mirror of
https://github.com/gryf/coach.git
synced 2025-12-17 19:20:19 +01:00
pre-release 0.10.0
This commit is contained in:
Gal Novik
@@ -3,33 +3,29 @@
|
||||
<!--[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">
|
||||
|
||||
<title>Behavioral Cloning - Reinforcement Learning Coach Documentation</title>
|
||||
|
||||
|
||||
<link rel="shortcut icon" href="../../../img/favicon.ico">
|
||||
|
||||
|
||||
<title>Behavioral Cloning - 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 = "Behavioral Cloning";
|
||||
var mkdocs_page_input_path = "algorithms/imitation/bc.md";
|
||||
var mkdocs_page_url = "/algorithms/imitation/bc/";
|
||||
</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>
|
||||
<script src="../../../js/theme.js"></script>
|
||||
<script src="https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS_HTML"></script>
|
||||
|
||||
<script type="text/javascript" src="../../../js/highlight.pack.js"></script>
|
||||
|
||||
</head>
|
||||
|
||||
@@ -40,7 +36,7 @@
|
||||
|
||||
<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 Documentation</a>
|
||||
<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" />
|
||||
@@ -49,195 +45,150 @@
|
||||
</div>
|
||||
|
||||
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
|
||||
<ul class="current">
|
||||
<ul class="current">
|
||||
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../..">Home</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../..">Home</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../design/index.html">Design</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../../usage/">Usage</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../usage/index.html">Usage</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Design</span>
|
||||
<ul class="subnav">
|
||||
<li><span>Algorithms</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/dqn/index.html">DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/double_dqn/index.html">Double DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/dueling_dqn/index.html">Dueling DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/categorical_dqn/index.html">Categorical DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/mmc/index.html">Mixed Monte Carlo</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/pal/index.html">Persistent Advantage Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/nec/index.html">Neural Episodic Control</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/bs_dqn/index.html">Bootstrapped DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/n_step/index.html">N-Step Q Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/naf/index.html">Normalized Advantage Functions</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/pg/index.html">Policy Gradient</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ac/index.html">Actor-Critic</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ddpg/index.html">Deep Determinstic Policy Gradients</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ppo/index.html">Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/cppo/index.html">Clipped Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../other/dfp/index.html">Direct Future Prediction</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 current">
|
||||
<a class="current" href="./index.html">Behavioral Cloning</a>
|
||||
|
||||
<ul>
|
||||
|
||||
<li class="toctree-l3"><a href="#behavioral-cloning">Behavioral Cloning</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#algorithm-description">Algorithm Description</a></li>
|
||||
|
||||
|
||||
</ul>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
<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>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../dashboard/index.html">Coach Dashboard</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Algorithms</span>
|
||||
<ul class="subnav">
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/dqn/">DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/double_dqn/">Double DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/dueling_dqn/">Dueling DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/categorical_dqn/">Categorical DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/mmc/">Mixed Monte Carlo</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/pal/">Persistent Advantage Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/nec/">Neural Episodic Control</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/bs_dqn/">Bootstrapped DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/n_step/">N-Step Q Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/naf/">Normalized Advantage Functions</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/pg/">Policy Gradient</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ac/">Actor-Critic</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ddpg/">Deep Determinstic Policy Gradients</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ppo/">Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/cppo/">Clipped Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../other/dfp/">Direct Future Prediction</a>
|
||||
</li>
|
||||
<li class=" current">
|
||||
|
||||
<a class="current" href="./">Behavioral Cloning</a>
|
||||
<ul class="subnav">
|
||||
<li><span>Contributing</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../contributing/add_agent/index.html">Adding a New Agent</a>
|
||||
<li class="toctree-l3"><a href="#behavioral-cloning">Behavioral Cloning</a></li>
|
||||
|
||||
<ul>
|
||||
|
||||
</li>
|
||||
<li><a class="toctree-l4" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#algorithm-description">Algorithm Description</a></li>
|
||||
|
||||
</ul>
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../contributing/add_env/index.html">Adding a New Environment</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
</ul>
|
||||
<li>
|
||||
</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="../../../contributing/add_agent/">Adding a New Agent</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../../contributing/add_env/">Adding a New Environment</a>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
</div>
|
||||
@@ -249,7 +200,7 @@
|
||||
|
||||
<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 Documentation</a>
|
||||
<a href="../../..">Reinforcement Learning Coach</a>
|
||||
</nav>
|
||||
|
||||
|
||||
@@ -301,10 +252,10 @@ The training goal is to reduce the difference between the actions predicted by t
|
||||
|
||||
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
|
||||
|
||||
<a href="../../../dashboard/index.html" class="btn btn-neutral float-right" title="Coach Dashboard"/>Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
<a href="../../../dashboard/" class="btn btn-neutral float-right" title="Coach Dashboard">Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
|
||||
|
||||
<a href="../../other/dfp/index.html" class="btn btn-neutral" title="Direct Future Prediction"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
<a href="../../other/dfp/" class="btn btn-neutral" title="Direct Future Prediction"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
|
||||
</div>
|
||||
|
||||
@@ -318,7 +269,7 @@ The training goal is to reduce the difference between the actions predicted by t
|
||||
|
||||
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>
|
||||
|
||||
@@ -326,17 +277,22 @@ The training goal is to reduce the difference between the actions predicted by t
|
||||
|
||||
</div>
|
||||
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<span class="rst-current-version" data-toggle="rst-current-version">
|
||||
|
||||
|
||||
<span><a href="../../other/dfp/index.html" style="color: #fcfcfc;">« Previous</a></span>
|
||||
<span><a href="../../other/dfp/" style="color: #fcfcfc;">« Previous</a></span>
|
||||
|
||||
|
||||
<span style="margin-left: 15px"><a href="../../../dashboard/index.html" style="color: #fcfcfc">Next »</a></span>
|
||||
<span style="margin-left: 15px"><a href="../../../dashboard/" 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>
|
||||
|
||||
@@ -3,33 +3,29 @@
|
||||
<!--[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">
|
||||
|
||||
<title>Direct Future Prediction - Reinforcement Learning Coach Documentation</title>
|
||||
|
||||
|
||||
<link rel="shortcut icon" href="../../../img/favicon.ico">
|
||||
|
||||
|
||||
<title>Direct Future Prediction - 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 = "Direct Future Prediction";
|
||||
var mkdocs_page_input_path = "algorithms/other/dfp.md";
|
||||
var mkdocs_page_url = "/algorithms/other/dfp/";
|
||||
</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>
|
||||
<script src="../../../js/theme.js"></script>
|
||||
<script src="https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS_HTML"></script>
|
||||
|
||||
<script type="text/javascript" src="../../../js/highlight.pack.js"></script>
|
||||
|
||||
</head>
|
||||
|
||||
@@ -40,7 +36,7 @@
|
||||
|
||||
<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 Documentation</a>
|
||||
<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" />
|
||||
@@ -49,195 +45,150 @@
|
||||
</div>
|
||||
|
||||
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
|
||||
<ul class="current">
|
||||
<ul class="current">
|
||||
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../..">Home</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../..">Home</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../design/index.html">Design</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../../usage/">Usage</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../usage/index.html">Usage</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Design</span>
|
||||
<ul class="subnav">
|
||||
<li><span>Algorithms</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/dqn/index.html">DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/double_dqn/index.html">Double DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/dueling_dqn/index.html">Dueling DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/categorical_dqn/index.html">Categorical DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/mmc/index.html">Mixed Monte Carlo</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/pal/index.html">Persistent Advantage Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/nec/index.html">Neural Episodic Control</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/bs_dqn/index.html">Bootstrapped DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/n_step/index.html">N-Step Q Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/naf/index.html">Normalized Advantage Functions</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/pg/index.html">Policy Gradient</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ac/index.html">Actor-Critic</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ddpg/index.html">Deep Determinstic Policy Gradients</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ppo/index.html">Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/cppo/index.html">Clipped Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 current">
|
||||
<a class="current" href="./index.html">Direct Future Prediction</a>
|
||||
|
||||
<ul>
|
||||
|
||||
<li class="toctree-l3"><a href="#direct-future-prediction">Direct Future Prediction</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#algorithm-description">Algorithm Description</a></li>
|
||||
|
||||
|
||||
</ul>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../imitation/bc/index.html">Behavioral Cloning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
<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>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../dashboard/index.html">Coach Dashboard</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Algorithms</span>
|
||||
<ul class="subnav">
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/dqn/">DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/double_dqn/">Double DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/dueling_dqn/">Dueling DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/categorical_dqn/">Categorical DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/mmc/">Mixed Monte Carlo</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/pal/">Persistent Advantage Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/nec/">Neural Episodic Control</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/bs_dqn/">Bootstrapped DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/n_step/">N-Step Q Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/naf/">Normalized Advantage Functions</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/pg/">Policy Gradient</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ac/">Actor-Critic</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ddpg/">Deep Determinstic Policy Gradients</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ppo/">Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/cppo/">Clipped Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class=" current">
|
||||
|
||||
<a class="current" href="./">Direct Future Prediction</a>
|
||||
<ul class="subnav">
|
||||
<li><span>Contributing</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../contributing/add_agent/index.html">Adding a New Agent</a>
|
||||
<li class="toctree-l3"><a href="#direct-future-prediction">Direct Future Prediction</a></li>
|
||||
|
||||
<ul>
|
||||
|
||||
</li>
|
||||
<li><a class="toctree-l4" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#algorithm-description">Algorithm Description</a></li>
|
||||
|
||||
</ul>
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../contributing/add_env/index.html">Adding a New Environment</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
</ul>
|
||||
<li>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../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="../../../contributing/add_agent/">Adding a New Agent</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../../contributing/add_env/">Adding a New Environment</a>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
</div>
|
||||
@@ -249,7 +200,7 @@
|
||||
|
||||
<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 Documentation</a>
|
||||
<a href="../../..">Reinforcement Learning Coach</a>
|
||||
</nav>
|
||||
|
||||
|
||||
@@ -302,10 +253,10 @@
|
||||
|
||||
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
|
||||
|
||||
<a href="../../imitation/bc/index.html" class="btn btn-neutral float-right" title="Behavioral Cloning"/>Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
<a href="../../imitation/bc/" class="btn btn-neutral float-right" title="Behavioral Cloning">Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
|
||||
|
||||
<a href="../../policy_optimization/cppo/index.html" class="btn btn-neutral" title="Clipped Proximal Policy Optimization"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
<a href="../../policy_optimization/cppo/" class="btn btn-neutral" title="Clipped Proximal Policy Optimization"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
|
||||
</div>
|
||||
|
||||
@@ -319,7 +270,7 @@
|
||||
|
||||
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>
|
||||
|
||||
@@ -327,17 +278,22 @@
|
||||
|
||||
</div>
|
||||
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<span class="rst-current-version" data-toggle="rst-current-version">
|
||||
|
||||
|
||||
<span><a href="../../policy_optimization/cppo/index.html" style="color: #fcfcfc;">« Previous</a></span>
|
||||
<span><a href="../../policy_optimization/cppo/" style="color: #fcfcfc;">« Previous</a></span>
|
||||
|
||||
|
||||
<span style="margin-left: 15px"><a href="../../imitation/bc/index.html" style="color: #fcfcfc">Next »</a></span>
|
||||
<span style="margin-left: 15px"><a href="../../imitation/bc/" 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>
|
||||
|
||||
@@ -3,33 +3,29 @@
|
||||
<!--[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">
|
||||
|
||||
<title>Actor-Critic - Reinforcement Learning Coach Documentation</title>
|
||||
|
||||
|
||||
<link rel="shortcut icon" href="../../../img/favicon.ico">
|
||||
|
||||
|
||||
<title>Actor-Critic - 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 = "Actor-Critic";
|
||||
var mkdocs_page_input_path = "algorithms/policy_optimization/ac.md";
|
||||
var mkdocs_page_url = "/algorithms/policy_optimization/ac/";
|
||||
</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>
|
||||
<script src="../../../js/theme.js"></script>
|
||||
<script src="https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS_HTML"></script>
|
||||
|
||||
<script type="text/javascript" src="../../../js/highlight.pack.js"></script>
|
||||
|
||||
</head>
|
||||
|
||||
@@ -40,7 +36,7 @@
|
||||
|
||||
<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 Documentation</a>
|
||||
<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" />
|
||||
@@ -49,195 +45,150 @@
|
||||
</div>
|
||||
|
||||
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
|
||||
<ul class="current">
|
||||
<ul class="current">
|
||||
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../..">Home</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../..">Home</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../design/index.html">Design</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../../usage/">Usage</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../usage/index.html">Usage</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Design</span>
|
||||
<ul class="subnav">
|
||||
<li><span>Algorithms</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/dqn/index.html">DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/double_dqn/index.html">Double DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/dueling_dqn/index.html">Dueling DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/categorical_dqn/index.html">Categorical DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/mmc/index.html">Mixed Monte Carlo</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/pal/index.html">Persistent Advantage Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/nec/index.html">Neural Episodic Control</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/bs_dqn/index.html">Bootstrapped DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/n_step/index.html">N-Step Q Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/naf/index.html">Normalized Advantage Functions</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../pg/index.html">Policy Gradient</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 current">
|
||||
<a class="current" href="./index.html">Actor-Critic</a>
|
||||
|
||||
<ul>
|
||||
|
||||
<li class="toctree-l3"><a href="#actor-critic">Actor-Critic</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#algorithm-description">Algorithm Description</a></li>
|
||||
|
||||
|
||||
</ul>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../ddpg/index.html">Deep Determinstic Policy Gradients</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../ppo/index.html">Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../cppo/index.html">Clipped Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../other/dfp/index.html">Direct Future Prediction</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../imitation/bc/index.html">Behavioral Cloning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
<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>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../dashboard/index.html">Coach Dashboard</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Algorithms</span>
|
||||
<ul class="subnav">
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/dqn/">DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/double_dqn/">Double DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/dueling_dqn/">Dueling DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/categorical_dqn/">Categorical DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/mmc/">Mixed Monte Carlo</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/pal/">Persistent Advantage Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/nec/">Neural Episodic Control</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/bs_dqn/">Bootstrapped DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/n_step/">N-Step Q Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/naf/">Normalized Advantage Functions</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../pg/">Policy Gradient</a>
|
||||
</li>
|
||||
<li class=" current">
|
||||
|
||||
<a class="current" href="./">Actor-Critic</a>
|
||||
<ul class="subnav">
|
||||
<li><span>Contributing</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../contributing/add_agent/index.html">Adding a New Agent</a>
|
||||
<li class="toctree-l3"><a href="#actor-critic">Actor-Critic</a></li>
|
||||
|
||||
<ul>
|
||||
|
||||
</li>
|
||||
<li><a class="toctree-l4" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#algorithm-description">Algorithm Description</a></li>
|
||||
|
||||
</ul>
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../contributing/add_env/index.html">Adding a New Environment</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
</ul>
|
||||
<li>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../ddpg/">Deep Determinstic Policy Gradients</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../ppo/">Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../cppo/">Clipped Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../other/dfp/">Direct Future Prediction</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../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="../../../contributing/add_agent/">Adding a New Agent</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../../contributing/add_env/">Adding a New Environment</a>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
</div>
|
||||
@@ -249,7 +200,7 @@
|
||||
|
||||
<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 Documentation</a>
|
||||
<a href="../../..">Reinforcement Learning Coach</a>
|
||||
</nav>
|
||||
|
||||
|
||||
@@ -302,10 +253,10 @@
|
||||
|
||||
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
|
||||
|
||||
<a href="../ddpg/index.html" class="btn btn-neutral float-right" title="Deep Determinstic Policy Gradients"/>Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
<a href="../ddpg/" class="btn btn-neutral float-right" title="Deep Determinstic Policy Gradients">Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
|
||||
|
||||
<a href="../pg/index.html" class="btn btn-neutral" title="Policy Gradient"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
<a href="../pg/" class="btn btn-neutral" title="Policy Gradient"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
|
||||
</div>
|
||||
|
||||
@@ -319,7 +270,7 @@
|
||||
|
||||
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>
|
||||
|
||||
@@ -327,17 +278,22 @@
|
||||
|
||||
</div>
|
||||
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<span class="rst-current-version" data-toggle="rst-current-version">
|
||||
|
||||
|
||||
<span><a href="../pg/index.html" style="color: #fcfcfc;">« Previous</a></span>
|
||||
<span><a href="../pg/" style="color: #fcfcfc;">« Previous</a></span>
|
||||
|
||||
|
||||
<span style="margin-left: 15px"><a href="../ddpg/index.html" style="color: #fcfcfc">Next »</a></span>
|
||||
<span style="margin-left: 15px"><a href="../ddpg/" 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>
|
||||
|
||||
@@ -3,33 +3,29 @@
|
||||
<!--[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">
|
||||
|
||||
<title>Clipped Proximal Policy Optimization - Reinforcement Learning Coach Documentation</title>
|
||||
|
||||
|
||||
<link rel="shortcut icon" href="../../../img/favicon.ico">
|
||||
|
||||
|
||||
<title>Clipped Proximal Policy Optimization - 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 = "Clipped Proximal Policy Optimization";
|
||||
var mkdocs_page_input_path = "algorithms/policy_optimization/cppo.md";
|
||||
var mkdocs_page_url = "/algorithms/policy_optimization/cppo/";
|
||||
</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>
|
||||
<script src="../../../js/theme.js"></script>
|
||||
<script src="https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS_HTML"></script>
|
||||
|
||||
<script type="text/javascript" src="../../../js/highlight.pack.js"></script>
|
||||
|
||||
</head>
|
||||
|
||||
@@ -40,7 +36,7 @@
|
||||
|
||||
<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 Documentation</a>
|
||||
<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" />
|
||||
@@ -49,195 +45,150 @@
|
||||
</div>
|
||||
|
||||
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
|
||||
<ul class="current">
|
||||
<ul class="current">
|
||||
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../..">Home</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../..">Home</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../design/index.html">Design</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../../usage/">Usage</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../usage/index.html">Usage</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Design</span>
|
||||
<ul class="subnav">
|
||||
<li><span>Algorithms</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/dqn/index.html">DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/double_dqn/index.html">Double DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/dueling_dqn/index.html">Dueling DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/categorical_dqn/index.html">Categorical DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/mmc/index.html">Mixed Monte Carlo</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/pal/index.html">Persistent Advantage Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/nec/index.html">Neural Episodic Control</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/bs_dqn/index.html">Bootstrapped DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/n_step/index.html">N-Step Q Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/naf/index.html">Normalized Advantage Functions</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../pg/index.html">Policy Gradient</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../ac/index.html">Actor-Critic</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../ddpg/index.html">Deep Determinstic Policy Gradients</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../ppo/index.html">Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 current">
|
||||
<a class="current" href="./index.html">Clipped Proximal Policy Optimization</a>
|
||||
|
||||
<ul>
|
||||
|
||||
<li class="toctree-l3"><a href="#clipped-proximal-policy-optimization">Clipped Proximal Policy Optimization</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#algorithm-description">Algorithm Description</a></li>
|
||||
|
||||
|
||||
</ul>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../other/dfp/index.html">Direct Future Prediction</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../imitation/bc/index.html">Behavioral Cloning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
<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>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../dashboard/index.html">Coach Dashboard</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Algorithms</span>
|
||||
<ul class="subnav">
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/dqn/">DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/double_dqn/">Double DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/dueling_dqn/">Dueling DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/categorical_dqn/">Categorical DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/mmc/">Mixed Monte Carlo</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/pal/">Persistent Advantage Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/nec/">Neural Episodic Control</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/bs_dqn/">Bootstrapped DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/n_step/">N-Step Q Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/naf/">Normalized Advantage Functions</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../pg/">Policy Gradient</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../ac/">Actor-Critic</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../ddpg/">Deep Determinstic Policy Gradients</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../ppo/">Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class=" current">
|
||||
|
||||
<a class="current" href="./">Clipped Proximal Policy Optimization</a>
|
||||
<ul class="subnav">
|
||||
<li><span>Contributing</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../contributing/add_agent/index.html">Adding a New Agent</a>
|
||||
<li class="toctree-l3"><a href="#clipped-proximal-policy-optimization">Clipped Proximal Policy Optimization</a></li>
|
||||
|
||||
<ul>
|
||||
|
||||
</li>
|
||||
<li><a class="toctree-l4" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#algorithm-description">Algorithm Description</a></li>
|
||||
|
||||
</ul>
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../contributing/add_env/index.html">Adding a New Environment</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
</ul>
|
||||
<li>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../other/dfp/">Direct Future Prediction</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../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="../../../contributing/add_agent/">Adding a New Agent</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../../contributing/add_env/">Adding a New Environment</a>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
</div>
|
||||
@@ -249,7 +200,7 @@
|
||||
|
||||
<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 Documentation</a>
|
||||
<a href="../../..">Reinforcement Learning Coach</a>
|
||||
</nav>
|
||||
|
||||
|
||||
@@ -312,10 +263,10 @@
|
||||
|
||||
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
|
||||
|
||||
<a href="../../other/dfp/index.html" class="btn btn-neutral float-right" title="Direct Future Prediction"/>Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
<a href="../../other/dfp/" class="btn btn-neutral float-right" title="Direct Future Prediction">Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
|
||||
|
||||
<a href="../ppo/index.html" class="btn btn-neutral" title="Proximal Policy Optimization"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
<a href="../ppo/" class="btn btn-neutral" title="Proximal Policy Optimization"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
|
||||
</div>
|
||||
|
||||
@@ -329,7 +280,7 @@
|
||||
|
||||
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>
|
||||
|
||||
@@ -337,17 +288,22 @@
|
||||
|
||||
</div>
|
||||
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<span class="rst-current-version" data-toggle="rst-current-version">
|
||||
|
||||
|
||||
<span><a href="../ppo/index.html" style="color: #fcfcfc;">« Previous</a></span>
|
||||
<span><a href="../ppo/" style="color: #fcfcfc;">« Previous</a></span>
|
||||
|
||||
|
||||
<span style="margin-left: 15px"><a href="../../other/dfp/index.html" style="color: #fcfcfc">Next »</a></span>
|
||||
<span style="margin-left: 15px"><a href="../../other/dfp/" 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>
|
||||
|
||||
@@ -3,33 +3,29 @@
|
||||
<!--[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">
|
||||
|
||||
<title>Deep Determinstic Policy Gradients - Reinforcement Learning Coach Documentation</title>
|
||||
|
||||
|
||||
<link rel="shortcut icon" href="../../../img/favicon.ico">
|
||||
|
||||
|
||||
<title>Deep Determinstic Policy Gradients - 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 = "Deep Determinstic Policy Gradients";
|
||||
var mkdocs_page_input_path = "algorithms/policy_optimization/ddpg.md";
|
||||
var mkdocs_page_url = "/algorithms/policy_optimization/ddpg/";
|
||||
</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>
|
||||
<script src="../../../js/theme.js"></script>
|
||||
<script src="https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS_HTML"></script>
|
||||
|
||||
<script type="text/javascript" src="../../../js/highlight.pack.js"></script>
|
||||
|
||||
</head>
|
||||
|
||||
@@ -40,7 +36,7 @@
|
||||
|
||||
<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 Documentation</a>
|
||||
<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" />
|
||||
@@ -49,195 +45,150 @@
|
||||
</div>
|
||||
|
||||
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
|
||||
<ul class="current">
|
||||
<ul class="current">
|
||||
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../..">Home</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../..">Home</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../design/index.html">Design</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../../usage/">Usage</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../usage/index.html">Usage</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Design</span>
|
||||
<ul class="subnav">
|
||||
<li><span>Algorithms</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/dqn/index.html">DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/double_dqn/index.html">Double DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/dueling_dqn/index.html">Dueling DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/categorical_dqn/index.html">Categorical DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/mmc/index.html">Mixed Monte Carlo</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/pal/index.html">Persistent Advantage Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/nec/index.html">Neural Episodic Control</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/bs_dqn/index.html">Bootstrapped DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/n_step/index.html">N-Step Q Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/naf/index.html">Normalized Advantage Functions</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../pg/index.html">Policy Gradient</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../ac/index.html">Actor-Critic</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 current">
|
||||
<a class="current" href="./index.html">Deep Determinstic Policy Gradients</a>
|
||||
|
||||
<ul>
|
||||
|
||||
<li class="toctree-l3"><a href="#deep-deterministic-policy-gradient">Deep Deterministic Policy Gradient</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#algorithm-description">Algorithm Description</a></li>
|
||||
|
||||
|
||||
</ul>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../ppo/index.html">Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../cppo/index.html">Clipped Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../other/dfp/index.html">Direct Future Prediction</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../imitation/bc/index.html">Behavioral Cloning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
<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>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../dashboard/index.html">Coach Dashboard</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Algorithms</span>
|
||||
<ul class="subnav">
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/dqn/">DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/double_dqn/">Double DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/dueling_dqn/">Dueling DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/categorical_dqn/">Categorical DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/mmc/">Mixed Monte Carlo</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/pal/">Persistent Advantage Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/nec/">Neural Episodic Control</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/bs_dqn/">Bootstrapped DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/n_step/">N-Step Q Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/naf/">Normalized Advantage Functions</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../pg/">Policy Gradient</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../ac/">Actor-Critic</a>
|
||||
</li>
|
||||
<li class=" current">
|
||||
|
||||
<a class="current" href="./">Deep Determinstic Policy Gradients</a>
|
||||
<ul class="subnav">
|
||||
<li><span>Contributing</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../contributing/add_agent/index.html">Adding a New Agent</a>
|
||||
<li class="toctree-l3"><a href="#deep-deterministic-policy-gradient">Deep Deterministic Policy Gradient</a></li>
|
||||
|
||||
<ul>
|
||||
|
||||
</li>
|
||||
<li><a class="toctree-l4" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#algorithm-description">Algorithm Description</a></li>
|
||||
|
||||
</ul>
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../contributing/add_env/index.html">Adding a New Environment</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
</ul>
|
||||
<li>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../ppo/">Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../cppo/">Clipped Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../other/dfp/">Direct Future Prediction</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../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="../../../contributing/add_agent/">Adding a New Agent</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../../contributing/add_env/">Adding a New Environment</a>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
</div>
|
||||
@@ -249,7 +200,7 @@
|
||||
|
||||
<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 Documentation</a>
|
||||
<a href="../../..">Reinforcement Learning Coach</a>
|
||||
</nav>
|
||||
|
||||
|
||||
@@ -310,10 +261,10 @@
|
||||
|
||||
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
|
||||
|
||||
<a href="../ppo/index.html" class="btn btn-neutral float-right" title="Proximal Policy Optimization"/>Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
<a href="../ppo/" class="btn btn-neutral float-right" title="Proximal Policy Optimization">Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
|
||||
|
||||
<a href="../ac/index.html" class="btn btn-neutral" title="Actor-Critic"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
<a href="../ac/" class="btn btn-neutral" title="Actor-Critic"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
|
||||
</div>
|
||||
|
||||
@@ -327,7 +278,7 @@
|
||||
|
||||
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>
|
||||
|
||||
@@ -335,17 +286,22 @@
|
||||
|
||||
</div>
|
||||
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<span class="rst-current-version" data-toggle="rst-current-version">
|
||||
|
||||
|
||||
<span><a href="../ac/index.html" style="color: #fcfcfc;">« Previous</a></span>
|
||||
<span><a href="../ac/" style="color: #fcfcfc;">« Previous</a></span>
|
||||
|
||||
|
||||
<span style="margin-left: 15px"><a href="../ppo/index.html" style="color: #fcfcfc">Next »</a></span>
|
||||
<span style="margin-left: 15px"><a href="../ppo/" 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>
|
||||
|
||||
@@ -3,33 +3,29 @@
|
||||
<!--[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">
|
||||
|
||||
<title>Policy Gradient - Reinforcement Learning Coach Documentation</title>
|
||||
|
||||
|
||||
<link rel="shortcut icon" href="../../../img/favicon.ico">
|
||||
|
||||
|
||||
<title>Policy Gradient - 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 = "Policy Gradient";
|
||||
var mkdocs_page_input_path = "algorithms/policy_optimization/pg.md";
|
||||
var mkdocs_page_url = "/algorithms/policy_optimization/pg/";
|
||||
</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>
|
||||
<script src="../../../js/theme.js"></script>
|
||||
<script src="https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS_HTML"></script>
|
||||
|
||||
<script type="text/javascript" src="../../../js/highlight.pack.js"></script>
|
||||
|
||||
</head>
|
||||
|
||||
@@ -40,7 +36,7 @@
|
||||
|
||||
<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 Documentation</a>
|
||||
<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" />
|
||||
@@ -49,195 +45,150 @@
|
||||
</div>
|
||||
|
||||
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
|
||||
<ul class="current">
|
||||
<ul class="current">
|
||||
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../..">Home</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../..">Home</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../design/index.html">Design</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../../usage/">Usage</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../usage/index.html">Usage</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Design</span>
|
||||
<ul class="subnav">
|
||||
<li><span>Algorithms</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/dqn/index.html">DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/double_dqn/index.html">Double DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/dueling_dqn/index.html">Dueling DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/categorical_dqn/index.html">Categorical DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/mmc/index.html">Mixed Monte Carlo</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/pal/index.html">Persistent Advantage Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/nec/index.html">Neural Episodic Control</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/bs_dqn/index.html">Bootstrapped DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/n_step/index.html">N-Step Q Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/naf/index.html">Normalized Advantage Functions</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 current">
|
||||
<a class="current" href="./index.html">Policy Gradient</a>
|
||||
|
||||
<ul>
|
||||
|
||||
<li class="toctree-l3"><a href="#policy-gradient">Policy Gradient</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#algorithm-description">Algorithm Description</a></li>
|
||||
|
||||
|
||||
</ul>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../ac/index.html">Actor-Critic</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../ddpg/index.html">Deep Determinstic Policy Gradients</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../ppo/index.html">Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../cppo/index.html">Clipped Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../other/dfp/index.html">Direct Future Prediction</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../imitation/bc/index.html">Behavioral Cloning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
<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>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../dashboard/index.html">Coach Dashboard</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Algorithms</span>
|
||||
<ul class="subnav">
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/dqn/">DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/double_dqn/">Double DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/dueling_dqn/">Dueling DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/categorical_dqn/">Categorical DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/mmc/">Mixed Monte Carlo</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/pal/">Persistent Advantage Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/nec/">Neural Episodic Control</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/bs_dqn/">Bootstrapped DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/n_step/">N-Step Q Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/naf/">Normalized Advantage Functions</a>
|
||||
</li>
|
||||
<li class=" current">
|
||||
|
||||
<a class="current" href="./">Policy Gradient</a>
|
||||
<ul class="subnav">
|
||||
<li><span>Contributing</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../contributing/add_agent/index.html">Adding a New Agent</a>
|
||||
<li class="toctree-l3"><a href="#policy-gradient">Policy Gradient</a></li>
|
||||
|
||||
<ul>
|
||||
|
||||
</li>
|
||||
<li><a class="toctree-l4" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#algorithm-description">Algorithm Description</a></li>
|
||||
|
||||
</ul>
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../contributing/add_env/index.html">Adding a New Environment</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
</ul>
|
||||
<li>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../ac/">Actor-Critic</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../ddpg/">Deep Determinstic Policy Gradients</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../ppo/">Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../cppo/">Clipped Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../other/dfp/">Direct Future Prediction</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../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="../../../contributing/add_agent/">Adding a New Agent</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../../contributing/add_env/">Adding a New Environment</a>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
</div>
|
||||
@@ -249,7 +200,7 @@
|
||||
|
||||
<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 Documentation</a>
|
||||
<a href="../../..">Reinforcement Learning Coach</a>
|
||||
</nav>
|
||||
|
||||
|
||||
@@ -302,10 +253,10 @@
|
||||
|
||||
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
|
||||
|
||||
<a href="../ac/index.html" class="btn btn-neutral float-right" title="Actor-Critic"/>Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
<a href="../ac/" class="btn btn-neutral float-right" title="Actor-Critic">Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
|
||||
|
||||
<a href="../../value_optimization/naf/index.html" class="btn btn-neutral" title="Normalized Advantage Functions"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
<a href="../../value_optimization/naf/" class="btn btn-neutral" title="Normalized Advantage Functions"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
|
||||
</div>
|
||||
|
||||
@@ -319,7 +270,7 @@
|
||||
|
||||
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>
|
||||
|
||||
@@ -327,17 +278,22 @@
|
||||
|
||||
</div>
|
||||
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<span class="rst-current-version" data-toggle="rst-current-version">
|
||||
|
||||
|
||||
<span><a href="../../value_optimization/naf/index.html" style="color: #fcfcfc;">« Previous</a></span>
|
||||
<span><a href="../../value_optimization/naf/" style="color: #fcfcfc;">« Previous</a></span>
|
||||
|
||||
|
||||
<span style="margin-left: 15px"><a href="../ac/index.html" style="color: #fcfcfc">Next »</a></span>
|
||||
<span style="margin-left: 15px"><a href="../ac/" 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>
|
||||
|
||||
@@ -3,33 +3,29 @@
|
||||
<!--[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">
|
||||
|
||||
<title>Proximal Policy Optimization - Reinforcement Learning Coach Documentation</title>
|
||||
|
||||
|
||||
<link rel="shortcut icon" href="../../../img/favicon.ico">
|
||||
|
||||
|
||||
<title>Proximal Policy Optimization - 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 = "Proximal Policy Optimization";
|
||||
var mkdocs_page_input_path = "algorithms/policy_optimization/ppo.md";
|
||||
var mkdocs_page_url = "/algorithms/policy_optimization/ppo/";
|
||||
</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>
|
||||
<script src="../../../js/theme.js"></script>
|
||||
<script src="https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS_HTML"></script>
|
||||
|
||||
<script type="text/javascript" src="../../../js/highlight.pack.js"></script>
|
||||
|
||||
</head>
|
||||
|
||||
@@ -40,7 +36,7 @@
|
||||
|
||||
<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 Documentation</a>
|
||||
<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" />
|
||||
@@ -49,195 +45,150 @@
|
||||
</div>
|
||||
|
||||
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
|
||||
<ul class="current">
|
||||
<ul class="current">
|
||||
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../..">Home</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../..">Home</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../design/index.html">Design</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../../usage/">Usage</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../usage/index.html">Usage</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Design</span>
|
||||
<ul class="subnav">
|
||||
<li><span>Algorithms</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/dqn/index.html">DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/double_dqn/index.html">Double DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/dueling_dqn/index.html">Dueling DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/categorical_dqn/index.html">Categorical DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/mmc/index.html">Mixed Monte Carlo</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/pal/index.html">Persistent Advantage Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/nec/index.html">Neural Episodic Control</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/bs_dqn/index.html">Bootstrapped DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/n_step/index.html">N-Step Q Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../value_optimization/naf/index.html">Normalized Advantage Functions</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../pg/index.html">Policy Gradient</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../ac/index.html">Actor-Critic</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../ddpg/index.html">Deep Determinstic Policy Gradients</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 current">
|
||||
<a class="current" href="./index.html">Proximal Policy Optimization</a>
|
||||
|
||||
<ul>
|
||||
|
||||
<li class="toctree-l3"><a href="#proximal-policy-optimization">Proximal Policy Optimization</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#algorithm-description">Algorithm Description</a></li>
|
||||
|
||||
|
||||
</ul>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../cppo/index.html">Clipped Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../other/dfp/index.html">Direct Future Prediction</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../imitation/bc/index.html">Behavioral Cloning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
<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>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../dashboard/index.html">Coach Dashboard</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Algorithms</span>
|
||||
<ul class="subnav">
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/dqn/">DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/double_dqn/">Double DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/dueling_dqn/">Dueling DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/categorical_dqn/">Categorical DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/mmc/">Mixed Monte Carlo</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/pal/">Persistent Advantage Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/nec/">Neural Episodic Control</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/bs_dqn/">Bootstrapped DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/n_step/">N-Step Q Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../value_optimization/naf/">Normalized Advantage Functions</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../pg/">Policy Gradient</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../ac/">Actor-Critic</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../ddpg/">Deep Determinstic Policy Gradients</a>
|
||||
</li>
|
||||
<li class=" current">
|
||||
|
||||
<a class="current" href="./">Proximal Policy Optimization</a>
|
||||
<ul class="subnav">
|
||||
<li><span>Contributing</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../contributing/add_agent/index.html">Adding a New Agent</a>
|
||||
<li class="toctree-l3"><a href="#proximal-policy-optimization">Proximal Policy Optimization</a></li>
|
||||
|
||||
<ul>
|
||||
|
||||
</li>
|
||||
<li><a class="toctree-l4" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#algorithm-description">Algorithm Description</a></li>
|
||||
|
||||
</ul>
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../contributing/add_env/index.html">Adding a New Environment</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
</ul>
|
||||
<li>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../cppo/">Clipped Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../other/dfp/">Direct Future Prediction</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../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="../../../contributing/add_agent/">Adding a New Agent</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../../contributing/add_env/">Adding a New Environment</a>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
</div>
|
||||
@@ -249,7 +200,7 @@
|
||||
|
||||
<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 Documentation</a>
|
||||
<a href="../../..">Reinforcement Learning Coach</a>
|
||||
</nav>
|
||||
|
||||
|
||||
@@ -303,10 +254,10 @@
|
||||
|
||||
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
|
||||
|
||||
<a href="../cppo/index.html" class="btn btn-neutral float-right" title="Clipped Proximal Policy Optimization"/>Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
<a href="../cppo/" class="btn btn-neutral float-right" title="Clipped Proximal Policy Optimization">Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
|
||||
|
||||
<a href="../ddpg/index.html" class="btn btn-neutral" title="Deep Determinstic Policy Gradients"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
<a href="../ddpg/" class="btn btn-neutral" title="Deep Determinstic Policy Gradients"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
|
||||
</div>
|
||||
|
||||
@@ -320,7 +271,7 @@
|
||||
|
||||
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>
|
||||
|
||||
@@ -328,17 +279,22 @@
|
||||
|
||||
</div>
|
||||
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<span class="rst-current-version" data-toggle="rst-current-version">
|
||||
|
||||
|
||||
<span><a href="../ddpg/index.html" style="color: #fcfcfc;">« Previous</a></span>
|
||||
<span><a href="../ddpg/" style="color: #fcfcfc;">« Previous</a></span>
|
||||
|
||||
|
||||
<span style="margin-left: 15px"><a href="../cppo/index.html" style="color: #fcfcfc">Next »</a></span>
|
||||
<span style="margin-left: 15px"><a href="../cppo/" 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>
|
||||
|
||||
@@ -3,33 +3,29 @@
|
||||
<!--[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">
|
||||
|
||||
<title>Bootstrapped DQN - Reinforcement Learning Coach Documentation</title>
|
||||
|
||||
|
||||
<link rel="shortcut icon" href="../../../img/favicon.ico">
|
||||
|
||||
|
||||
<title>Bootstrapped DQN - 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 = "Bootstrapped DQN";
|
||||
var mkdocs_page_input_path = "algorithms/value_optimization/bs_dqn.md";
|
||||
var mkdocs_page_url = "/algorithms/value_optimization/bs_dqn/";
|
||||
</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>
|
||||
<script src="../../../js/theme.js"></script>
|
||||
<script src="https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS_HTML"></script>
|
||||
|
||||
<script type="text/javascript" src="../../../js/highlight.pack.js"></script>
|
||||
|
||||
</head>
|
||||
|
||||
@@ -40,7 +36,7 @@
|
||||
|
||||
<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 Documentation</a>
|
||||
<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" />
|
||||
@@ -49,195 +45,150 @@
|
||||
</div>
|
||||
|
||||
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
|
||||
<ul class="current">
|
||||
<ul class="current">
|
||||
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../..">Home</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../..">Home</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../design/index.html">Design</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../../usage/">Usage</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../usage/index.html">Usage</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Design</span>
|
||||
<ul class="subnav">
|
||||
<li><span>Algorithms</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../dqn/index.html">DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../double_dqn/index.html">Double DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../dueling_dqn/index.html">Dueling DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../categorical_dqn/index.html">Categorical DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../mmc/index.html">Mixed Monte Carlo</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../pal/index.html">Persistent Advantage Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../nec/index.html">Neural Episodic Control</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 current">
|
||||
<a class="current" href="./index.html">Bootstrapped DQN</a>
|
||||
|
||||
<ul>
|
||||
|
||||
<li class="toctree-l3"><a href="#bootstrapped-dqn">Bootstrapped DQN</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#algorithm-description">Algorithm Description</a></li>
|
||||
|
||||
|
||||
</ul>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../n_step/index.html">N-Step Q Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../naf/index.html">Normalized Advantage Functions</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/pg/index.html">Policy Gradient</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ac/index.html">Actor-Critic</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ddpg/index.html">Deep Determinstic Policy Gradients</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ppo/index.html">Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/cppo/index.html">Clipped Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../other/dfp/index.html">Direct Future Prediction</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../imitation/bc/index.html">Behavioral Cloning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
<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>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../dashboard/index.html">Coach Dashboard</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Algorithms</span>
|
||||
<ul class="subnav">
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../dqn/">DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../double_dqn/">Double DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../dueling_dqn/">Dueling DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../categorical_dqn/">Categorical DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../mmc/">Mixed Monte Carlo</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../pal/">Persistent Advantage Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../nec/">Neural Episodic Control</a>
|
||||
</li>
|
||||
<li class=" current">
|
||||
|
||||
<a class="current" href="./">Bootstrapped DQN</a>
|
||||
<ul class="subnav">
|
||||
<li><span>Contributing</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../contributing/add_agent/index.html">Adding a New Agent</a>
|
||||
<li class="toctree-l3"><a href="#bootstrapped-dqn">Bootstrapped DQN</a></li>
|
||||
|
||||
<ul>
|
||||
|
||||
</li>
|
||||
<li><a class="toctree-l4" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#algorithm-description">Algorithm Description</a></li>
|
||||
|
||||
</ul>
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../contributing/add_env/index.html">Adding a New Environment</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
</ul>
|
||||
<li>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../n_step/">N-Step Q Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../naf/">Normalized Advantage Functions</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/pg/">Policy Gradient</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ac/">Actor-Critic</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ddpg/">Deep Determinstic Policy Gradients</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ppo/">Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/cppo/">Clipped Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../other/dfp/">Direct Future Prediction</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../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="../../../contributing/add_agent/">Adding a New Agent</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../../contributing/add_env/">Adding a New Environment</a>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
</div>
|
||||
@@ -249,7 +200,7 @@
|
||||
|
||||
<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 Documentation</a>
|
||||
<a href="../../..">Reinforcement Learning Coach</a>
|
||||
</nav>
|
||||
|
||||
|
||||
@@ -304,10 +255,10 @@
|
||||
|
||||
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
|
||||
|
||||
<a href="../n_step/index.html" class="btn btn-neutral float-right" title="N-Step Q Learning"/>Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
<a href="../n_step/" class="btn btn-neutral float-right" title="N-Step Q Learning">Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
|
||||
|
||||
<a href="../nec/index.html" class="btn btn-neutral" title="Neural Episodic Control"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
<a href="../nec/" class="btn btn-neutral" title="Neural Episodic Control"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
|
||||
</div>
|
||||
|
||||
@@ -321,7 +272,7 @@
|
||||
|
||||
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>
|
||||
|
||||
@@ -329,17 +280,22 @@
|
||||
|
||||
</div>
|
||||
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<span class="rst-current-version" data-toggle="rst-current-version">
|
||||
|
||||
|
||||
<span><a href="../nec/index.html" style="color: #fcfcfc;">« Previous</a></span>
|
||||
<span><a href="../nec/" style="color: #fcfcfc;">« Previous</a></span>
|
||||
|
||||
|
||||
<span style="margin-left: 15px"><a href="../n_step/index.html" style="color: #fcfcfc">Next »</a></span>
|
||||
<span style="margin-left: 15px"><a href="../n_step/" 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>
|
||||
|
||||
@@ -3,33 +3,29 @@
|
||||
<!--[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">
|
||||
|
||||
<title>Categorical DQN - Reinforcement Learning Coach Documentation</title>
|
||||
|
||||
|
||||
<link rel="shortcut icon" href="../../../img/favicon.ico">
|
||||
|
||||
|
||||
<title>Categorical DQN - 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 = "Categorical DQN";
|
||||
var mkdocs_page_input_path = "algorithms/value_optimization/categorical_dqn.md";
|
||||
var mkdocs_page_url = "/algorithms/value_optimization/categorical_dqn/";
|
||||
</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>
|
||||
<script src="../../../js/theme.js"></script>
|
||||
<script src="https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS_HTML"></script>
|
||||
|
||||
<script type="text/javascript" src="../../../js/highlight.pack.js"></script>
|
||||
|
||||
</head>
|
||||
|
||||
@@ -40,7 +36,7 @@
|
||||
|
||||
<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 Documentation</a>
|
||||
<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" />
|
||||
@@ -49,195 +45,150 @@
|
||||
</div>
|
||||
|
||||
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
|
||||
<ul class="current">
|
||||
<ul class="current">
|
||||
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../..">Home</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../..">Home</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../design/index.html">Design</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../../usage/">Usage</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../usage/index.html">Usage</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Design</span>
|
||||
<ul class="subnav">
|
||||
<li><span>Algorithms</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../dqn/index.html">DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../double_dqn/index.html">Double DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../dueling_dqn/index.html">Dueling DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 current">
|
||||
<a class="current" href="./index.html">Categorical DQN</a>
|
||||
|
||||
<ul>
|
||||
|
||||
<li class="toctree-l3"><a href="#categorical-dqn">Categorical DQN</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#algorithm-description">Algorithm Description</a></li>
|
||||
|
||||
|
||||
</ul>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../mmc/index.html">Mixed Monte Carlo</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../pal/index.html">Persistent Advantage Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../nec/index.html">Neural Episodic Control</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../bs_dqn/index.html">Bootstrapped DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../n_step/index.html">N-Step Q Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../naf/index.html">Normalized Advantage Functions</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/pg/index.html">Policy Gradient</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ac/index.html">Actor-Critic</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ddpg/index.html">Deep Determinstic Policy Gradients</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ppo/index.html">Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/cppo/index.html">Clipped Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../other/dfp/index.html">Direct Future Prediction</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../imitation/bc/index.html">Behavioral Cloning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
<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>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../dashboard/index.html">Coach Dashboard</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Algorithms</span>
|
||||
<ul class="subnav">
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../dqn/">DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../double_dqn/">Double DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../dueling_dqn/">Dueling DQN</a>
|
||||
</li>
|
||||
<li class=" current">
|
||||
|
||||
<a class="current" href="./">Categorical DQN</a>
|
||||
<ul class="subnav">
|
||||
<li><span>Contributing</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../contributing/add_agent/index.html">Adding a New Agent</a>
|
||||
<li class="toctree-l3"><a href="#categorical-dqn">Categorical DQN</a></li>
|
||||
|
||||
<ul>
|
||||
|
||||
</li>
|
||||
<li><a class="toctree-l4" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#algorithm-description">Algorithm Description</a></li>
|
||||
|
||||
</ul>
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../contributing/add_env/index.html">Adding a New Environment</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
</ul>
|
||||
<li>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../mmc/">Mixed Monte Carlo</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../pal/">Persistent Advantage Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../nec/">Neural Episodic Control</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../bs_dqn/">Bootstrapped DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../n_step/">N-Step Q Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../naf/">Normalized Advantage Functions</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/pg/">Policy Gradient</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ac/">Actor-Critic</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ddpg/">Deep Determinstic Policy Gradients</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ppo/">Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/cppo/">Clipped Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../other/dfp/">Direct Future Prediction</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../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="../../../contributing/add_agent/">Adding a New Agent</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../../contributing/add_env/">Adding a New Environment</a>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
</div>
|
||||
@@ -249,7 +200,7 @@
|
||||
|
||||
<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 Documentation</a>
|
||||
<a href="../../..">Reinforcement Learning Coach</a>
|
||||
</nav>
|
||||
|
||||
|
||||
@@ -313,10 +264,10 @@
|
||||
|
||||
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
|
||||
|
||||
<a href="../mmc/index.html" class="btn btn-neutral float-right" title="Mixed Monte Carlo"/>Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
<a href="../mmc/" class="btn btn-neutral float-right" title="Mixed Monte Carlo">Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
|
||||
|
||||
<a href="../dueling_dqn/index.html" class="btn btn-neutral" title="Dueling DQN"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
<a href="../dueling_dqn/" class="btn btn-neutral" title="Dueling DQN"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
|
||||
</div>
|
||||
|
||||
@@ -330,7 +281,7 @@
|
||||
|
||||
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>
|
||||
|
||||
@@ -338,17 +289,22 @@
|
||||
|
||||
</div>
|
||||
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<span class="rst-current-version" data-toggle="rst-current-version">
|
||||
|
||||
|
||||
<span><a href="../dueling_dqn/index.html" style="color: #fcfcfc;">« Previous</a></span>
|
||||
<span><a href="../dueling_dqn/" style="color: #fcfcfc;">« Previous</a></span>
|
||||
|
||||
|
||||
<span style="margin-left: 15px"><a href="../mmc/index.html" style="color: #fcfcfc">Next »</a></span>
|
||||
<span style="margin-left: 15px"><a href="../mmc/" 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>
|
||||
|
||||
@@ -3,33 +3,29 @@
|
||||
<!--[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">
|
||||
|
||||
<title>Double DQN - Reinforcement Learning Coach Documentation</title>
|
||||
|
||||
|
||||
<link rel="shortcut icon" href="../../../img/favicon.ico">
|
||||
|
||||
|
||||
<title>Double DQN - 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 = "Double DQN";
|
||||
var mkdocs_page_input_path = "algorithms/value_optimization/double_dqn.md";
|
||||
var mkdocs_page_url = "/algorithms/value_optimization/double_dqn/";
|
||||
</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>
|
||||
<script src="../../../js/theme.js"></script>
|
||||
<script src="https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS_HTML"></script>
|
||||
|
||||
<script type="text/javascript" src="../../../js/highlight.pack.js"></script>
|
||||
|
||||
</head>
|
||||
|
||||
@@ -40,7 +36,7 @@
|
||||
|
||||
<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 Documentation</a>
|
||||
<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" />
|
||||
@@ -49,195 +45,150 @@
|
||||
</div>
|
||||
|
||||
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
|
||||
<ul class="current">
|
||||
<ul class="current">
|
||||
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../..">Home</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../..">Home</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../design/index.html">Design</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../../usage/">Usage</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../usage/index.html">Usage</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Design</span>
|
||||
<ul class="subnav">
|
||||
<li><span>Algorithms</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../dqn/index.html">DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 current">
|
||||
<a class="current" href="./index.html">Double DQN</a>
|
||||
|
||||
<ul>
|
||||
|
||||
<li class="toctree-l3"><a href="#double-dqn">Double DQN</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#algorithm-description">Algorithm Description</a></li>
|
||||
|
||||
|
||||
</ul>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../dueling_dqn/index.html">Dueling DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../categorical_dqn/index.html">Categorical DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../mmc/index.html">Mixed Monte Carlo</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../pal/index.html">Persistent Advantage Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../nec/index.html">Neural Episodic Control</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../bs_dqn/index.html">Bootstrapped DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../n_step/index.html">N-Step Q Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../naf/index.html">Normalized Advantage Functions</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/pg/index.html">Policy Gradient</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ac/index.html">Actor-Critic</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ddpg/index.html">Deep Determinstic Policy Gradients</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ppo/index.html">Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/cppo/index.html">Clipped Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../other/dfp/index.html">Direct Future Prediction</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../imitation/bc/index.html">Behavioral Cloning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
<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>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../dashboard/index.html">Coach Dashboard</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Algorithms</span>
|
||||
<ul class="subnav">
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../dqn/">DQN</a>
|
||||
</li>
|
||||
<li class=" current">
|
||||
|
||||
<a class="current" href="./">Double DQN</a>
|
||||
<ul class="subnav">
|
||||
<li><span>Contributing</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../contributing/add_agent/index.html">Adding a New Agent</a>
|
||||
<li class="toctree-l3"><a href="#double-dqn">Double DQN</a></li>
|
||||
|
||||
<ul>
|
||||
|
||||
</li>
|
||||
<li><a class="toctree-l4" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#algorithm-description">Algorithm Description</a></li>
|
||||
|
||||
</ul>
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../contributing/add_env/index.html">Adding a New Environment</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
</ul>
|
||||
<li>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../dueling_dqn/">Dueling DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../categorical_dqn/">Categorical DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../mmc/">Mixed Monte Carlo</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../pal/">Persistent Advantage Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../nec/">Neural Episodic Control</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../bs_dqn/">Bootstrapped DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../n_step/">N-Step Q Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../naf/">Normalized Advantage Functions</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/pg/">Policy Gradient</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ac/">Actor-Critic</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ddpg/">Deep Determinstic Policy Gradients</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ppo/">Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/cppo/">Clipped Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../other/dfp/">Direct Future Prediction</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../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="../../../contributing/add_agent/">Adding a New Agent</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../../contributing/add_env/">Adding a New Environment</a>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
</div>
|
||||
@@ -249,7 +200,7 @@
|
||||
|
||||
<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 Documentation</a>
|
||||
<a href="../../..">Reinforcement Learning Coach</a>
|
||||
</nav>
|
||||
|
||||
|
||||
@@ -308,10 +259,10 @@
|
||||
|
||||
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
|
||||
|
||||
<a href="../dueling_dqn/index.html" class="btn btn-neutral float-right" title="Dueling DQN"/>Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
<a href="../dueling_dqn/" class="btn btn-neutral float-right" title="Dueling DQN">Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
|
||||
|
||||
<a href="../dqn/index.html" class="btn btn-neutral" title="DQN"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
<a href="../dqn/" class="btn btn-neutral" title="DQN"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
|
||||
</div>
|
||||
|
||||
@@ -325,7 +276,7 @@
|
||||
|
||||
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>
|
||||
|
||||
@@ -333,17 +284,22 @@
|
||||
|
||||
</div>
|
||||
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<span class="rst-current-version" data-toggle="rst-current-version">
|
||||
|
||||
|
||||
<span><a href="../dqn/index.html" style="color: #fcfcfc;">« Previous</a></span>
|
||||
<span><a href="../dqn/" style="color: #fcfcfc;">« Previous</a></span>
|
||||
|
||||
|
||||
<span style="margin-left: 15px"><a href="../dueling_dqn/index.html" style="color: #fcfcfc">Next »</a></span>
|
||||
<span style="margin-left: 15px"><a href="../dueling_dqn/" 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>
|
||||
|
||||
@@ -3,33 +3,29 @@
|
||||
<!--[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">
|
||||
|
||||
<title>DQN - Reinforcement Learning Coach Documentation</title>
|
||||
|
||||
|
||||
<link rel="shortcut icon" href="../../../img/favicon.ico">
|
||||
|
||||
|
||||
<title>DQN - 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 = "DQN";
|
||||
var mkdocs_page_input_path = "algorithms/value_optimization/dqn.md";
|
||||
var mkdocs_page_url = "/algorithms/value_optimization/dqn/";
|
||||
</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>
|
||||
<script src="../../../js/theme.js"></script>
|
||||
<script src="https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS_HTML"></script>
|
||||
|
||||
<script type="text/javascript" src="../../../js/highlight.pack.js"></script>
|
||||
|
||||
</head>
|
||||
|
||||
@@ -40,7 +36,7 @@
|
||||
|
||||
<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 Documentation</a>
|
||||
<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" />
|
||||
@@ -49,195 +45,150 @@
|
||||
</div>
|
||||
|
||||
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
|
||||
<ul class="current">
|
||||
<ul class="current">
|
||||
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../..">Home</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../..">Home</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../design/index.html">Design</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../../usage/">Usage</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../usage/index.html">Usage</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Design</span>
|
||||
<ul class="subnav">
|
||||
<li><span>Algorithms</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 current">
|
||||
<a class="current" href="./index.html">DQN</a>
|
||||
|
||||
<ul>
|
||||
|
||||
<li class="toctree-l3"><a href="#deep-q-networks">Deep Q Networks</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#algorithm-description">Algorithm Description</a></li>
|
||||
|
||||
|
||||
</ul>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../double_dqn/index.html">Double DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../dueling_dqn/index.html">Dueling DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../categorical_dqn/index.html">Categorical DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../mmc/index.html">Mixed Monte Carlo</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../pal/index.html">Persistent Advantage Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../nec/index.html">Neural Episodic Control</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../bs_dqn/index.html">Bootstrapped DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../n_step/index.html">N-Step Q Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../naf/index.html">Normalized Advantage Functions</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/pg/index.html">Policy Gradient</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ac/index.html">Actor-Critic</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ddpg/index.html">Deep Determinstic Policy Gradients</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ppo/index.html">Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/cppo/index.html">Clipped Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../other/dfp/index.html">Direct Future Prediction</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../imitation/bc/index.html">Behavioral Cloning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
<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>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../dashboard/index.html">Coach Dashboard</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Algorithms</span>
|
||||
<ul class="subnav">
|
||||
<li class=" current">
|
||||
|
||||
<a class="current" href="./">DQN</a>
|
||||
<ul class="subnav">
|
||||
<li><span>Contributing</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../contributing/add_agent/index.html">Adding a New Agent</a>
|
||||
<li class="toctree-l3"><a href="#deep-q-networks">Deep Q Networks</a></li>
|
||||
|
||||
<ul>
|
||||
|
||||
</li>
|
||||
<li><a class="toctree-l4" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#algorithm-description">Algorithm Description</a></li>
|
||||
|
||||
</ul>
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../contributing/add_env/index.html">Adding a New Environment</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
</ul>
|
||||
<li>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../double_dqn/">Double DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../dueling_dqn/">Dueling DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../categorical_dqn/">Categorical DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../mmc/">Mixed Monte Carlo</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../pal/">Persistent Advantage Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../nec/">Neural Episodic Control</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../bs_dqn/">Bootstrapped DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../n_step/">N-Step Q Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../naf/">Normalized Advantage Functions</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/pg/">Policy Gradient</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ac/">Actor-Critic</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ddpg/">Deep Determinstic Policy Gradients</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ppo/">Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/cppo/">Clipped Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../other/dfp/">Direct Future Prediction</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../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="../../../contributing/add_agent/">Adding a New Agent</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../../contributing/add_env/">Adding a New Environment</a>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
</div>
|
||||
@@ -249,7 +200,7 @@
|
||||
|
||||
<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 Documentation</a>
|
||||
<a href="../../..">Reinforcement Learning Coach</a>
|
||||
</nav>
|
||||
|
||||
|
||||
@@ -307,10 +258,10 @@
|
||||
|
||||
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
|
||||
|
||||
<a href="../double_dqn/index.html" class="btn btn-neutral float-right" title="Double DQN"/>Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
<a href="../double_dqn/" class="btn btn-neutral float-right" title="Double DQN">Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
|
||||
|
||||
<a href="../../../usage/index.html" class="btn btn-neutral" title="Usage"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
<a href="../../../design/filters/" class="btn btn-neutral" title="Filters"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
|
||||
</div>
|
||||
|
||||
@@ -324,7 +275,7 @@
|
||||
|
||||
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>
|
||||
|
||||
@@ -332,17 +283,22 @@
|
||||
|
||||
</div>
|
||||
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<span class="rst-current-version" data-toggle="rst-current-version">
|
||||
|
||||
|
||||
<span><a href="../../../usage/index.html" style="color: #fcfcfc;">« Previous</a></span>
|
||||
<span><a href="../../../design/filters/" style="color: #fcfcfc;">« Previous</a></span>
|
||||
|
||||
|
||||
<span style="margin-left: 15px"><a href="../double_dqn/index.html" style="color: #fcfcfc">Next »</a></span>
|
||||
<span style="margin-left: 15px"><a href="../double_dqn/" 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>
|
||||
|
||||
@@ -3,33 +3,29 @@
|
||||
<!--[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">
|
||||
|
||||
<title>Dueling DQN - Reinforcement Learning Coach Documentation</title>
|
||||
|
||||
|
||||
<link rel="shortcut icon" href="../../../img/favicon.ico">
|
||||
|
||||
|
||||
<title>Dueling DQN - 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 = "Dueling DQN";
|
||||
var mkdocs_page_input_path = "algorithms/value_optimization/dueling_dqn.md";
|
||||
var mkdocs_page_url = "/algorithms/value_optimization/dueling_dqn/";
|
||||
</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>
|
||||
<script src="../../../js/theme.js"></script>
|
||||
<script src="https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS_HTML"></script>
|
||||
|
||||
<script type="text/javascript" src="../../../js/highlight.pack.js"></script>
|
||||
|
||||
</head>
|
||||
|
||||
@@ -40,7 +36,7 @@
|
||||
|
||||
<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 Documentation</a>
|
||||
<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" />
|
||||
@@ -49,195 +45,150 @@
|
||||
</div>
|
||||
|
||||
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
|
||||
<ul class="current">
|
||||
<ul class="current">
|
||||
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../..">Home</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../..">Home</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../design/index.html">Design</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../../usage/">Usage</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../usage/index.html">Usage</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Design</span>
|
||||
<ul class="subnav">
|
||||
<li><span>Algorithms</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../dqn/index.html">DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../double_dqn/index.html">Double DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 current">
|
||||
<a class="current" href="./index.html">Dueling DQN</a>
|
||||
|
||||
<ul>
|
||||
|
||||
<li class="toctree-l3"><a href="#dueling-dqn">Dueling DQN</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#general-description">General Description</a></li>
|
||||
|
||||
|
||||
</ul>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../categorical_dqn/index.html">Categorical DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../mmc/index.html">Mixed Monte Carlo</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../pal/index.html">Persistent Advantage Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../nec/index.html">Neural Episodic Control</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../bs_dqn/index.html">Bootstrapped DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../n_step/index.html">N-Step Q Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../naf/index.html">Normalized Advantage Functions</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/pg/index.html">Policy Gradient</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ac/index.html">Actor-Critic</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ddpg/index.html">Deep Determinstic Policy Gradients</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ppo/index.html">Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/cppo/index.html">Clipped Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../other/dfp/index.html">Direct Future Prediction</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../imitation/bc/index.html">Behavioral Cloning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
<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>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../dashboard/index.html">Coach Dashboard</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Algorithms</span>
|
||||
<ul class="subnav">
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../dqn/">DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../double_dqn/">Double DQN</a>
|
||||
</li>
|
||||
<li class=" current">
|
||||
|
||||
<a class="current" href="./">Dueling DQN</a>
|
||||
<ul class="subnav">
|
||||
<li><span>Contributing</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../contributing/add_agent/index.html">Adding a New Agent</a>
|
||||
<li class="toctree-l3"><a href="#dueling-dqn">Dueling DQN</a></li>
|
||||
|
||||
<ul>
|
||||
|
||||
</li>
|
||||
<li><a class="toctree-l4" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#general-description">General Description</a></li>
|
||||
|
||||
</ul>
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../contributing/add_env/index.html">Adding a New Environment</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
</ul>
|
||||
<li>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../categorical_dqn/">Categorical DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../mmc/">Mixed Monte Carlo</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../pal/">Persistent Advantage Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../nec/">Neural Episodic Control</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../bs_dqn/">Bootstrapped DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../n_step/">N-Step Q Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../naf/">Normalized Advantage Functions</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/pg/">Policy Gradient</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ac/">Actor-Critic</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ddpg/">Deep Determinstic Policy Gradients</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ppo/">Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/cppo/">Clipped Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../other/dfp/">Direct Future Prediction</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../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="../../../contributing/add_agent/">Adding a New Agent</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../../contributing/add_env/">Adding a New Environment</a>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
</div>
|
||||
@@ -249,7 +200,7 @@
|
||||
|
||||
<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 Documentation</a>
|
||||
<a href="../../..">Reinforcement Learning Coach</a>
|
||||
</nav>
|
||||
|
||||
|
||||
@@ -297,10 +248,10 @@ This is especially important in environments where there are many actions to cho
|
||||
|
||||
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
|
||||
|
||||
<a href="../categorical_dqn/index.html" class="btn btn-neutral float-right" title="Categorical DQN"/>Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
<a href="../categorical_dqn/" class="btn btn-neutral float-right" title="Categorical DQN">Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
|
||||
|
||||
<a href="../double_dqn/index.html" class="btn btn-neutral" title="Double DQN"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
<a href="../double_dqn/" class="btn btn-neutral" title="Double DQN"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
|
||||
</div>
|
||||
|
||||
@@ -314,7 +265,7 @@ This is especially important in environments where there are many actions to cho
|
||||
|
||||
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>
|
||||
|
||||
@@ -322,17 +273,22 @@ This is especially important in environments where there are many actions to cho
|
||||
|
||||
</div>
|
||||
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<span class="rst-current-version" data-toggle="rst-current-version">
|
||||
|
||||
|
||||
<span><a href="../double_dqn/index.html" style="color: #fcfcfc;">« Previous</a></span>
|
||||
<span><a href="../double_dqn/" style="color: #fcfcfc;">« Previous</a></span>
|
||||
|
||||
|
||||
<span style="margin-left: 15px"><a href="../categorical_dqn/index.html" style="color: #fcfcfc">Next »</a></span>
|
||||
<span style="margin-left: 15px"><a href="../categorical_dqn/" 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>
|
||||
|
||||
@@ -3,33 +3,29 @@
|
||||
<!--[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">
|
||||
|
||||
<title>Mixed Monte Carlo - Reinforcement Learning Coach Documentation</title>
|
||||
|
||||
|
||||
<link rel="shortcut icon" href="../../../img/favicon.ico">
|
||||
|
||||
|
||||
<title>Mixed Monte Carlo - 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 = "Mixed Monte Carlo";
|
||||
var mkdocs_page_input_path = "algorithms/value_optimization/mmc.md";
|
||||
var mkdocs_page_url = "/algorithms/value_optimization/mmc/";
|
||||
</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>
|
||||
<script src="../../../js/theme.js"></script>
|
||||
<script src="https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS_HTML"></script>
|
||||
|
||||
<script type="text/javascript" src="../../../js/highlight.pack.js"></script>
|
||||
|
||||
</head>
|
||||
|
||||
@@ -40,7 +36,7 @@
|
||||
|
||||
<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 Documentation</a>
|
||||
<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" />
|
||||
@@ -49,195 +45,150 @@
|
||||
</div>
|
||||
|
||||
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
|
||||
<ul class="current">
|
||||
<ul class="current">
|
||||
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../..">Home</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../..">Home</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../design/index.html">Design</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../../usage/">Usage</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../usage/index.html">Usage</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Design</span>
|
||||
<ul class="subnav">
|
||||
<li><span>Algorithms</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../dqn/index.html">DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../double_dqn/index.html">Double DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../dueling_dqn/index.html">Dueling DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../categorical_dqn/index.html">Categorical DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 current">
|
||||
<a class="current" href="./index.html">Mixed Monte Carlo</a>
|
||||
|
||||
<ul>
|
||||
|
||||
<li class="toctree-l3"><a href="#mixed-monte-carlo">Mixed Monte Carlo</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#algorithm-description">Algorithm Description</a></li>
|
||||
|
||||
|
||||
</ul>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../pal/index.html">Persistent Advantage Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../nec/index.html">Neural Episodic Control</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../bs_dqn/index.html">Bootstrapped DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../n_step/index.html">N-Step Q Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../naf/index.html">Normalized Advantage Functions</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/pg/index.html">Policy Gradient</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ac/index.html">Actor-Critic</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ddpg/index.html">Deep Determinstic Policy Gradients</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ppo/index.html">Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/cppo/index.html">Clipped Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../other/dfp/index.html">Direct Future Prediction</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../imitation/bc/index.html">Behavioral Cloning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
<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>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../dashboard/index.html">Coach Dashboard</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Algorithms</span>
|
||||
<ul class="subnav">
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../dqn/">DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../double_dqn/">Double DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../dueling_dqn/">Dueling DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../categorical_dqn/">Categorical DQN</a>
|
||||
</li>
|
||||
<li class=" current">
|
||||
|
||||
<a class="current" href="./">Mixed Monte Carlo</a>
|
||||
<ul class="subnav">
|
||||
<li><span>Contributing</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../contributing/add_agent/index.html">Adding a New Agent</a>
|
||||
<li class="toctree-l3"><a href="#mixed-monte-carlo">Mixed Monte Carlo</a></li>
|
||||
|
||||
<ul>
|
||||
|
||||
</li>
|
||||
<li><a class="toctree-l4" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#algorithm-description">Algorithm Description</a></li>
|
||||
|
||||
</ul>
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../contributing/add_env/index.html">Adding a New Environment</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
</ul>
|
||||
<li>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../pal/">Persistent Advantage Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../nec/">Neural Episodic Control</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../bs_dqn/">Bootstrapped DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../n_step/">N-Step Q Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../naf/">Normalized Advantage Functions</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/pg/">Policy Gradient</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ac/">Actor-Critic</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ddpg/">Deep Determinstic Policy Gradients</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ppo/">Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/cppo/">Clipped Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../other/dfp/">Direct Future Prediction</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../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="../../../contributing/add_agent/">Adding a New Agent</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../../contributing/add_env/">Adding a New Environment</a>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
</div>
|
||||
@@ -249,7 +200,7 @@
|
||||
|
||||
<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 Documentation</a>
|
||||
<a href="../../..">Reinforcement Learning Coach</a>
|
||||
</nav>
|
||||
|
||||
|
||||
@@ -309,10 +260,10 @@ Once in every few thousand steps, copy the weights from the online network to th
|
||||
|
||||
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
|
||||
|
||||
<a href="../pal/index.html" class="btn btn-neutral float-right" title="Persistent Advantage Learning"/>Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
<a href="../pal/" class="btn btn-neutral float-right" title="Persistent Advantage Learning">Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
|
||||
|
||||
<a href="../categorical_dqn/index.html" class="btn btn-neutral" title="Categorical DQN"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
<a href="../categorical_dqn/" class="btn btn-neutral" title="Categorical DQN"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
|
||||
</div>
|
||||
|
||||
@@ -326,7 +277,7 @@ Once in every few thousand steps, copy the weights from the online network to th
|
||||
|
||||
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>
|
||||
|
||||
@@ -334,17 +285,22 @@ Once in every few thousand steps, copy the weights from the online network to th
|
||||
|
||||
</div>
|
||||
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<span class="rst-current-version" data-toggle="rst-current-version">
|
||||
|
||||
|
||||
<span><a href="../categorical_dqn/index.html" style="color: #fcfcfc;">« Previous</a></span>
|
||||
<span><a href="../categorical_dqn/" style="color: #fcfcfc;">« Previous</a></span>
|
||||
|
||||
|
||||
<span style="margin-left: 15px"><a href="../pal/index.html" style="color: #fcfcfc">Next »</a></span>
|
||||
<span style="margin-left: 15px"><a href="../pal/" 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>
|
||||
|
||||
@@ -3,33 +3,29 @@
|
||||
<!--[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">
|
||||
|
||||
<title>N-Step Q Learning - Reinforcement Learning Coach Documentation</title>
|
||||
|
||||
|
||||
<link rel="shortcut icon" href="../../../img/favicon.ico">
|
||||
|
||||
|
||||
<title>N-Step Q Learning - 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 = "N-Step Q Learning";
|
||||
var mkdocs_page_input_path = "algorithms/value_optimization/n_step.md";
|
||||
var mkdocs_page_url = "/algorithms/value_optimization/n_step/";
|
||||
</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>
|
||||
<script src="../../../js/theme.js"></script>
|
||||
<script src="https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS_HTML"></script>
|
||||
|
||||
<script type="text/javascript" src="../../../js/highlight.pack.js"></script>
|
||||
|
||||
</head>
|
||||
|
||||
@@ -40,7 +36,7 @@
|
||||
|
||||
<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 Documentation</a>
|
||||
<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" />
|
||||
@@ -49,195 +45,150 @@
|
||||
</div>
|
||||
|
||||
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
|
||||
<ul class="current">
|
||||
<ul class="current">
|
||||
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../..">Home</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../..">Home</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../design/index.html">Design</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../../usage/">Usage</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../usage/index.html">Usage</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Design</span>
|
||||
<ul class="subnav">
|
||||
<li><span>Algorithms</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../dqn/index.html">DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../double_dqn/index.html">Double DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../dueling_dqn/index.html">Dueling DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../categorical_dqn/index.html">Categorical DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../mmc/index.html">Mixed Monte Carlo</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../pal/index.html">Persistent Advantage Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../nec/index.html">Neural Episodic Control</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../bs_dqn/index.html">Bootstrapped DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 current">
|
||||
<a class="current" href="./index.html">N-Step Q Learning</a>
|
||||
|
||||
<ul>
|
||||
|
||||
<li class="toctree-l3"><a href="#n-step-q-learning">N-Step Q Learning</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#algorithm-description">Algorithm Description</a></li>
|
||||
|
||||
|
||||
</ul>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../naf/index.html">Normalized Advantage Functions</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/pg/index.html">Policy Gradient</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ac/index.html">Actor-Critic</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ddpg/index.html">Deep Determinstic Policy Gradients</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ppo/index.html">Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/cppo/index.html">Clipped Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../other/dfp/index.html">Direct Future Prediction</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../imitation/bc/index.html">Behavioral Cloning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
<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>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../dashboard/index.html">Coach Dashboard</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Algorithms</span>
|
||||
<ul class="subnav">
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../dqn/">DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../double_dqn/">Double DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../dueling_dqn/">Dueling DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../categorical_dqn/">Categorical DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../mmc/">Mixed Monte Carlo</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../pal/">Persistent Advantage Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../nec/">Neural Episodic Control</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../bs_dqn/">Bootstrapped DQN</a>
|
||||
</li>
|
||||
<li class=" current">
|
||||
|
||||
<a class="current" href="./">N-Step Q Learning</a>
|
||||
<ul class="subnav">
|
||||
<li><span>Contributing</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../contributing/add_agent/index.html">Adding a New Agent</a>
|
||||
<li class="toctree-l3"><a href="#n-step-q-learning">N-Step Q Learning</a></li>
|
||||
|
||||
<ul>
|
||||
|
||||
</li>
|
||||
<li><a class="toctree-l4" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#algorithm-description">Algorithm Description</a></li>
|
||||
|
||||
</ul>
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../contributing/add_env/index.html">Adding a New Environment</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
</ul>
|
||||
<li>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../naf/">Normalized Advantage Functions</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/pg/">Policy Gradient</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ac/">Actor-Critic</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ddpg/">Deep Determinstic Policy Gradients</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ppo/">Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/cppo/">Clipped Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../other/dfp/">Direct Future Prediction</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../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="../../../contributing/add_agent/">Adding a New Agent</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../../contributing/add_env/">Adding a New Environment</a>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
</div>
|
||||
@@ -249,7 +200,7 @@
|
||||
|
||||
<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 Documentation</a>
|
||||
<a href="../../..">Reinforcement Learning Coach</a>
|
||||
</nav>
|
||||
|
||||
|
||||
@@ -308,10 +259,10 @@ where <script type="math/tex">k</script> is <script type="math/tex">T_{max} - St
|
||||
|
||||
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
|
||||
|
||||
<a href="../naf/index.html" class="btn btn-neutral float-right" title="Normalized Advantage Functions"/>Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
<a href="../naf/" class="btn btn-neutral float-right" title="Normalized Advantage Functions">Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
|
||||
|
||||
<a href="../bs_dqn/index.html" class="btn btn-neutral" title="Bootstrapped DQN"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
<a href="../bs_dqn/" class="btn btn-neutral" title="Bootstrapped DQN"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
|
||||
</div>
|
||||
|
||||
@@ -325,7 +276,7 @@ where <script type="math/tex">k</script> is <script type="math/tex">T_{max} - St
|
||||
|
||||
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>
|
||||
|
||||
@@ -333,17 +284,22 @@ where <script type="math/tex">k</script> is <script type="math/tex">T_{max} - St
|
||||
|
||||
</div>
|
||||
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<span class="rst-current-version" data-toggle="rst-current-version">
|
||||
|
||||
|
||||
<span><a href="../bs_dqn/index.html" style="color: #fcfcfc;">« Previous</a></span>
|
||||
<span><a href="../bs_dqn/" style="color: #fcfcfc;">« Previous</a></span>
|
||||
|
||||
|
||||
<span style="margin-left: 15px"><a href="../naf/index.html" style="color: #fcfcfc">Next »</a></span>
|
||||
<span style="margin-left: 15px"><a href="../naf/" 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>
|
||||
|
||||
@@ -3,33 +3,29 @@
|
||||
<!--[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">
|
||||
|
||||
<title>Normalized Advantage Functions - Reinforcement Learning Coach Documentation</title>
|
||||
|
||||
|
||||
<link rel="shortcut icon" href="../../../img/favicon.ico">
|
||||
|
||||
|
||||
<title>Normalized Advantage Functions - 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 = "Normalized Advantage Functions";
|
||||
var mkdocs_page_input_path = "algorithms/value_optimization/naf.md";
|
||||
var mkdocs_page_url = "/algorithms/value_optimization/naf/";
|
||||
</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>
|
||||
<script src="../../../js/theme.js"></script>
|
||||
<script src="https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS_HTML"></script>
|
||||
|
||||
<script type="text/javascript" src="../../../js/highlight.pack.js"></script>
|
||||
|
||||
</head>
|
||||
|
||||
@@ -40,7 +36,7 @@
|
||||
|
||||
<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 Documentation</a>
|
||||
<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" />
|
||||
@@ -49,195 +45,150 @@
|
||||
</div>
|
||||
|
||||
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
|
||||
<ul class="current">
|
||||
<ul class="current">
|
||||
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../..">Home</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../..">Home</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../design/index.html">Design</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../../usage/">Usage</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../usage/index.html">Usage</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Design</span>
|
||||
<ul class="subnav">
|
||||
<li><span>Algorithms</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../dqn/index.html">DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../double_dqn/index.html">Double DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../dueling_dqn/index.html">Dueling DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../categorical_dqn/index.html">Categorical DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../mmc/index.html">Mixed Monte Carlo</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../pal/index.html">Persistent Advantage Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../nec/index.html">Neural Episodic Control</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../bs_dqn/index.html">Bootstrapped DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../n_step/index.html">N-Step Q Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 current">
|
||||
<a class="current" href="./index.html">Normalized Advantage Functions</a>
|
||||
|
||||
<ul>
|
||||
|
||||
<li class="toctree-l3"><a href="#normalized-advantage-functions">Normalized Advantage Functions</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#algorithm-description">Algorithm Description</a></li>
|
||||
|
||||
|
||||
</ul>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/pg/index.html">Policy Gradient</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ac/index.html">Actor-Critic</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ddpg/index.html">Deep Determinstic Policy Gradients</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ppo/index.html">Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/cppo/index.html">Clipped Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../other/dfp/index.html">Direct Future Prediction</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../imitation/bc/index.html">Behavioral Cloning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
<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>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../dashboard/index.html">Coach Dashboard</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Algorithms</span>
|
||||
<ul class="subnav">
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../dqn/">DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../double_dqn/">Double DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../dueling_dqn/">Dueling DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../categorical_dqn/">Categorical DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../mmc/">Mixed Monte Carlo</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../pal/">Persistent Advantage Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../nec/">Neural Episodic Control</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../bs_dqn/">Bootstrapped DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../n_step/">N-Step Q Learning</a>
|
||||
</li>
|
||||
<li class=" current">
|
||||
|
||||
<a class="current" href="./">Normalized Advantage Functions</a>
|
||||
<ul class="subnav">
|
||||
<li><span>Contributing</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../contributing/add_agent/index.html">Adding a New Agent</a>
|
||||
<li class="toctree-l3"><a href="#normalized-advantage-functions">Normalized Advantage Functions</a></li>
|
||||
|
||||
<ul>
|
||||
|
||||
</li>
|
||||
<li><a class="toctree-l4" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#algorithm-description">Algorithm Description</a></li>
|
||||
|
||||
</ul>
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../contributing/add_env/index.html">Adding a New Environment</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
</ul>
|
||||
<li>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/pg/">Policy Gradient</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ac/">Actor-Critic</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ddpg/">Deep Determinstic Policy Gradients</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ppo/">Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/cppo/">Clipped Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../other/dfp/">Direct Future Prediction</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../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="../../../contributing/add_agent/">Adding a New Agent</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../../contributing/add_env/">Adding a New Environment</a>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
</div>
|
||||
@@ -249,7 +200,7 @@
|
||||
|
||||
<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 Documentation</a>
|
||||
<a href="../../..">Reinforcement Learning Coach</a>
|
||||
</nav>
|
||||
|
||||
|
||||
@@ -300,10 +251,10 @@ After every training step, use a soft update in order to copy the weights from t
|
||||
|
||||
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
|
||||
|
||||
<a href="../../policy_optimization/pg/index.html" class="btn btn-neutral float-right" title="Policy Gradient"/>Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
<a href="../../policy_optimization/pg/" class="btn btn-neutral float-right" title="Policy Gradient">Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
|
||||
|
||||
<a href="../n_step/index.html" class="btn btn-neutral" title="N-Step Q Learning"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
<a href="../n_step/" class="btn btn-neutral" title="N-Step Q Learning"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
|
||||
</div>
|
||||
|
||||
@@ -317,7 +268,7 @@ After every training step, use a soft update in order to copy the weights from t
|
||||
|
||||
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>
|
||||
|
||||
@@ -325,17 +276,22 @@ After every training step, use a soft update in order to copy the weights from t
|
||||
|
||||
</div>
|
||||
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<span class="rst-current-version" data-toggle="rst-current-version">
|
||||
|
||||
|
||||
<span><a href="../n_step/index.html" style="color: #fcfcfc;">« Previous</a></span>
|
||||
<span><a href="../n_step/" style="color: #fcfcfc;">« Previous</a></span>
|
||||
|
||||
|
||||
<span style="margin-left: 15px"><a href="../../policy_optimization/pg/index.html" style="color: #fcfcfc">Next »</a></span>
|
||||
<span style="margin-left: 15px"><a href="../../policy_optimization/pg/" 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>
|
||||
|
||||
@@ -3,33 +3,29 @@
|
||||
<!--[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">
|
||||
|
||||
<title>Neural Episodic Control - Reinforcement Learning Coach Documentation</title>
|
||||
|
||||
|
||||
<link rel="shortcut icon" href="../../../img/favicon.ico">
|
||||
|
||||
|
||||
<title>Neural Episodic Control - 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 = "Neural Episodic Control";
|
||||
var mkdocs_page_input_path = "algorithms/value_optimization/nec.md";
|
||||
var mkdocs_page_url = "/algorithms/value_optimization/nec/";
|
||||
</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>
|
||||
<script src="../../../js/theme.js"></script>
|
||||
<script src="https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS_HTML"></script>
|
||||
|
||||
<script type="text/javascript" src="../../../js/highlight.pack.js"></script>
|
||||
|
||||
</head>
|
||||
|
||||
@@ -40,7 +36,7 @@
|
||||
|
||||
<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 Documentation</a>
|
||||
<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" />
|
||||
@@ -49,195 +45,150 @@
|
||||
</div>
|
||||
|
||||
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
|
||||
<ul class="current">
|
||||
<ul class="current">
|
||||
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../..">Home</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../..">Home</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../design/index.html">Design</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../../usage/">Usage</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../usage/index.html">Usage</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Design</span>
|
||||
<ul class="subnav">
|
||||
<li><span>Algorithms</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../dqn/index.html">DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../double_dqn/index.html">Double DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../dueling_dqn/index.html">Dueling DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../categorical_dqn/index.html">Categorical DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../mmc/index.html">Mixed Monte Carlo</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../pal/index.html">Persistent Advantage Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 current">
|
||||
<a class="current" href="./index.html">Neural Episodic Control</a>
|
||||
|
||||
<ul>
|
||||
|
||||
<li class="toctree-l3"><a href="#neural-episodic-control">Neural Episodic Control</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#algorithm-description">Algorithm Description</a></li>
|
||||
|
||||
|
||||
</ul>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../bs_dqn/index.html">Bootstrapped DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../n_step/index.html">N-Step Q Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../naf/index.html">Normalized Advantage Functions</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/pg/index.html">Policy Gradient</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ac/index.html">Actor-Critic</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ddpg/index.html">Deep Determinstic Policy Gradients</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ppo/index.html">Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/cppo/index.html">Clipped Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../other/dfp/index.html">Direct Future Prediction</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../imitation/bc/index.html">Behavioral Cloning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
<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>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../dashboard/index.html">Coach Dashboard</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Algorithms</span>
|
||||
<ul class="subnav">
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../dqn/">DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../double_dqn/">Double DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../dueling_dqn/">Dueling DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../categorical_dqn/">Categorical DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../mmc/">Mixed Monte Carlo</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../pal/">Persistent Advantage Learning</a>
|
||||
</li>
|
||||
<li class=" current">
|
||||
|
||||
<a class="current" href="./">Neural Episodic Control</a>
|
||||
<ul class="subnav">
|
||||
<li><span>Contributing</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../contributing/add_agent/index.html">Adding a New Agent</a>
|
||||
<li class="toctree-l3"><a href="#neural-episodic-control">Neural Episodic Control</a></li>
|
||||
|
||||
<ul>
|
||||
|
||||
</li>
|
||||
<li><a class="toctree-l4" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#algorithm-description">Algorithm Description</a></li>
|
||||
|
||||
</ul>
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../contributing/add_env/index.html">Adding a New Environment</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
</ul>
|
||||
<li>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../bs_dqn/">Bootstrapped DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../n_step/">N-Step Q Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../naf/">Normalized Advantage Functions</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/pg/">Policy Gradient</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ac/">Actor-Critic</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ddpg/">Deep Determinstic Policy Gradients</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ppo/">Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/cppo/">Clipped Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../other/dfp/">Direct Future Prediction</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../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="../../../contributing/add_agent/">Adding a New Agent</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../../contributing/add_env/">Adding a New Environment</a>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
</div>
|
||||
@@ -249,7 +200,7 @@
|
||||
|
||||
<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 Documentation</a>
|
||||
<a href="../../..">Reinforcement Learning Coach</a>
|
||||
</nav>
|
||||
|
||||
|
||||
@@ -307,10 +258,10 @@
|
||||
|
||||
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
|
||||
|
||||
<a href="../bs_dqn/index.html" class="btn btn-neutral float-right" title="Bootstrapped DQN"/>Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
<a href="../bs_dqn/" class="btn btn-neutral float-right" title="Bootstrapped DQN">Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
|
||||
|
||||
<a href="../pal/index.html" class="btn btn-neutral" title="Persistent Advantage Learning"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
<a href="../pal/" class="btn btn-neutral" title="Persistent Advantage Learning"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
|
||||
</div>
|
||||
|
||||
@@ -324,7 +275,7 @@
|
||||
|
||||
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>
|
||||
|
||||
@@ -332,17 +283,22 @@
|
||||
|
||||
</div>
|
||||
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<span class="rst-current-version" data-toggle="rst-current-version">
|
||||
|
||||
|
||||
<span><a href="../pal/index.html" style="color: #fcfcfc;">« Previous</a></span>
|
||||
<span><a href="../pal/" style="color: #fcfcfc;">« Previous</a></span>
|
||||
|
||||
|
||||
<span style="margin-left: 15px"><a href="../bs_dqn/index.html" style="color: #fcfcfc">Next »</a></span>
|
||||
<span style="margin-left: 15px"><a href="../bs_dqn/" 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>
|
||||
|
||||
@@ -3,33 +3,29 @@
|
||||
<!--[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">
|
||||
|
||||
<title>Persistent Advantage Learning - Reinforcement Learning Coach Documentation</title>
|
||||
|
||||
|
||||
<link rel="shortcut icon" href="../../../img/favicon.ico">
|
||||
|
||||
|
||||
<title>Persistent Advantage Learning - 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 = "Persistent Advantage Learning";
|
||||
var mkdocs_page_input_path = "algorithms/value_optimization/pal.md";
|
||||
var mkdocs_page_url = "/algorithms/value_optimization/pal/";
|
||||
</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>
|
||||
<script src="../../../js/theme.js"></script>
|
||||
<script src="https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS_HTML"></script>
|
||||
|
||||
<script type="text/javascript" src="../../../js/highlight.pack.js"></script>
|
||||
|
||||
</head>
|
||||
|
||||
@@ -40,7 +36,7 @@
|
||||
|
||||
<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 Documentation</a>
|
||||
<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" />
|
||||
@@ -49,195 +45,150 @@
|
||||
</div>
|
||||
|
||||
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
|
||||
<ul class="current">
|
||||
<ul class="current">
|
||||
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../..">Home</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../..">Home</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../design/index.html">Design</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="../../../usage/">Usage</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../usage/index.html">Usage</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Design</span>
|
||||
<ul class="subnav">
|
||||
<li><span>Algorithms</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../dqn/index.html">DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../double_dqn/index.html">Double DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../dueling_dqn/index.html">Dueling DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../categorical_dqn/index.html">Categorical DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../mmc/index.html">Mixed Monte Carlo</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 current">
|
||||
<a class="current" href="./index.html">Persistent Advantage Learning</a>
|
||||
|
||||
<ul>
|
||||
|
||||
<li class="toctree-l3"><a href="#persistent-advantage-learning">Persistent Advantage Learning</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#algorithm-description">Algorithm Description</a></li>
|
||||
|
||||
|
||||
</ul>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../nec/index.html">Neural Episodic Control</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../bs_dqn/index.html">Bootstrapped DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../n_step/index.html">N-Step Q Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../naf/index.html">Normalized Advantage Functions</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/pg/index.html">Policy Gradient</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ac/index.html">Actor-Critic</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ddpg/index.html">Deep Determinstic Policy Gradients</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/ppo/index.html">Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../policy_optimization/cppo/index.html">Clipped Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../other/dfp/index.html">Direct Future Prediction</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../imitation/bc/index.html">Behavioral Cloning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
<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>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../dashboard/index.html">Coach Dashboard</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Algorithms</span>
|
||||
<ul class="subnav">
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../dqn/">DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../double_dqn/">Double DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../dueling_dqn/">Dueling DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../categorical_dqn/">Categorical DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../mmc/">Mixed Monte Carlo</a>
|
||||
</li>
|
||||
<li class=" current">
|
||||
|
||||
<a class="current" href="./">Persistent Advantage Learning</a>
|
||||
<ul class="subnav">
|
||||
<li><span>Contributing</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../contributing/add_agent/index.html">Adding a New Agent</a>
|
||||
<li class="toctree-l3"><a href="#persistent-advantage-learning">Persistent Advantage Learning</a></li>
|
||||
|
||||
<ul>
|
||||
|
||||
</li>
|
||||
<li><a class="toctree-l4" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#algorithm-description">Algorithm Description</a></li>
|
||||
|
||||
</ul>
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="../../../contributing/add_env/index.html">Adding a New Environment</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
</ul>
|
||||
<li>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../nec/">Neural Episodic Control</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../bs_dqn/">Bootstrapped DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../n_step/">N-Step Q Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../naf/">Normalized Advantage Functions</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/pg/">Policy Gradient</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ac/">Actor-Critic</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ddpg/">Deep Determinstic Policy Gradients</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/ppo/">Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../policy_optimization/cppo/">Clipped Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../other/dfp/">Direct Future Prediction</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../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="../../../contributing/add_agent/">Adding a New Agent</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="../../../contributing/add_env/">Adding a New Environment</a>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
</div>
|
||||
@@ -249,7 +200,7 @@
|
||||
|
||||
<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 Documentation</a>
|
||||
<a href="../../..">Reinforcement Learning Coach</a>
|
||||
</nav>
|
||||
|
||||
|
||||
@@ -321,10 +272,10 @@
|
||||
|
||||
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
|
||||
|
||||
<a href="../nec/index.html" class="btn btn-neutral float-right" title="Neural Episodic Control"/>Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
<a href="../nec/" class="btn btn-neutral float-right" title="Neural Episodic Control">Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
|
||||
|
||||
<a href="../mmc/index.html" class="btn btn-neutral" title="Mixed Monte Carlo"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
<a href="../mmc/" class="btn btn-neutral" title="Mixed Monte Carlo"><span class="icon icon-circle-arrow-left"></span> Previous</a>
|
||||
|
||||
</div>
|
||||
|
||||
@@ -338,7 +289,7 @@
|
||||
|
||||
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>
|
||||
|
||||
@@ -346,17 +297,22 @@
|
||||
|
||||
</div>
|
||||
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<div class="rst-versions" role="note" style="cursor: pointer">
|
||||
<span class="rst-current-version" data-toggle="rst-current-version">
|
||||
|
||||
|
||||
<span><a href="../mmc/index.html" style="color: #fcfcfc;">« Previous</a></span>
|
||||
<span><a href="../mmc/" style="color: #fcfcfc;">« Previous</a></span>
|
||||
|
||||
|
||||
<span style="margin-left: 15px"><a href="../nec/index.html" style="color: #fcfcfc">Next »</a></span>
|
||||
<span style="margin-left: 15px"><a href="../nec/" 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>
|
||||
|
||||
Reference in New Issue
Block a user