mirror of
https://github.com/gryf/coach.git
synced 2025-12-18 11:40:18 +01:00
pre-release 0.10.0
This commit is contained in:
Gal Novik
360
docs/index.html
360
docs/index.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">
|
||||
<meta name="description" content="Reinforcement Learning Coach by Intel Nervana.">
|
||||
|
||||
<title>Reinforcement Learning Coach Documentation</title>
|
||||
|
||||
|
||||
<link rel="shortcut icon" href="./img/favicon.ico">
|
||||
|
||||
|
||||
<title>Home - 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 = "None";
|
||||
var mkdocs_page_name = "Home";
|
||||
var mkdocs_page_input_path = "index.md";
|
||||
var mkdocs_page_url = "/";
|
||||
</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="./index.html" 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" />
|
||||
@@ -49,197 +45,152 @@
|
||||
</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 current">
|
||||
<a class="current" href="./index.html">Home</a>
|
||||
|
||||
<ul>
|
||||
|
||||
<li class="toctree-l3"><a href="#what-is-coach">What is Coach?</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#motivation">Motivation</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#solution">Solution</a></li>
|
||||
|
||||
<li><a class="toctree-l4" href="#design">Design</a></li>
|
||||
|
||||
|
||||
</ul>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="design/index.html">Design</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="usage/index.html">Usage</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 current">
|
||||
|
||||
<a class="current" href=".">Home</a>
|
||||
<ul class="subnav">
|
||||
<li><span>Algorithms</span></li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="algorithms/value_optimization/dqn/index.html">DQN</a>
|
||||
<li class="toctree-l2"><a href="#what-is-coach">What is Coach?</a></li>
|
||||
|
||||
<ul>
|
||||
|
||||
</li>
|
||||
<li><a class="toctree-l3" href="#motivation">Motivation</a></li>
|
||||
|
||||
<li><a class="toctree-l3" href="#solution">Solution</a></li>
|
||||
|
||||
<li><a class="toctree-l3" href="#design">Design</a></li>
|
||||
|
||||
</ul>
|
||||
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="algorithms/value_optimization/double_dqn/index.html">Double DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="algorithms/value_optimization/dueling_dqn/index.html">Dueling DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="algorithms/value_optimization/categorical_dqn/index.html">Categorical DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="algorithms/value_optimization/mmc/index.html">Mixed Monte Carlo</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="algorithms/value_optimization/pal/index.html">Persistent Advantage Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="algorithms/value_optimization/nec/index.html">Neural Episodic Control</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="algorithms/value_optimization/bs_dqn/index.html">Bootstrapped DQN</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="algorithms/value_optimization/n_step/index.html">N-Step Q Learning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="algorithms/value_optimization/naf/index.html">Normalized Advantage Functions</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="algorithms/policy_optimization/pg/index.html">Policy Gradient</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="algorithms/policy_optimization/ac/index.html">Actor-Critic</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="algorithms/policy_optimization/ddpg/index.html">Deep Determinstic Policy Gradients</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="algorithms/policy_optimization/ppo/index.html">Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="algorithms/policy_optimization/cppo/index.html">Clipped Proximal Policy Optimization</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="algorithms/other/dfp/index.html">Direct Future Prediction</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="algorithms/imitation/bc/index.html">Behavioral Cloning</a>
|
||||
|
||||
</li>
|
||||
|
||||
|
||||
</ul>
|
||||
<li>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="dashboard/index.html">Coach Dashboard</a>
|
||||
|
||||
</li>
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="usage/">Usage</a>
|
||||
</li>
|
||||
|
||||
<li>
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Design</span>
|
||||
<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>
|
||||
|
||||
|
||||
|
||||
<li class="toctree-l1 ">
|
||||
<a class="" href="contributing/add_env/index.html">Adding a New Environment</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 class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Algorithms</span>
|
||||
<ul class="subnav">
|
||||
<li class="">
|
||||
|
||||
<a class="" href="algorithms/value_optimization/dqn/">DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="algorithms/value_optimization/double_dqn/">Double DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="algorithms/value_optimization/dueling_dqn/">Dueling DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="algorithms/value_optimization/categorical_dqn/">Categorical DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="algorithms/value_optimization/mmc/">Mixed Monte Carlo</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="algorithms/value_optimization/pal/">Persistent Advantage Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="algorithms/value_optimization/nec/">Neural Episodic Control</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="algorithms/value_optimization/bs_dqn/">Bootstrapped DQN</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="algorithms/value_optimization/n_step/">N-Step Q Learning</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="algorithms/value_optimization/naf/">Normalized Advantage Functions</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="algorithms/policy_optimization/pg/">Policy Gradient</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="algorithms/policy_optimization/ac/">Actor-Critic</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="algorithms/policy_optimization/ddpg/">Deep Determinstic Policy Gradients</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="algorithms/policy_optimization/ppo/">Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="algorithms/policy_optimization/cppo/">Clipped Proximal Policy Optimization</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="algorithms/other/dfp/">Direct Future Prediction</a>
|
||||
</li>
|
||||
<li class="">
|
||||
|
||||
<a class="" href="algorithms/imitation/bc/">Behavioral Cloning</a>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
|
||||
<li class="toctree-l1">
|
||||
|
||||
<a class="" href="dashboard/">Coach Dashboard</a>
|
||||
</li>
|
||||
|
||||
<li class="toctree-l1">
|
||||
|
||||
<span class="caption-text">Contributing</span>
|
||||
<ul class="subnav">
|
||||
<li class="">
|
||||
|
||||
<a class="" href="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>
|
||||
@@ -251,7 +202,7 @@
|
||||
|
||||
<nav class="wy-nav-top" role="navigation" aria-label="top navigation">
|
||||
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
|
||||
<a href="./index.html">Reinforcement Learning Coach Documentation</a>
|
||||
<a href=".">Reinforcement Learning Coach</a>
|
||||
</nav>
|
||||
|
||||
|
||||
@@ -259,7 +210,7 @@
|
||||
<div class="rst-content">
|
||||
<div role="navigation" aria-label="breadcrumbs navigation">
|
||||
<ul class="wy-breadcrumbs">
|
||||
<li><a href="./index.html">Docs</a> »</li>
|
||||
<li><a href=".">Docs</a> »</li>
|
||||
|
||||
|
||||
|
||||
@@ -281,7 +232,7 @@
|
||||
With Coach, it is possible to model an agent by combining various building blocks, and training the agent on multiple environments.
|
||||
The available environments allow testing the agent in different practical fields such as robotics, autonomous driving, games and more.
|
||||
Coach collects statistics from the training process and supports advanced visualization techniques for debugging the agent being trained.</p>
|
||||
<p>Blog post from the Intel® Nervana™ website can be found <a href="https://www.intelnervana.com/reinforcement-learning-coach-intel">here</a>. </p>
|
||||
<p>Blog post from the Intel® AI website can be found <a href="https://ai.intel.com/reinforcement-learning-coach-intel/">here</a>.</p>
|
||||
<p>GitHub repository is <a href="https://github.com/NervanaSystems/coach">here</a>. </p>
|
||||
<h2 id="design">Design</h2>
|
||||
<p><img src="img/design.png" alt="Coach Design" style="width: 800px;"/></p>
|
||||
@@ -292,7 +243,7 @@ Coach collects statistics from the training process and supports advanced visual
|
||||
|
||||
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
|
||||
|
||||
<a href="design/index.html" class="btn btn-neutral float-right" title="Design"/>Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
<a href="usage/" class="btn btn-neutral float-right" title="Usage">Next <span class="icon icon-circle-arrow-right"></span></a>
|
||||
|
||||
|
||||
</div>
|
||||
@@ -307,7 +258,7 @@ Coach collects statistics from the training process and supports advanced visual
|
||||
|
||||
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>
|
||||
|
||||
@@ -315,20 +266,25 @@ Coach collects statistics from the training process and supports advanced visual
|
||||
|
||||
</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 style="margin-left: 15px"><a href="design/index.html" style="color: #fcfcfc">Next »</a></span>
|
||||
<span style="margin-left: 15px"><a href="usage/" 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>
|
||||
|
||||
<!--
|
||||
MkDocs version : 0.14.0
|
||||
Build Date UTC : 2017-12-18 18:59:45.506407
|
||||
MkDocs version : 0.17.5
|
||||
Build Date UTC : 2018-08-09 12:14:19
|
||||
-->
|
||||
|
||||
Reference in New Issue
Block a user