
||||
var mkdocs_page_url = "/contributing/add_agent/";
|
||||
</script>
|
||||
|
||||
<script src="../../js/jquery-2.1.1.min.js"></script>
|
||||
<script src="../../js/modernizr-2.8.3.min.js"></script>
|
||||
<script type="text/javascript" src="../../js/highlight.pack.js"></script>
|
||||
|
||||
</head>
|
||||
|
||||
<body class="wy-body-for-nav" role="document">
|
||||
|
||||
<div class="wy-grid-for-nav">
|
||||
|
||||
|
||||
<nav data-toggle="wy-nav-shift" class="wy-nav-side stickynav">
|
||||
<div class="wy-side-nav-search">
|
||||
<a href="../.." class="icon icon-home"> Reinforcement Learning Coach</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" />
|
||||
</form>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
|
||||
<ul class="current">
|
||||
|
||||
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../..">Home</a>
|
||||
</li>
|
||||
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../usage/">Usage</a>
|
||||
</li>
|
||||
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Design</span>
|
||||
<ul class="subnav">
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../design/features/">Features</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../design/control_flow/">Control Flow</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../design/network/">Network</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../design/filters/">Filters</a>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Algorithms</span>
|
||||
<ul class="subnav">
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/value_optimization/dqn/">DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/value_optimization/double_dqn/">Double DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/value_optimization/dueling_dqn/">Dueling DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/value_optimization/categorical_dqn/">Categorical DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/value_optimization/mmc/">Mixed Monte Carlo</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/value_optimization/pal/">Persistent Advantage Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/value_optimization/nec/">Neural Episodic Control</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/value_optimization/bs_dqn/">Bootstrapped DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/value_optimization/n_step/">N-Step Q Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/value_optimization/naf/">Normalized Advantage Functions</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/policy_optimization/pg/">Policy Gradient</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/policy_optimization/ac/">Actor-Critic</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/policy_optimization/ddpg/">Deep Determinstic Policy Gradients</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/policy_optimization/ppo/">Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/policy_optimization/cppo/">Clipped Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/other/dfp/">Direct Future Prediction</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/imitation/bc/">Behavioral Cloning</a>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../dashboard/">Coach Dashboard</a>
|
||||
</li>
|
||||
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Contributing</span>
|
||||
<ul class="subnav">
|
||||
<li class=" current">
|
||||
|
||||
<a class="current" href="./">Adding a New Agent</a>
|
||||
<ul class="subnav">
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../add_env/">Adding a New Environment</a>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
</nav>
|
||||
|
||||
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
|
||||
|
||||
|
||||
<nav class="wy-nav-top" role="navigation" aria-label="top navigation">
|
||||
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
|
||||
<a href="../..">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="../..">Docs</a> »</li>
|
||||
|
||||
|
||||
|
||||
<li>Contributing »</li>
|
||||
|
||||
|
||||
|
||||
<li>Adding a New Agent</li>
|
||||
<li class="wy-breadcrumbs-aside">
|
||||
|
||||
</li>
|
||||
</ul>
|
||||
<hr/>
|
||||
</div>
|
||||
<div role="main">
|
||||
<div class="section">
|
||||
|
||||
<!-- language-all: python -->
|
||||
|
||||
<p>Coach's modularity makes adding an agent a simple and clean task, that involves the following steps:</p>
|
||||
<ol>
|
||||
<li>
|
||||
<p>Implement your algorithm in a new file. The agent can inherit base classes such as <strong>ValueOptimizationAgent</strong> or
|
||||
<strong>ActorCriticAgent</strong>, or the more generic <strong>Agent</strong> base class.</p>
|
||||
<ul>
|
||||
<li><strong>ValueOptimizationAgent</strong>, <strong>PolicyOptimizationAgent</strong> and <strong>Agent</strong> are abstract classes.
|
||||
learn_from_batch() should be overriden with the desired behavior for the algorithm being implemented.
|
||||
If deciding to inherit from <strong>Agent</strong>, also choose_action() should be overriden.<pre><code>def learn_from_batch(self, batch) -> Tuple[float, List, List]:
|
||||
"""
|
||||
Given a batch of transitions, calculates their target values and updates the network.
|
||||
:param batch: A list of transitions
|
||||
:return: The total loss of the training, the loss per head and the unclipped gradients
|
||||
"""
|
||||
|
||||
def choose_action(self, curr_state):
|
||||
"""
|
||||
choose an action to act with in the current episode being played. Different behavior might be exhibited when training
|
||||
or testing.
|
||||
|
||||
:param curr_state: the current state to act upon.
|
||||
:return: chosen action, some action value describing the action (q-value, probability, etc)
|
||||
"""
|
||||
</code></pre>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
<li>
|
||||
<p>Implement your agent's specific network head, if needed, at the implementation for the framework of your choice.
|
||||
For example <strong>architectures/neon_components/heads.py</strong>. The head will inherit the generic base class Head.
|
||||
A new output type should be added to configurations.py, and a mapping between the new head and output type should
|
||||
be defined in the get_output_head() function at <strong>architectures/neon_components/general_network.py</strong></p>
|
||||
</li>
|
||||
<li>
|
||||
<p>Define a new parameters class that inherits AgentParameters.
|
||||
The parameters class defines all the hyperparameters for the agent, and is initialized with 4 main components:</p>
|
||||
<ul>
|
||||
<li><strong>algorithm</strong>: A class inheriting AlgorithmParameters which defines any algorithm specific parameters</li>
|
||||
<li><strong>exploration</strong>: A class inheriting ExplorationParameters which defines the exploration policy parameters.
|
||||
There are several common exploration policies built-in which you can use, and are defined under
|
||||
the exploration sub directory. You can also define your own custom exploration policy.</li>
|
||||
<li><strong>memory</strong>: A class inheriting MemoryParameters which defined the memory parameters.
|
||||
There are several common memory types built-in which you can use, and are defined under the memories
|
||||
sub directory. You can also define your own custom memory.</li>
|
||||
<li><strong>networks</strong>: A dictionary defining all the networks that will be used by the agent. The keys of the dictionary
|
||||
define the network name and will be used to access each network through the agent class.
|
||||
The dictionary values are a class inheriting NetworkParameters, which define the network structure
|
||||
and parameters.</li>
|
||||
</ul>
|
||||
<p>Additionally, set the path property to return the path to your agent class in the following format:</p>
|
||||
<pre><code> <path to python module>:<name of agent class>
|
||||
</code></pre>
|
||||
<p>For example,</p>
|
||||
<pre><code> class RainbowAgentParameters(AgentParameters):
|
||||
def __init__(self):
|
||||
super().__init__(algorithm=RainbowAlgorithmParameters(),
|
||||
exploration=RainbowExplorationParameters(),
|
||||
memory=RainbowMemoryParameters(),
|
||||
networks={"main": RainbowNetworkParameters()})
|
||||
|
||||
@property
|
||||
def path(self):
|
||||
return 'rainbow.rainbow_agent:RainbowAgent'
|
||||
</code></pre>
|
||||
</li>
|
||||
<li>
|
||||
<p>(Optional) Define a preset using the new agent type with a given environment, and the hyper-parameters that should
|
||||
be used for training on that environment.</p>
|
||||
</li>
|
||||
</ol>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<footer>
|
||||
|
||||
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
|
||||
|
||||
<a href="../add_env/" class="btn btn-neutral float-right" title="Adding a New Environment">Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
|
||||
|
||||
<a href="../../dashboard/" class="btn btn-neutral" title="Coach Dashboard"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
|
||||
</div>
|
||||
|
||||
|
||||
<hr/>
|
||||
|
||||
<div role="contentinfo">
|
||||
<!-- Copyright etc -->
|
||||
|
||||
</div>
|
||||
|
||||
Built with <a href="http://www.mkdocs.org">MkDocs</a> using a <a href="https://github.com/snide/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
|
||||
</footer>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
|
||||
</section>
|
||||
|
||||
</div>
|
||||
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<span class="rst-current-version" data-toggle="rst-current-version">
|
||||
|
||||
|
||||
<span><a href="../../dashboard/" style="color: #fcfcfc;">« Previous</a></span>
|
||||
|
||||
|
||||
<span style="margin-left: 15px"><a href="../add_env/" style="color: #fcfcfc">Next »</a></span>
|
||||
|
||||
</span>
|
||||
</div>
|
||||
<script>var base_url = '../..';</script>
|
||||
<script src="../../js/theme.js"></script>
|
||||
<script src="https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS_HTML"></script>
|
||||
<script src="../../search/require.js"></script>
|
||||
<script src="../../search/search.js"></script>
|
||||
|
||||
</body>
|
||||
</html>
|
||||
332
docs/contributing/add_env.html
Normal file
332
docs/contributing/add_env.html
Normal file
@@ -0,0 +1,332 @@
|
||||
|
||||
|
||||
<!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>
|
||||
@@ -1,348 +0,0 @@
|
||||
<!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 http-equiv="X-UA-Compatible" content="IE=edge">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
|
||||
|
||||
<link rel="shortcut icon" href="../../img/favicon.ico">
|
||||
<title>Adding a New Environment - Reinforcement Learning Coach</title>
|
||||
<link href='https://fonts.googleapis.com/css?family=Lato:400,700|Roboto+Slab:400,700|Inconsolata:400,700' rel='stylesheet' type='text/css'>
|
||||
|
||||
<link rel="stylesheet" href="../../css/theme.css" type="text/css" />
|
||||
<link rel="stylesheet" href="../../css/theme_extra.css" type="text/css" />
|
||||
<link rel="stylesheet" href="../../css/highlight.css">
|
||||
<link href="../../extra.css" rel="stylesheet">
|
||||
|
||||
<script>
|
||||
// Current page data
|
||||
var mkdocs_page_name = "Adding a New Environment";
|
||||
var mkdocs_page_input_path = "contributing/add_env.md";
|
||||
var mkdocs_page_url = "/contributing/add_env/";
|
||||
</script>
|
||||
|
||||
<script src="../../js/jquery-2.1.1.min.js"></script>
|
||||
<script src="../../js/modernizr-2.8.3.min.js"></script>
|
||||
<script type="text/javascript" src="../../js/highlight.pack.js"></script>
|
||||
|
||||
</head>
|
||||
|
||||
<body class="wy-body-for-nav" role="document">
|
||||
|
||||
<div class="wy-grid-for-nav">
|
||||
|
||||
|
||||
<nav data-toggle="wy-nav-shift" class="wy-nav-side stickynav">
|
||||
<div class="wy-side-nav-search">
|
||||
<a href="../.." class="icon icon-home"> Reinforcement Learning Coach</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" />
|
||||
</form>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
|
||||
<ul class="current">
|
||||
|
||||
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../..">Home</a>
|
||||
</li>
|
||||
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../usage/">Usage</a>
|
||||
</li>
|
||||
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Design</span>
|
||||
<ul class="subnav">
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../design/features/">Features</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../design/control_flow/">Control Flow</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../design/network/">Network</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../design/filters/">Filters</a>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Algorithms</span>
|
||||
<ul class="subnav">
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/value_optimization/dqn/">DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/value_optimization/double_dqn/">Double DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/value_optimization/dueling_dqn/">Dueling DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/value_optimization/categorical_dqn/">Categorical DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/value_optimization/mmc/">Mixed Monte Carlo</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/value_optimization/pal/">Persistent Advantage Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/value_optimization/nec/">Neural Episodic Control</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/value_optimization/bs_dqn/">Bootstrapped DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/value_optimization/n_step/">N-Step Q Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/value_optimization/naf/">Normalized Advantage Functions</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/policy_optimization/pg/">Policy Gradient</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/policy_optimization/ac/">Actor-Critic</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/policy_optimization/ddpg/">Deep Determinstic Policy Gradients</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/policy_optimization/ppo/">Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/policy_optimization/cppo/">Clipped Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/other/dfp/">Direct Future Prediction</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../algorithms/imitation/bc/">Behavioral Cloning</a>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../dashboard/">Coach Dashboard</a>
|
||||
</li>
|
||||
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Contributing</span>
|
||||
<ul class="subnav">
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../add_agent/">Adding a New Agent</a>
|
||||
</li>
|
||||
<li class=" current">
|
||||
|
||||
<a class="current" href="./">Adding a New Environment</a>
|
||||
<ul class="subnav">
|
||||
|
||||
<li class="toctree-l3"><a href="#using-the-openai-gym-api">Using the OpenAI Gym API</a></li>
|
||||
|
||||
|
||||
<li class="toctree-l3"><a href="#using-the-coach-api">Using the Coach API</a></li>
|
||||
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
</nav>
|
||||
|
||||
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
|
||||
|
||||
|
||||
<nav class="wy-nav-top" role="navigation" aria-label="top navigation">
|
||||
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
|
||||
<a href="../..">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="../..">Docs</a> »</li>
|
||||
|
||||
|
||||
|
||||
<li>Contributing »</li>
|
||||
|
||||
|
||||
|
||||
<li>Adding a New Environment</li>
|
||||
<li class="wy-breadcrumbs-aside">
|
||||
|
||||
</li>
|
||||
</ul>
|
||||
<hr/>
|
||||
</div>
|
||||
<div role="main">
|
||||
<div class="section">
|
||||
|
||||
<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>
|
||||
<h2 id="using-the-openai-gym-api">Using the OpenAI Gym API</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 GymEnvironmentParameters(),
|
||||
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 Pendulum_HAC preset:</p>
|
||||
<pre><code> env_params = GymEnvironmentParameters()
|
||||
env_params.level = "rl_coach.environments.mujoco.pendulum_with_goals:PendulumWithGoals"
|
||||
env_params.additional_simulator_parameters = {"time_limit": 1000}
|
||||
</code></pre>
|
||||
<h2 id="using-the-coach-api">Using the Coach API</h2>
|
||||
<p>There are a few simple steps to follow, and we will walk through them one by one.</p>
|
||||
<ol>
|
||||
<li>
|
||||
<p>Create a new class for your environment, and inherit the Environment class.</p>
|
||||
</li>
|
||||
<li>
|
||||
<p>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>
|
||||
<pre><code> def _take_action(self, action_idx: ActionType) -> None:
|
||||
"""
|
||||
An environment dependent function that sends an action to the simulator.
|
||||
:param action_idx: the action to perform on the environment
|
||||
:return: None
|
||||
"""
|
||||
|
||||
def _update_state(self) -> None:
|
||||
"""
|
||||
Updates the state from the environment.
|
||||
Should update self.observation, self.reward, self.done, self.measurements and self.info
|
||||
:return: None
|
||||
"""
|
||||
|
||||
def _restart_environment_episode(self, force_environment_reset=False) -> None:
|
||||
"""
|
||||
Restarts the simulator episode
|
||||
:param force_environment_reset: Force the environment to reset even if the episode is not done yet.
|
||||
:return: None
|
||||
"""
|
||||
|
||||
def _render(self) -> None:
|
||||
"""
|
||||
Renders the environment using the native simulator renderer
|
||||
:return: None
|
||||
"""
|
||||
|
||||
def get_rendered_image(self) -> np.ndarray:
|
||||
"""
|
||||
Return a numpy array containing the image that will be rendered to the screen.
|
||||
This can be different from the observation. For example, mujoco's observation is a measurements vector.
|
||||
:return: numpy array containing the image that will be rendered to the screen
|
||||
"""
|
||||
</code></pre>
|
||||
</li>
|
||||
<li>
|
||||
<p>Create a new parameters class for your environment, which inherits the EnvironmentParameters class.
|
||||
In the <strong>init</strong> 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>
|
||||
<pre><code> class DoomEnvironmentParameters(EnvironmentParameters):
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
self.default_input_filter = DoomInputFilter
|
||||
self.default_output_filter = DoomOutputFilter
|
||||
self.cameras = [DoomEnvironment.CameraTypes.OBSERVATION]
|
||||
|
||||
@property
|
||||
def path(self):
|
||||
return 'rl_coach.environments.doom_environment:DoomEnvironment'
|
||||
</code></pre>
|
||||
</li>
|
||||
<li>
|
||||
<p>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>
|
||||
<footer>
|
||||
|
||||
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
|
||||
|
||||
|
||||
<a href="../add_agent/" class="btn btn-neutral" title="Adding a New Agent"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
|
||||
</div>
|
||||
|
||||
|
||||
<hr/>
|
||||
|
||||
<div role="contentinfo">
|
||||
<!-- Copyright etc -->
|
||||
|
||||
</div>
|
||||
|
||||
Built with <a href="http://www.mkdocs.org">MkDocs</a> using a <a href="https://github.com/snide/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
|
||||
</footer>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
|
||||
</section>
|
||||
|
||||
</div>
|
||||
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<span class="rst-current-version" data-toggle="rst-current-version">
|
||||
|
||||
|
||||
<span><a href="../add_agent/" style="color: #fcfcfc;">« Previous</a></span>
|
||||
|
||||
|
||||
</span>
|
||||
</div>
|
||||
<script>var base_url = '../..';</script>
|
||||
<script src="../../js/theme.js"></script>
|
||||
<script src="https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS_HTML"></script>
|
||||
<script src="../../search/require.js"></script>
|
||||
<script src="../../search/search.js"></script>
|
||||
|
||||
</body>
|
||||
</html>
|
||||
Reference in New Issue
Block a user