mirror of
https://github.com/gryf/coach.git
synced 2025-12-17 19:20:19 +01:00
272 lines
11 KiB
HTML
272 lines
11 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>Distributed Coach - Horizontal Scale-Out — 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="Adding a New Agent" href="../contributing/add_agent.html" />
|
||
<link rel="prev" title="Network Design" href="network.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>
|
||
<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"><a class="reference internal" href="../features/index.html">Features</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../selecting_an_algorithm.html">Selecting an Algorithm</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../dashboard.html">Coach Dashboard</a></li>
|
||
</ul>
|
||
<p class="caption"><span class="caption-text">Design</span></p>
|
||
<ul class="current">
|
||
<li class="toctree-l1"><a class="reference internal" href="control_flow.html">Control Flow</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="network.html">Network Design</a></li>
|
||
<li class="toctree-l1 current"><a class="current reference internal" href="#">Distributed Coach - Horizontal Scale-Out</a><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="#supported-synchronization-types">Supported Synchronization Types</a></li>
|
||
</ul>
|
||
</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>Distributed Coach - Horizontal Scale-Out</li>
|
||
|
||
|
||
<li class="wy-breadcrumbs-aside">
|
||
|
||
|
||
<a href="../_sources/design/horizontal_scaling.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="distributed-coach-horizontal-scale-out">
|
||
<span id="dist-coach-design"></span><h1>Distributed Coach - Horizontal Scale-Out<a class="headerlink" href="#distributed-coach-horizontal-scale-out" title="Permalink to this headline">¶</a></h1>
|
||
<p>Coach supports the horizontal scale-out of rollout workers using <cite>–distributed_coach</cite> or <cite>-dc</cite> options. Coach uses
|
||
three interfaces for horizontal scale-out, which allows for integration with different technologies and flexibility.
|
||
These three interfaces are orchestrator, memory backend and data store.</p>
|
||
<ul class="simple">
|
||
<li><p><strong>Orchestrator</strong> - The orchestrator interface provides basic interaction points for orchestration, scheduling and
|
||
resource management of training and rollout workers in the distributed coach mode. The interactions points define
|
||
how Coach should deploy, undeploy and monitor the workers spawned by Coach.</p></li>
|
||
<li><p><strong>Memory Backend</strong> - This interface is used as the backing store or stream for the memory abstraction in
|
||
distributed Coach. The implementation of this module is mainly used for communicating experiences (transitions
|
||
and episodes) from the rollout to the training worker.</p></li>
|
||
<li><p><strong>Data Store</strong> - This interface is used as a backing store for the policy checkpoints. It is mainly used to
|
||
synchronizing policy checkpoints from the training to the rollout worker.</p></li>
|
||
</ul>
|
||
<a class="reference internal image-reference" href="../_images/horizontal-scale-out.png"><img alt="../_images/horizontal-scale-out.png" class="align-center" src="../_images/horizontal-scale-out.png" style="width: 800px;" /></a>
|
||
<div class="section" id="supported-synchronization-types">
|
||
<h2>Supported Synchronization Types<a class="headerlink" href="#supported-synchronization-types" title="Permalink to this headline">¶</a></h2>
|
||
<p>Synchronization type refers to the mechanism by which the policy checkpoints are synchronized from the training to the
|
||
rollout worker. For each algorithm, it is specified by using the <cite>DistributedCoachSynchronizationType</cite> as a part of
|
||
<cite>agent_params.algorithm.distributed_coach_synchronization_type</cite> in the preset. In distributed Coach, two types of
|
||
synchronization modes are supported: <cite>SYNC</cite> and <cite>ASYNC</cite>.</p>
|
||
<ul class="simple">
|
||
<li><p><strong>SYNC</strong> - In this type, the trainer waits for all the experiences to be gathered from distributed rollout workers
|
||
before training a new policy and the rollout workers wait for a new policy before gathering experiences. It is suitable
|
||
for ON policy algorithms.</p></li>
|
||
<li><p><strong>ASYNC</strong> - In this type, the trainer doesn’t wait for any set of experiences to be gathered from distributed
|
||
rollout workers and the rollout workers continously gather experiences loading new policies, whenever they become
|
||
available. It is suitable for OFF policy algorithms.</p></li>
|
||
</ul>
|
||
</div>
|
||
</div>
|
||
|
||
|
||
</div>
|
||
|
||
</div>
|
||
<footer>
|
||
|
||
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
|
||
|
||
<a href="../contributing/add_agent.html" class="btn btn-neutral float-right" title="Adding a New Agent" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a>
|
||
|
||
|
||
<a href="network.html" class="btn btn-neutral float-left" title="Network Design" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left"></span> Previous</a>
|
||
|
||
</div>
|
||
|
||
|
||
<hr/>
|
||
|
||
<div role="contentinfo">
|
||
<p>
|
||
© Copyright 2018-2019, 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> |