mirror of
https://github.com/gryf/coach.git
synced 2025-12-17 19:20:19 +01:00
264 lines
9.6 KiB
HTML
264 lines
9.6 KiB
HTML
|
|
|
|
<!DOCTYPE html>
|
|
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
|
|
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
|
|
<head>
|
|
<meta charset="utf-8">
|
|
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
|
|
|
<title>Benchmarks — Reinforcement Learning Coach 0.12.0 documentation</title>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<script type="text/javascript" src="../_static/js/modernizr.min.js"></script>
|
|
|
|
|
|
<script type="text/javascript" id="documentation_options" data-url_root="../" src="../_static/documentation_options.js"></script>
|
|
<script type="text/javascript" src="../_static/jquery.js"></script>
|
|
<script type="text/javascript" src="../_static/underscore.js"></script>
|
|
<script type="text/javascript" src="../_static/doctools.js"></script>
|
|
<script type="text/javascript" src="../_static/language_data.js"></script>
|
|
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
|
|
|
|
<script type="text/javascript" src="../_static/js/theme.js"></script>
|
|
|
|
|
|
|
|
|
|
<link rel="stylesheet" href="../_static/css/theme.css" type="text/css" />
|
|
<link rel="stylesheet" href="../_static/pygments.css" type="text/css" />
|
|
<link rel="stylesheet" href="../_static/css/custom.css" type="text/css" />
|
|
<link rel="index" title="Index" href="../genindex.html" />
|
|
<link rel="search" title="Search" href="../search.html" />
|
|
<link rel="next" title="Selecting an Algorithm" href="../selecting_an_algorithm.html" />
|
|
<link rel="prev" title="Environments" href="environments.html" />
|
|
<link href="../_static/css/custom.css" rel="stylesheet" type="text/css">
|
|
|
|
</head>
|
|
|
|
<body class="wy-body-for-nav">
|
|
|
|
|
|
<div class="wy-grid-for-nav">
|
|
|
|
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
|
|
<div class="wy-side-scroll">
|
|
<div class="wy-side-nav-search" >
|
|
|
|
|
|
|
|
<a href="../index.html" class="icon icon-home"> Reinforcement Learning Coach
|
|
|
|
|
|
|
|
|
|
<img src="../_static/dark_logo.png" class="logo" alt="Logo"/>
|
|
|
|
</a>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<div role="search">
|
|
<form id="rtd-search-form" class="wy-form" action="../search.html" method="get">
|
|
<input type="text" name="q" placeholder="Search docs" />
|
|
<input type="hidden" name="check_keywords" value="yes" />
|
|
<input type="hidden" name="area" value="default" />
|
|
</form>
|
|
</div>
|
|
|
|
|
|
</div>
|
|
|
|
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<p class="caption"><span class="caption-text">Intro</span></p>
|
|
<ul class="current">
|
|
<li class="toctree-l1"><a class="reference internal" href="../usage.html">Usage</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../dist_usage.html">Usage - Distributed Coach</a></li>
|
|
<li class="toctree-l1 current"><a class="reference internal" href="index.html">Features</a><ul class="current">
|
|
<li class="toctree-l2"><a class="reference internal" href="algorithms.html">Algorithms</a></li>
|
|
<li class="toctree-l2"><a class="reference internal" href="environments.html">Environments</a></li>
|
|
<li class="toctree-l2 current"><a class="current reference internal" href="#">Benchmarks</a></li>
|
|
</ul>
|
|
</li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../selecting_an_algorithm.html">Selecting an Algorithm</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../dashboard.html">Coach Dashboard</a></li>
|
|
</ul>
|
|
<p class="caption"><span class="caption-text">Design</span></p>
|
|
<ul>
|
|
<li class="toctree-l1"><a class="reference internal" href="../design/control_flow.html">Control Flow</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../design/network.html">Network Design</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../design/horizontal_scaling.html">Distributed Coach - Horizontal Scale-Out</a></li>
|
|
</ul>
|
|
<p class="caption"><span class="caption-text">Contributing</span></p>
|
|
<ul>
|
|
<li class="toctree-l1"><a class="reference internal" href="../contributing/add_agent.html">Adding a New Agent</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../contributing/add_env.html">Adding a New Environment</a></li>
|
|
</ul>
|
|
<p class="caption"><span class="caption-text">Components</span></p>
|
|
<ul>
|
|
<li class="toctree-l1"><a class="reference internal" href="../components/agents/index.html">Agents</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../components/architectures/index.html">Architectures</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../components/data_stores/index.html">Data Stores</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../components/environments/index.html">Environments</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../components/exploration_policies/index.html">Exploration Policies</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../components/filters/index.html">Filters</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../components/memories/index.html">Memories</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../components/memory_backends/index.html">Memory Backends</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../components/orchestrators/index.html">Orchestrators</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../components/core_types.html">Core Types</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../components/spaces.html">Spaces</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../components/additional_parameters.html">Additional Parameters</a></li>
|
|
</ul>
|
|
|
|
|
|
|
|
</div>
|
|
</div>
|
|
</nav>
|
|
|
|
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
|
|
|
|
|
|
<nav class="wy-nav-top" aria-label="top navigation">
|
|
|
|
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
|
|
<a href="../index.html">Reinforcement Learning Coach</a>
|
|
|
|
</nav>
|
|
|
|
|
|
<div class="wy-nav-content">
|
|
|
|
<div class="rst-content">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<div role="navigation" aria-label="breadcrumbs navigation">
|
|
|
|
<ul class="wy-breadcrumbs">
|
|
|
|
<li><a href="../index.html">Docs</a> »</li>
|
|
|
|
<li><a href="index.html">Features</a> »</li>
|
|
|
|
<li>Benchmarks</li>
|
|
|
|
|
|
<li class="wy-breadcrumbs-aside">
|
|
|
|
|
|
<a href="../_sources/features/benchmarks.rst.txt" rel="nofollow"> View page source</a>
|
|
|
|
|
|
</li>
|
|
|
|
</ul>
|
|
|
|
|
|
<hr/>
|
|
</div>
|
|
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
|
|
<div itemprop="articleBody">
|
|
|
|
<div class="section" id="benchmarks">
|
|
<h1>Benchmarks<a class="headerlink" href="#benchmarks" title="Permalink to this headline">¶</a></h1>
|
|
<p>Reinforcement learning is a developing field, and so far it has been particularly difficult to reproduce some of the
|
|
results published in the original papers. Some reasons for this are:</p>
|
|
<ul class="simple">
|
|
<li><p>Reinforcement learning algorithms are notoriously known as having an unstable learning process.
|
|
The data the neural networks trains on is dynamic, and depends on the random seed defined for the environment.</p></li>
|
|
<li><p>Reinforcement learning algorithms have many moving parts. For some environments and agents, there are many
|
|
“tricks” which are needed to get the exact behavior the paper authors had seen. Also, there are <strong>a lot</strong> of
|
|
hyper-parameters to set.</p></li>
|
|
</ul>
|
|
<p>In order for a reinforcement learning implementation to be useful for research or for data science, it must be
|
|
shown that it achieves the expected behavior. For this reason, we collected a set of benchmark results from most
|
|
of the algorithms implemented in Coach. The algorithms were tested on a subset of the same environments that were
|
|
used in the original papers, and with multiple seed for each environment.
|
|
Additionally, Coach uses some strict testing mechanisms to try and make sure the results we show for these
|
|
benchmarks stay intact as Coach continues to develop.</p>
|
|
<p>To see the benchmark results, please visit the
|
|
<a class="reference external" href="https://github.com/NervanaSystems/coach/tree/master/benchmarks">following GitHub page</a>.</p>
|
|
</div>
|
|
|
|
|
|
</div>
|
|
|
|
</div>
|
|
<footer>
|
|
|
|
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
|
|
|
|
<a href="../selecting_an_algorithm.html" class="btn btn-neutral float-right" title="Selecting an Algorithm" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a>
|
|
|
|
|
|
<a href="environments.html" class="btn btn-neutral float-left" title="Environments" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left"></span> Previous</a>
|
|
|
|
</div>
|
|
|
|
|
|
<hr/>
|
|
|
|
<div role="contentinfo">
|
|
<p>
|
|
© Copyright 2018-2019, Intel AI Lab
|
|
|
|
</p>
|
|
</div>
|
|
Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
|
|
|
|
</footer>
|
|
|
|
</div>
|
|
</div>
|
|
|
|
</section>
|
|
|
|
</div>
|
|
|
|
|
|
|
|
<script type="text/javascript">
|
|
jQuery(function () {
|
|
SphinxRtdTheme.Navigation.enable(true);
|
|
});
|
|
</script>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
</body>
|
|
</html> |