mirror of
https://github.com/facebookresearch/ReAgent.git
synced 2026-06-16 12:44:41 +00:00
228 lines
14 KiB
HTML
228 lines
14 KiB
HTML
<!DOCTYPE html>
|
||
<html class="writer-html5" lang="en" >
|
||
<head>
|
||
<meta charset="utf-8" /><meta name="generator" content="Docutils 0.17.1: http://docutils.sourceforge.net/" />
|
||
|
||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||
<title>reagent.gym.envs.functionality package — ReAgent 1.0 documentation</title>
|
||
<link rel="stylesheet" href="../_static/pygments.css" type="text/css" />
|
||
<link rel="stylesheet" href="../_static/css/theme.css" type="text/css" />
|
||
<!--[if lt IE 9]>
|
||
<script src="../_static/js/html5shiv.min.js"></script>
|
||
<![endif]-->
|
||
|
||
<script data-url_root="../" id="documentation_options" src="../_static/documentation_options.js"></script>
|
||
<script src="../_static/jquery.js"></script>
|
||
<script src="../_static/underscore.js"></script>
|
||
<script src="../_static/doctools.js"></script>
|
||
<script src="../_static/js/theme.js"></script>
|
||
<link rel="index" title="Index" href="../genindex.html" />
|
||
<link rel="search" title="Search" href="../search.html" />
|
||
<link rel="next" title="reagent.gym.envs.pomdp package" href="reagent.gym.envs.pomdp.html" />
|
||
<link rel="prev" title="reagent.gym.envs.dynamics package" href="reagent.gym.envs.dynamics.html" />
|
||
</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"> ReAgent
|
||
</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="Navigation menu">
|
||
<p class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
|
||
<ul>
|
||
<li class="toctree-l1"><a class="reference internal" href="../installation.html">Installation</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../usage.html">Usage</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../rasp_tutorial.html">RASP (Not Actively Maintained)</a></li>
|
||
</ul>
|
||
<p class="caption" role="heading"><span class="caption-text">Advanced Topics</span></p>
|
||
<ul>
|
||
<li class="toctree-l1"><a class="reference internal" href="../continuous_integration.html">Continuous Integration</a></li>
|
||
</ul>
|
||
<p class="caption" role="heading"><span class="caption-text">Package Reference</span></p>
|
||
<ul class="current">
|
||
<li class="toctree-l1"><a class="reference internal" href="reagent.core.html">Core</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="reagent.data.html">Data</a></li>
|
||
<li class="toctree-l1 current"><a class="reference internal" href="reagent.gym.html">Gym</a><ul class="current">
|
||
<li class="toctree-l2 current"><a class="reference internal" href="reagent.gym.html#subpackages">Subpackages</a><ul class="current">
|
||
<li class="toctree-l3"><a class="reference internal" href="reagent.gym.agents.html">reagent.gym.agents package</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="reagent.gym.datasets.html">reagent.gym.datasets package</a></li>
|
||
<li class="toctree-l3 current"><a class="reference internal" href="reagent.gym.envs.html">reagent.gym.envs package</a><ul class="current">
|
||
<li class="toctree-l4 current"><a class="reference internal" href="reagent.gym.envs.html#subpackages">Subpackages</a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="reagent.gym.envs.html#submodules">Submodules</a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="reagent.gym.envs.html#module-reagent.gym.envs.changing_arms">reagent.gym.envs.changing_arms module</a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="reagent.gym.envs.html#module-reagent.gym.envs.env_wrapper">reagent.gym.envs.env_wrapper module</a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="reagent.gym.envs.html#module-reagent.gym.envs.gym">reagent.gym.envs.gym module</a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="reagent.gym.envs.html#module-reagent.gym.envs.oracle_pvm">reagent.gym.envs.oracle_pvm module</a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="reagent.gym.envs.html#module-reagent.gym.envs.recsim">reagent.gym.envs.recsim module</a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="reagent.gym.envs.html#module-reagent.gym.envs.toy_vm">reagent.gym.envs.toy_vm module</a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="reagent.gym.envs.html#module-reagent.gym.envs.utils">reagent.gym.envs.utils module</a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="reagent.gym.envs.html#module-reagent.gym.envs">Module contents</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="reagent.gym.policies.html">reagent.gym.policies package</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="reagent.gym.preprocessors.html">reagent.gym.preprocessors package</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="reagent.gym.runners.html">reagent.gym.runners package</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="reagent.gym.tests.html">reagent.gym.tests package</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l2"><a class="reference internal" href="reagent.gym.html#submodules">Submodules</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="reagent.gym.html#module-reagent.gym.normalizers">reagent.gym.normalizers module</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="reagent.gym.html#module-reagent.gym.types">reagent.gym.types module</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="reagent.gym.html#module-reagent.gym.utils">reagent.gym.utils module</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="reagent.gym.html#module-reagent.gym">Module contents</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l1"><a class="reference internal" href="reagent.evaluation.html">Evaluation</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="reagent.lite.html">Lite</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="reagent.mab.html">MAB</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="reagent.model_managers.html">Model Managers</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="reagent.model_utils.html">Model Utils</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="reagent.net_builder.html">Net Builders</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="reagent.optimizer.html">Optimizers</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="reagent.models.html">Models</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="reagent.prediction.html">Prediction</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="reagent.preprocessing.html">Preprocessing</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="reagent.training.html">Training</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="reagent.workflow.html">Workflow</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="modules.html">All Modules</a></li>
|
||
</ul>
|
||
<p class="caption" role="heading"><span class="caption-text">Others</span></p>
|
||
<ul>
|
||
<li class="toctree-l1"><a class="reference external" href="https://github.com/facebookresearch/ReAgent">Github</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../license.html">License</a></li>
|
||
</ul>
|
||
|
||
</div>
|
||
</div>
|
||
</nav>
|
||
|
||
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"><nav class="wy-nav-top" aria-label="Mobile navigation menu" >
|
||
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
|
||
<a href="../index.html">ReAgent</a>
|
||
</nav>
|
||
|
||
<div class="wy-nav-content">
|
||
<div class="rst-content">
|
||
<div role="navigation" aria-label="Page navigation">
|
||
<ul class="wy-breadcrumbs">
|
||
<li><a href="../index.html" class="icon icon-home"></a> »</li>
|
||
<li><a href="reagent.gym.html">reagent.gym package</a> »</li>
|
||
<li><a href="reagent.gym.envs.html">reagent.gym.envs package</a> »</li>
|
||
<li>reagent.gym.envs.functionality package</li>
|
||
<li class="wy-breadcrumbs-aside">
|
||
<a href="../_sources/api/reagent.gym.envs.functionality.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">
|
||
|
||
<section id="reagent-gym-envs-functionality-package">
|
||
<h1>reagent.gym.envs.functionality package<a class="headerlink" href="#reagent-gym-envs-functionality-package" title="Permalink to this headline"></a></h1>
|
||
<section id="submodules">
|
||
<h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this headline"></a></h2>
|
||
</section>
|
||
<section id="module-reagent.gym.envs.functionality.possible_actions_mask_tester">
|
||
<span id="reagent-gym-envs-functionality-possible-actions-mask-tester-module"></span><h2>reagent.gym.envs.functionality.possible_actions_mask_tester module<a class="headerlink" href="#module-reagent.gym.envs.functionality.possible_actions_mask_tester" title="Permalink to this headline"></a></h2>
|
||
<p>Simple environment to test possible_actions_mask.
|
||
State simply tells you which iteration it is, but doesn’t tell anything about
|
||
which action to take, so only source of info is possible_actions_mask.
|
||
The Q-value of each action to converge to the (discounted) value of the MDP.</p>
|
||
<p>The value of the MDP should be 10 * max_steps = 200</p>
|
||
<dl class="py class">
|
||
<dt class="sig sig-object py" id="reagent.gym.envs.functionality.possible_actions_mask_tester.PossibleActionsMaskTester">
|
||
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.gym.envs.functionality.possible_actions_mask_tester.</span></span><span class="sig-name descname"><span class="pre">PossibleActionsMaskTester</span></span><a class="headerlink" href="#reagent.gym.envs.functionality.possible_actions_mask_tester.PossibleActionsMaskTester" title="Permalink to this definition"></a></dt>
|
||
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">gym.core.Env</span></code></p>
|
||
<dl class="py method">
|
||
<dt class="sig sig-object py" id="reagent.gym.envs.functionality.possible_actions_mask_tester.PossibleActionsMaskTester.reset">
|
||
<span class="sig-name descname"><span class="pre">reset</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#reagent.gym.envs.functionality.possible_actions_mask_tester.PossibleActionsMaskTester.reset" title="Permalink to this definition"></a></dt>
|
||
<dd><p>Resets the environment to an initial state and returns an initial
|
||
observation.</p>
|
||
<p>Note that this function should not reset the environment’s random
|
||
number generator(s); random variables in the environment’s state should
|
||
be sampled independently between multiple calls to <cite>reset()</cite>. In other
|
||
words, each call of <cite>reset()</cite> should yield an environment suitable for
|
||
a new episode, independent of previous episodes.</p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Returns</dt>
|
||
<dd class="field-odd"><p>the initial observation.</p>
|
||
</dd>
|
||
<dt class="field-even">Return type</dt>
|
||
<dd class="field-even"><p>observation (object)</p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
<dl class="py method">
|
||
<dt class="sig sig-object py" id="reagent.gym.envs.functionality.possible_actions_mask_tester.PossibleActionsMaskTester.step">
|
||
<span class="sig-name descname"><span class="pre">step</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">action</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.gym.envs.functionality.possible_actions_mask_tester.PossibleActionsMaskTester.step" title="Permalink to this definition"></a></dt>
|
||
<dd><p>Run one timestep of the environment’s dynamics. When end of
|
||
episode is reached, you are responsible for calling <cite>reset()</cite>
|
||
to reset this environment’s state.</p>
|
||
<p>Accepts an action and returns a tuple (observation, reward, done, info).</p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Parameters</dt>
|
||
<dd class="field-odd"><p><strong>action</strong> (<em>object</em>) – an action provided by the agent</p>
|
||
</dd>
|
||
<dt class="field-even">Returns</dt>
|
||
<dd class="field-even"><p>agent’s observation of the current environment
|
||
reward (float) : amount of reward returned after previous action
|
||
done (bool): whether the episode has ended, in which case further step() calls will return undefined results
|
||
info (dict): contains auxiliary diagnostic information (helpful for debugging, and sometimes learning)</p>
|
||
</dd>
|
||
<dt class="field-odd">Return type</dt>
|
||
<dd class="field-odd"><p>observation (object)</p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="module-reagent.gym.envs.functionality">
|
||
<span id="module-contents"></span><h2>Module contents<a class="headerlink" href="#module-reagent.gym.envs.functionality" title="Permalink to this headline"></a></h2>
|
||
</section>
|
||
</section>
|
||
|
||
|
||
</div>
|
||
</div>
|
||
<footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer">
|
||
<a href="reagent.gym.envs.dynamics.html" class="btn btn-neutral float-left" title="reagent.gym.envs.dynamics package" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a>
|
||
<a href="reagent.gym.envs.pomdp.html" class="btn btn-neutral float-right" title="reagent.gym.envs.pomdp package" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a>
|
||
</div>
|
||
|
||
<hr/>
|
||
|
||
<div role="contentinfo">
|
||
<p>© Copyright 2022, Meta Platforms, Inc.</p>
|
||
</div>
|
||
|
||
Built with <a href="https://www.sphinx-doc.org/">Sphinx</a> using a
|
||
<a href="https://github.com/readthedocs/sphinx_rtd_theme">theme</a>
|
||
provided by <a href="https://readthedocs.org">Read the Docs</a>.
|
||
|
||
|
||
</footer>
|
||
</div>
|
||
</div>
|
||
</section>
|
||
</div>
|
||
<script>
|
||
jQuery(function () {
|
||
SphinxRtdTheme.Navigation.enable(true);
|
||
});
|
||
</script>
|
||
|
||
</body>
|
||
</html> |