mirror of
https://github.com/gryf/coach.git
synced 2025-12-17 11:10:20 +01:00
287 lines
11 KiB
HTML
287 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>Network Design — 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="Distributed Coach - Horizontal Scale-Out" href="horizontal_scaling.html" />
|
||
<link rel="prev" title="Control Flow" href="control_flow.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 current"><a class="current reference internal" href="#">Network Design</a><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="#keeping-network-copies-in-sync">Keeping Network Copies in Sync</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l1"><a class="reference internal" href="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>Network Design</li>
|
||
|
||
|
||
<li class="wy-breadcrumbs-aside">
|
||
|
||
|
||
<a href="../_sources/design/network.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="network-design">
|
||
<h1>Network Design<a class="headerlink" href="#network-design" title="Permalink to this headline">¶</a></h1>
|
||
<p>Each agent has at least one neural network, used as the function approximator, for choosing the actions.
|
||
The network is designed in a modular way to allow reusability in different agents.
|
||
It is separated into three main parts:</p>
|
||
<ul>
|
||
<li><p><strong>Input Embedders</strong> - This is the first stage of the network, meant to convert the input into a feature vector representation.
|
||
It is possible to combine several instances of any of the supported embedders, in order to allow varied combinations of inputs.</p>
|
||
<blockquote>
|
||
<div><p>There are two main types of input embedders:</p>
|
||
<ol class="arabic simple">
|
||
<li><p>Image embedder - Convolutional neural network.</p></li>
|
||
<li><p>Vector embedder - Multi-layer perceptron.</p></li>
|
||
</ol>
|
||
</div></blockquote>
|
||
</li>
|
||
<li><p><strong>Middlewares</strong> - The middleware gets the output of the input embedder, and processes it into a different representation domain,
|
||
before sending it through the output head. The goal of the middleware is to enable processing the combined outputs of
|
||
several input embedders, and pass them through some extra processing.
|
||
This, for instance, might include an LSTM or just a plain simple FC layer.</p></li>
|
||
<li><p><strong>Output Heads</strong> - The output head is used in order to predict the values required from the network.
|
||
These might include action-values, state-values or a policy. As with the input embedders,
|
||
it is possible to use several output heads in the same network. For example, the <em>Actor Critic</em> agent combines two
|
||
heads - a policy head and a state-value head.
|
||
In addition, the output heads defines the loss function according to the head type.</p>
|
||
<p></p>
|
||
</li>
|
||
</ul>
|
||
<a class="reference internal image-reference" href="../_images/network.png"><img alt="../_images/network.png" class="align-center" src="../_images/network.png" style="width: 400px;" /></a>
|
||
<div class="section" id="keeping-network-copies-in-sync">
|
||
<h2>Keeping Network Copies in Sync<a class="headerlink" href="#keeping-network-copies-in-sync" title="Permalink to this headline">¶</a></h2>
|
||
<p>Most of the reinforcement learning agents include more than one copy of the neural network.
|
||
These copies serve as counterparts of the main network which are updated in different rates,
|
||
and are often synchronized either locally or between parallel workers. For easier synchronization of those copies,
|
||
a wrapper around these copies exposes a simplified API, which allows hiding these complexities from the agent.
|
||
In this wrapper, 3 types of networks can be defined:</p>
|
||
<ul class="simple">
|
||
<li><p><strong>online network</strong> - A mandatory network which is the main network the agent will use</p></li>
|
||
<li><p><strong>global network</strong> - An optional network which is shared between workers in single-node multi-process distributed learning.
|
||
It is updated by all the workers directly, and holds the most up-to-date weights.</p></li>
|
||
<li><p><strong>target network</strong> - An optional network which is local for each worker. It can be used in order to keep a copy of
|
||
the weights stable for a long period of time. This is used in different agents, like DQN for example, in order to
|
||
have stable targets for the online network while training it.</p></li>
|
||
</ul>
|
||
<a class="reference internal image-reference" href="../_images/distributed.png"><img alt="../_images/distributed.png" class="align-center" src="../_images/distributed.png" style="width: 600px;" /></a>
|
||
</div>
|
||
</div>
|
||
|
||
|
||
</div>
|
||
|
||
</div>
|
||
<footer>
|
||
|
||
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
|
||
|
||
<a href="horizontal_scaling.html" class="btn btn-neutral float-right" title="Distributed Coach - Horizontal Scale-Out" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a>
|
||
|
||
|
||
<a href="control_flow.html" class="btn btn-neutral float-left" title="Control Flow" 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> |