mirror of
https://github.com/gryf/coach.git
synced 2025-12-17 19:20:19 +01:00
323 lines
16 KiB
HTML
323 lines
16 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>Control Flow — Reinforcement Learning Coach 0.12.1 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="Network Design" href="network.html" />
|
||
<link rel="prev" title="Coach Dashboard" href="../dashboard.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 current"><a class="current reference internal" href="#">Control Flow</a><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="#graph-manager">Graph Manager</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="#level-manager">Level Manager</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="#agent">Agent</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l1"><a class="reference internal" href="network.html">Network Design</a></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>Control Flow</li>
|
||
|
||
|
||
<li class="wy-breadcrumbs-aside">
|
||
|
||
|
||
<a href="../_sources/design/control_flow.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="control-flow">
|
||
<h1>Control Flow<a class="headerlink" href="#control-flow" title="Permalink to this headline">¶</a></h1>
|
||
<p>Coach is built in a modular way, encouraging modules reuse and reducing the amount of boilerplate code needed
|
||
for developing new algorithms or integrating a new challenge as an environment.
|
||
On the other hand, it can be overwhelming for new users to ramp up on the code.
|
||
To help with that, here’s a short overview of the control flow.</p>
|
||
<div class="section" id="graph-manager">
|
||
<h2>Graph Manager<a class="headerlink" href="#graph-manager" title="Permalink to this headline">¶</a></h2>
|
||
<p>The main entry point for Coach is <code class="code docutils literal notranslate"><span class="pre">coach.py</span></code>.
|
||
The main functionality of this script is to parse the command line arguments and invoke all the sub-processes needed
|
||
for the given experiment.
|
||
<code class="code docutils literal notranslate"><span class="pre">coach.py</span></code> executes the given <strong>preset</strong> file which returns a <code class="code docutils literal notranslate"><span class="pre">GraphManager</span></code> object.</p>
|
||
<p>A <strong>preset</strong> is a design pattern that is intended for concentrating the entire definition of an experiment in a single
|
||
file. This helps with experiments reproducibility, improves readability and prevents confusion.
|
||
The outcome of a preset is a <code class="code docutils literal notranslate"><span class="pre">GraphManager</span></code> which will usually be instantiated in the final lines of the preset.</p>
|
||
<p>A <code class="code docutils literal notranslate"><span class="pre">GraphManager</span></code> is an object that holds all the agents and environments of an experiment, and is mostly responsible
|
||
for scheduling their work. Why is it called a <strong>graph</strong> manager? Because agents and environments are structured into
|
||
a graph of interactions. For example, in hierarchical reinforcement learning schemes, there will often be a master
|
||
policy agent, that will control a sub-policy agent, which will interact with the environment. Other schemes can have
|
||
much more complex graphs of control, such as several hierarchy layers, each with multiple agents.
|
||
The graph manager’s main loop is the improve loop.</p>
|
||
<a class="reference internal image-reference" href="../_images/improve.png"><img alt="../_images/improve.png" class="align-center" src="../_images/improve.png" style="width: 400px;" /></a>
|
||
<p>The improve loop skips between 3 main phases - heatup, training and evaluation:</p>
|
||
<ul class="simple">
|
||
<li><p><strong>Heatup</strong> - the goal of this phase is to collect initial data for populating the replay buffers. The heatup phase
|
||
takes place only in the beginning of the experiment, and the agents will act completely randomly during this phase.
|
||
Importantly, the agents do not train their networks during this phase. DQN for example, uses 50k random steps in order
|
||
to initialize the replay buffers.</p></li>
|
||
<li><p><strong>Training</strong> - the training phase is the main phase of the experiment. This phase can change between agent types,
|
||
but essentially consists of repeated cycles of acting, collecting data from the environment, and training the agent
|
||
networks. During this phase, the agent will use its exploration policy in training mode, which will add noise to its
|
||
actions in order to improve its knowledge about the environment state space.</p></li>
|
||
<li><p><strong>Evaluation</strong> - the evaluation phase is intended for evaluating the current performance of the agent. The agents
|
||
will act greedily in order to exploit the knowledge aggregated so far and the performance over multiple episodes of
|
||
evaluation will be averaged in order to reduce the stochasticity effects of all the components.</p></li>
|
||
</ul>
|
||
</div>
|
||
<div class="section" id="level-manager">
|
||
<h2>Level Manager<a class="headerlink" href="#level-manager" title="Permalink to this headline">¶</a></h2>
|
||
<p>In each of the 3 phases described above, the graph manager will invoke all the hierarchy levels in the graph in a
|
||
synchronized manner. In Coach, agents do not interact directly with the environment. Instead, they go through a
|
||
<em>LevelManager</em>, which is a proxy that manages their interaction. The level manager passes the current state and reward
|
||
from the environment to the agent, and the actions from the agent to the environment.</p>
|
||
<p>The motivation for having a level manager is to disentangle the code of the environment and the agent, so to allow more
|
||
complex interactions. Each level can have multiple agents which interact with the environment. Who gets to choose the
|
||
action for each step is controlled by the level manager.
|
||
Additionally, each level manager can act as an environment for the hierarchy level above it, such that each hierarchy
|
||
level can be seen as an interaction between an agent and an environment, even if the environment is just more agents in
|
||
a lower hierarchy level.</p>
|
||
</div>
|
||
<div class="section" id="agent">
|
||
<h2>Agent<a class="headerlink" href="#agent" title="Permalink to this headline">¶</a></h2>
|
||
<p>The base agent class has 3 main function that will be used during those phases - observe, act and train.</p>
|
||
<ul class="simple">
|
||
<li><p><strong>Observe</strong> - this function gets the latest response from the environment as input, and updates the internal state
|
||
of the agent with the new information. The environment response will
|
||
be first passed through the agent’s <code class="code docutils literal notranslate"><span class="pre">InputFilter</span></code> object, which will process the values in the response, according
|
||
to the specific agent definition. The environment response will then be converted into a
|
||
<code class="code docutils literal notranslate"><span class="pre">Transition</span></code> which will contain the information from a single step
|
||
<span class="math notranslate nohighlight">\((s_{t}, a_{t}, r_{t}, s_{t+1}, \textrm{terminal signal})\)</span>, and store it in the memory.</p></li>
|
||
</ul>
|
||
<a class="reference internal image-reference" href="../_images/observe.png"><img alt="../_images/observe.png" class="align-center" src="../_images/observe.png" style="width: 700px;" /></a>
|
||
<ul class="simple">
|
||
<li><p><strong>Act</strong> - this function uses the current internal state of the agent in order to select the next action to take on
|
||
the environment. This function will call the per-agent custom function <code class="code docutils literal notranslate"><span class="pre">choose_action</span></code> that will use the network
|
||
and the exploration policy in order to select an action. The action will be stored, together with any additional
|
||
information (like the action value for example) in an <code class="code docutils literal notranslate"><span class="pre">ActionInfo</span></code> object. The ActionInfo object will then be
|
||
passed through the agent’s <code class="code docutils literal notranslate"><span class="pre">OutputFilter</span></code> to allow any processing of the action (like discretization,
|
||
or shifting, for example), before passing it to the environment.</p></li>
|
||
</ul>
|
||
<a class="reference internal image-reference" href="../_images/act.png"><img alt="../_images/act.png" class="align-center" src="../_images/act.png" style="width: 700px;" /></a>
|
||
<ul class="simple">
|
||
<li><p><strong>Train</strong> - this function will sample a batch from the memory and train on it. The batch of transitions will be
|
||
first wrapped into a <code class="code docutils literal notranslate"><span class="pre">Batch</span></code> object to allow efficient querying of the batch values. It will then be passed into
|
||
the agent specific <code class="code docutils literal notranslate"><span class="pre">learn_from_batch</span></code> function, that will extract network target values from the batch and will
|
||
train the networks accordingly. Lastly, if there’s a target network defined for the agent, it will sync the target
|
||
network weights with the online network.</p></li>
|
||
</ul>
|
||
<a class="reference internal image-reference" href="../_images/train.png"><img alt="../_images/train.png" class="align-center" src="../_images/train.png" style="width: 700px;" /></a>
|
||
</div>
|
||
</div>
|
||
|
||
|
||
</div>
|
||
|
||
</div>
|
||
<footer>
|
||
|
||
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
|
||
|
||
<a href="network.html" class="btn btn-neutral float-right" title="Network Design" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a>
|
||
|
||
|
||
<a href="../dashboard.html" class="btn btn-neutral float-left" title="Coach Dashboard" 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> |