mirror of
https://github.com/gryf/coach.git
synced 2025-12-17 19:20:19 +01:00
ACER algorithm (#184)
* initial ACER commit * Code cleanup + several fixes * Q-retrace bug fix + small clean-ups * added documentation for acer * ACER benchmarks * update benchmarks table * Add nightly running of golden and trace tests. (#202) Resolves #200 * comment out nightly trace tests until values reset. * remove redundant observe ignore (#168) * ensure nightly test env containers exist. (#205) Also bump integration test timeout * wxPython removal (#207) Replacing wxPython with Python's Tkinter. Also removing the option to choose multiple files as it is unused and causes errors, and fixing the load file/directory spinner. * Create CONTRIBUTING.md (#210) * Create CONTRIBUTING.md. Resolves #188 * run nightly golden tests sequentially. (#217) Should reduce resource requirements and potential CPU contention but increases overall execution time. * tests: added new setup configuration + test args (#211) - added utils for future tests and conftest - added test args * new docs build * golden test update
This commit is contained in:
shadiendrawis
@@ -30,7 +30,7 @@
|
||||
<link rel="index" title="Index" href="../../../genindex.html" />
|
||||
<link rel="search" title="Search" href="../../../search.html" />
|
||||
<link rel="next" title="Bootstrapped DQN" href="../value_optimization/bs_dqn.html" />
|
||||
<link rel="prev" title="Actor-Critic" href="../policy_optimization/ac.html" />
|
||||
<link rel="prev" title="ACER" href="../policy_optimization/acer.html" />
|
||||
<link href="../../../_static/css/custom.css" rel="stylesheet" type="text/css">
|
||||
|
||||
|
||||
@@ -107,6 +107,7 @@
|
||||
<ul class="current">
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="../index.html">Agents</a><ul class="current">
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/ac.html">Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/acer.html">ACER</a></li>
|
||||
<li class="toctree-l2 current"><a class="current reference internal" href="#">Behavioral Cloning</a><ul>
|
||||
<li class="toctree-l3"><a class="reference internal" href="#network-structure">Network Structure</a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="#algorithm-description">Algorithm Description</a><ul>
|
||||
@@ -252,7 +253,7 @@ the expert for each state.</p>
|
||||
<a href="../value_optimization/bs_dqn.html" class="btn btn-neutral float-right" title="Bootstrapped DQN" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a>
|
||||
|
||||
|
||||
<a href="../policy_optimization/ac.html" class="btn btn-neutral" title="Actor-Critic" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left"></span> Previous</a>
|
||||
<a href="../policy_optimization/acer.html" class="btn btn-neutral" title="ACER" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left"></span> Previous</a>
|
||||
|
||||
</div>
|
||||
|
||||
@@ -286,7 +287,8 @@ the expert for each state.</p>
|
||||
<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 async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></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>
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -107,6 +107,7 @@
|
||||
<ul class="current">
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="../index.html">Agents</a><ul class="current">
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/ac.html">Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/acer.html">ACER</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="bc.html">Behavioral Cloning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/bs_dqn.html">Bootstrapped DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/categorical_dqn.html">Categorical DQN</a></li>
|
||||
@@ -301,7 +302,8 @@ The key of the state dictionary which corresponds to the value that will be used
|
||||
<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 async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></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>
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -107,6 +107,7 @@
|
||||
<ul class="current">
|
||||
<li class="toctree-l1 current"><a class="current reference internal" href="#">Agents</a><ul>
|
||||
<li class="toctree-l2"><a class="reference internal" href="policy_optimization/ac.html">Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="policy_optimization/acer.html">ACER</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="imitation/bc.html">Behavioral Cloning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="value_optimization/bs_dqn.html">Bootstrapped DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="value_optimization/categorical_dqn.html">Categorical DQN</a></li>
|
||||
@@ -213,6 +214,7 @@ A detailed description of those algorithms can be found by navigating to each of
|
||||
<p class="caption"><span class="caption-text">Agents</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="policy_optimization/ac.html">Actor-Critic</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="policy_optimization/acer.html">ACER</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="imitation/bc.html">Behavioral Cloning</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="value_optimization/bs_dqn.html">Bootstrapped DQN</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="value_optimization/categorical_dqn.html">Categorical DQN</a></li>
|
||||
@@ -334,17 +336,9 @@ training or testing.</p>
|
||||
<dt id="rl_coach.agents.agent.Agent.collect_savers">
|
||||
<code class="descname">collect_savers</code><span class="sig-paren">(</span><em>parent_path_suffix: str</em><span class="sig-paren">)</span> → rl_coach.saver.SaverCollection<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.collect_savers"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.collect_savers" title="Permalink to this definition">¶</a></dt>
|
||||
<dd><p>Collect all of agent’s network savers
|
||||
:param parent_path_suffix: path suffix of the parent of the agent</p>
|
||||
<blockquote>
|
||||
<div>(could be name of level manager or composite agent)</div></blockquote>
|
||||
<table class="docutils field-list" frame="void" rules="none">
|
||||
<col class="field-name" />
|
||||
<col class="field-body" />
|
||||
<tbody valign="top">
|
||||
<tr class="field-odd field"><th class="field-name">Returns:</th><td class="field-body">collection of all agent savers</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
:param parent_path_suffix: path suffix of the parent of the agent
|
||||
(could be name of level manager or composite agent)
|
||||
:return: collection of all agent savers</p>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="method">
|
||||
@@ -640,15 +634,20 @@ by val, and by the current phase set in self.phase.</p>
|
||||
|
||||
<dl class="method">
|
||||
<dt id="rl_coach.agents.agent.Agent.run_pre_network_filter_for_inference">
|
||||
<code class="descname">run_pre_network_filter_for_inference</code><span class="sig-paren">(</span><em>state: Dict[str, numpy.ndarray]</em><span class="sig-paren">)</span> → Dict[str, numpy.ndarray]<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.run_pre_network_filter_for_inference"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.run_pre_network_filter_for_inference" title="Permalink to this definition">¶</a></dt>
|
||||
<code class="descname">run_pre_network_filter_for_inference</code><span class="sig-paren">(</span><em>state: Dict[str, numpy.ndarray], update_filter_internal_state: bool = True</em><span class="sig-paren">)</span> → Dict[str, numpy.ndarray]<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.run_pre_network_filter_for_inference"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.run_pre_network_filter_for_inference" title="Permalink to this definition">¶</a></dt>
|
||||
<dd><p>Run filters which where defined for being applied right before using the state for inference.</p>
|
||||
<table class="docutils field-list" frame="void" rules="none">
|
||||
<col class="field-name" />
|
||||
<col class="field-body" />
|
||||
<tbody valign="top">
|
||||
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><strong>state</strong> – The state to run the filters on</td>
|
||||
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple">
|
||||
<li><strong>state</strong> – The state to run the filters on</li>
|
||||
<li><strong>update_filter_internal_state</strong> – Should update the filter’s internal state - should not update when evaluating</li>
|
||||
</ul>
|
||||
</td>
|
||||
</tr>
|
||||
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body">The filtered state</td>
|
||||
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body"><p class="first last">The filtered state</p>
|
||||
</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
@@ -860,7 +859,8 @@ Can be useful for agents that want to tweak the reward, termination signal, etc.
|
||||
<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 async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></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>
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -107,6 +107,7 @@
|
||||
<ul class="current">
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="../index.html">Agents</a><ul class="current">
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/ac.html">Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/acer.html">ACER</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/bc.html">Behavioral Cloning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/bs_dqn.html">Bootstrapped DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/categorical_dqn.html">Categorical DQN</a></li>
|
||||
@@ -239,10 +240,9 @@ and the result is a single vector of future values for each action.</li>
|
||||
<h3>Training the network<a class="headerlink" href="#training-the-network" title="Permalink to this headline">¶</a></h3>
|
||||
<p>Given a batch of transitions, run them through the network to get the current predictions of the future measurements
|
||||
per action, and set them as the initial targets for training the network. For each transition
|
||||
<span class="math notranslate nohighlight">\((s_t,a_t,r_t,s_{t+1} )\)</span> in the batch, the target of the network for the action that was taken, is the actual</p>
|
||||
<blockquote>
|
||||
<div>measurements that were seen in time-steps <span class="math notranslate nohighlight">\(t+1,t+2,t+4,t+8,t+16\)</span> and <span class="math notranslate nohighlight">\(t+32\)</span>.
|
||||
For the actions that were not taken, the targets are the current values.</div></blockquote>
|
||||
<span class="math notranslate nohighlight">\((s_t,a_t,r_t,s_{t+1} )\)</span> in the batch, the target of the network for the action that was taken, is the actual
|
||||
measurements that were seen in time-steps <span class="math notranslate nohighlight">\(t+1,t+2,t+4,t+8,t+16\)</span> and <span class="math notranslate nohighlight">\(t+32\)</span>.
|
||||
For the actions that were not taken, the targets are the current values.</p>
|
||||
<dl class="class">
|
||||
<dt id="rl_coach.agents.dfp_agent.DFPAlgorithmParameters">
|
||||
<em class="property">class </em><code class="descclassname">rl_coach.agents.dfp_agent.</code><code class="descname">DFPAlgorithmParameters</code><a class="reference internal" href="../../../_modules/rl_coach/agents/dfp_agent.html#DFPAlgorithmParameters"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.dfp_agent.DFPAlgorithmParameters" title="Permalink to this definition">¶</a></dt>
|
||||
@@ -253,7 +253,8 @@ For the actions that were not taken, the targets are the current values.</div></
|
||||
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple">
|
||||
<li><strong>num_predicted_steps_ahead</strong> – (int)
|
||||
Number of future steps to predict measurements for. The future steps won’t be sequential, but rather jump
|
||||
in multiples of 2. For example, if num_predicted_steps_ahead = 3, then the steps will be: t+1, t+2, t+4</li>
|
||||
in multiples of 2. For example, if num_predicted_steps_ahead = 3, then the steps will be: t+1, t+2, t+4.
|
||||
The predicted steps will be [t + 2**i for i in range(num_predicted_steps_ahead)]</li>
|
||||
<li><strong>goal_vector</strong> – (List[float])
|
||||
The goal vector will weight each of the measurements to form an optimization goal. The vector should have
|
||||
the same length as the number of measurements, and it will be vector multiplied by the measurements.
|
||||
@@ -329,7 +330,8 @@ have a different scale and you want to normalize them to the same scale.</li>
|
||||
<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 async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></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>
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -29,7 +29,7 @@
|
||||
<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="Behavioral Cloning" href="../imitation/bc.html" />
|
||||
<link rel="next" title="ACER" href="acer.html" />
|
||||
<link rel="prev" title="Agents" href="../index.html" />
|
||||
<link href="../../../_static/css/custom.css" rel="stylesheet" type="text/css">
|
||||
|
||||
@@ -115,6 +115,7 @@
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="acer.html">ACER</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/bc.html">Behavioral Cloning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/bs_dqn.html">Bootstrapped DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/categorical_dqn.html">Categorical DQN</a></li>
|
||||
@@ -282,7 +283,7 @@ If set to True, the state value targets for the V head will be estimated using t
|
||||
|
||||
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
|
||||
|
||||
<a href="../imitation/bc.html" class="btn btn-neutral float-right" title="Behavioral Cloning" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a>
|
||||
<a href="acer.html" class="btn btn-neutral float-right" title="ACER" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a>
|
||||
|
||||
|
||||
<a href="../index.html" class="btn btn-neutral" title="Agents" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left"></span> Previous</a>
|
||||
@@ -319,7 +320,8 @@ If set to True, the state value targets for the V head will be estimated using t
|
||||
<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 async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></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>
|
||||
|
||||
|
||||
|
||||
|
||||
379
docs/components/agents/policy_optimization/acer.html
Normal file
379
docs/components/agents/policy_optimization/acer.html
Normal file
@@ -0,0 +1,379 @@
|
||||
|
||||
|
||||
<!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>ACER — Reinforcement Learning Coach 0.11.0 documentation</title>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<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="Behavioral Cloning" href="../imitation/bc.html" />
|
||||
<link rel="prev" title="Actor-Critic" href="ac.html" />
|
||||
<link href="../../../_static/css/custom.css" rel="stylesheet" type="text/css">
|
||||
|
||||
|
||||
|
||||
<script src="../../../_static/js/modernizr.min.js"></script>
|
||||
|
||||
</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>
|
||||
<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 class="current">
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="../index.html">Agents</a><ul class="current">
|
||||
<li class="toctree-l2"><a class="reference internal" href="ac.html">Actor-Critic</a></li>
|
||||
<li class="toctree-l2 current"><a class="current reference internal" href="#">ACER</a><ul>
|
||||
<li class="toctree-l3"><a class="reference internal" href="#network-structure">Network Structure</a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="#algorithm-description">Algorithm Description</a><ul>
|
||||
<li class="toctree-l4"><a class="reference internal" href="#choosing-an-action-discrete-actions">Choosing an action - Discrete actions</a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="#training-the-network">Training the network</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/bc.html">Behavioral Cloning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/bs_dqn.html">Bootstrapped DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/categorical_dqn.html">Categorical DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/cil.html">Conditional Imitation Learning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="cppo.html">Clipped Proximal Policy Optimization</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="ddpg.html">Deep Deterministic Policy Gradient</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../other/dfp.html">Direct Future Prediction</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/double_dqn.html">Double DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/dqn.html">Deep Q Networks</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/dueling_dqn.html">Dueling DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/mmc.html">Mixed Monte Carlo</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/n_step.html">N-Step Q Learning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/naf.html">Normalized Advantage Functions</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/nec.html">Neural Episodic Control</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/pal.html">Persistent Advantage Learning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="pg.html">Policy Gradient</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="ppo.html">Proximal Policy Optimization</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/rainbow.html">Rainbow</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/qr_dqn.html">Quantile Regression DQN</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../architectures/index.html">Architectures</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../data_stores/index.html">Data Stores</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../environments/index.html">Environments</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../exploration_policies/index.html">Exploration Policies</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../filters/index.html">Filters</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../memories/index.html">Memories</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../memory_backends/index.html">Memory Backends</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../orchestrators/index.html">Orchestrators</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../core_types.html">Core Types</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../spaces.html">Spaces</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../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">Agents</a> »</li>
|
||||
|
||||
<li>ACER</li>
|
||||
|
||||
|
||||
<li class="wy-breadcrumbs-aside">
|
||||
|
||||
|
||||
<a href="../../../_sources/components/agents/policy_optimization/acer.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="acer">
|
||||
<h1>ACER<a class="headerlink" href="#acer" title="Permalink to this headline">¶</a></h1>
|
||||
<p><strong>Actions space:</strong> Discrete</p>
|
||||
<p><strong>References:</strong> <a class="reference external" href="https://arxiv.org/abs/1611.01224">Sample Efficient Actor-Critic with Experience Replay</a></p>
|
||||
<div class="section" id="network-structure">
|
||||
<h2>Network Structure<a class="headerlink" href="#network-structure" title="Permalink to this headline">¶</a></h2>
|
||||
<a class="reference internal image-reference" href="../../../_images/acer.png"><img alt="../../../_images/acer.png" class="align-center" src="../../../_images/acer.png" style="width: 500px;" /></a>
|
||||
</div>
|
||||
<div class="section" id="algorithm-description">
|
||||
<h2>Algorithm Description<a class="headerlink" href="#algorithm-description" title="Permalink to this headline">¶</a></h2>
|
||||
<div class="section" id="choosing-an-action-discrete-actions">
|
||||
<h3>Choosing an action - Discrete actions<a class="headerlink" href="#choosing-an-action-discrete-actions" title="Permalink to this headline">¶</a></h3>
|
||||
<p>The policy network is used in order to predict action probabilites. While training, a sample is taken from a categorical
|
||||
distribution assigned with these probabilities. When testing, the action with the highest probability is used.</p>
|
||||
</div>
|
||||
<div class="section" id="training-the-network">
|
||||
<h3>Training the network<a class="headerlink" href="#training-the-network" title="Permalink to this headline">¶</a></h3>
|
||||
<p>Each iteration perform one on-policy update with a batch of the last <span class="math notranslate nohighlight">\(T_{max}\)</span> transitions,
|
||||
and <span class="math notranslate nohighlight">\(n\)</span> (replay ratio) off-policy updates from batches of <span class="math notranslate nohighlight">\(T_{max}\)</span> transitions sampled from the replay buffer.</p>
|
||||
<p>Each update perform the following procedure:</p>
|
||||
<ol class="arabic">
|
||||
<li><p class="first"><strong>Calculate state values:</strong></p>
|
||||
<div class="math notranslate nohighlight">
|
||||
\[V(s_t) = \mathbb{E}_{a \sim \pi} [Q(s_t,a)]\]</div>
|
||||
</li>
|
||||
<li><p class="first"><strong>Calculate Q retrace:</strong></p>
|
||||
<blockquote>
|
||||
<div><div class="math notranslate nohighlight">
|
||||
\[Q^{ret}(s_t,a_t) = r_t +\gamma \bar{\rho}_{t+1}[Q^{ret}(s_{t+1},a_{t+1}) - Q(s_{t+1},a_{t+1})] + \gamma V(s_{t+1})\]</div>
|
||||
<div class="math notranslate nohighlight">
|
||||
\[\text{where} \quad \bar{\rho}_{t} = \min{\left\{c,\rho_t\right\}},\quad \rho_t=\frac{\pi (a_t \mid s_t)}{\mu (a_t \mid s_t)}\]</div>
|
||||
</div></blockquote>
|
||||
</li>
|
||||
<li><dl class="first docutils">
|
||||
<dt><strong>Accumulate gradients:</strong></dt>
|
||||
<dd><p class="first"><span class="math notranslate nohighlight">\(\bullet\)</span> <strong>Policy gradients (with bias correction):</strong></p>
|
||||
<blockquote>
|
||||
<div><div class="math notranslate nohighlight">
|
||||
\[\begin{split}\hat{g}_t^{policy} & = & \bar{\rho}_{t} \nabla \log \pi (a_t \mid s_t) [Q^{ret}(s_t,a_t) - V(s_t)] \\
|
||||
& & + \mathbb{E}_{a \sim \pi} \left(\left[\frac{\rho_t(a)-c}{\rho_t(a)}\right] \nabla \log \pi (a \mid s_t) [Q(s_t,a) - V(s_t)] \right)\end{split}\]</div>
|
||||
</div></blockquote>
|
||||
<p><span class="math notranslate nohighlight">\(\bullet\)</span> <strong>Q-Head gradients (MSE):</strong></p>
|
||||
<blockquote class="last">
|
||||
<div><div class="math notranslate nohighlight">
|
||||
\[\begin{split}\hat{g}_t^{Q} = (Q^{ret}(s_t,a_t) - Q(s_t,a_t)) \nabla Q(s_t,a_t)\\\end{split}\]</div>
|
||||
</div></blockquote>
|
||||
</dd>
|
||||
</dl>
|
||||
</li>
|
||||
<li><p class="first"><strong>(Optional) Trust region update:</strong> change the policy loss gradient w.r.t network output:</p>
|
||||
<blockquote>
|
||||
<div><div class="math notranslate nohighlight">
|
||||
\[\hat{g}_t^{trust-region} = \hat{g}_t^{policy} - \max \left\{0, \frac{k^T \hat{g}_t^{policy} - \delta}{\lVert k \rVert_2^2}\right\} k\]</div>
|
||||
<div class="math notranslate nohighlight">
|
||||
\[\text{where} \quad k = \nabla D_{KL}[\pi_{avg} \parallel \pi]\]</div>
|
||||
<p>The average policy network is an exponential moving average of the parameters of the network (<span class="math notranslate nohighlight">\(\theta_{avg}=\alpha\theta_{avg}+(1-\alpha)\theta\)</span>).
|
||||
The goal of the trust region update is to the difference between the updated policy and the average policy to ensure stability.</p>
|
||||
</div></blockquote>
|
||||
</li>
|
||||
</ol>
|
||||
<dl class="class">
|
||||
<dt id="rl_coach.agents.acer_agent.ACERAlgorithmParameters">
|
||||
<em class="property">class </em><code class="descclassname">rl_coach.agents.acer_agent.</code><code class="descname">ACERAlgorithmParameters</code><a class="reference internal" href="../../../_modules/rl_coach/agents/acer_agent.html#ACERAlgorithmParameters"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.acer_agent.ACERAlgorithmParameters" title="Permalink to this definition">¶</a></dt>
|
||||
<dd><table class="docutils field-list" frame="void" rules="none">
|
||||
<col class="field-name" />
|
||||
<col class="field-body" />
|
||||
<tbody valign="top">
|
||||
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple">
|
||||
<li><strong>num_steps_between_gradient_updates</strong> – (int)
|
||||
Every num_steps_between_gradient_updates transitions will be considered as a single batch and use for
|
||||
accumulating gradients. This is also the number of steps used for bootstrapping according to the n-step formulation.</li>
|
||||
<li><strong>ratio_of_replay</strong> – (int)
|
||||
The number of off-policy training iterations in each ACER iteration.</li>
|
||||
<li><strong>num_transitions_to_start_replay</strong> – (int)
|
||||
Number of environment steps until ACER starts to train off-policy from the experience replay.
|
||||
This emulates a heat-up phase where the agents learns only on-policy until there are enough transitions in
|
||||
the experience replay to start the off-policy training.</li>
|
||||
<li><strong>rate_for_copying_weights_to_target</strong> – (float)
|
||||
The rate of the exponential moving average for the average policy which is used for the trust region optimization.
|
||||
The target network in this algorithm is used as the average policy.</li>
|
||||
<li><strong>importance_weight_truncation</strong> – (float)
|
||||
The clipping constant for the importance weight truncation (not used in the Q-retrace calculation).</li>
|
||||
<li><strong>use_trust_region_optimization</strong> – (bool)
|
||||
If set to True, the gradients of the network will be modified with a term dependant on the KL divergence between
|
||||
the average policy and the current one, to bound the change of the policy during the network update.</li>
|
||||
<li><strong>max_KL_divergence</strong> – (float)
|
||||
The upper bound parameter for the trust region optimization, use_trust_region_optimization needs to be set true
|
||||
for this parameter to have an effect.</li>
|
||||
<li><strong>beta_entropy</strong> – (float)
|
||||
An entropy regulaization term can be added to the loss function in order to control exploration. This term
|
||||
is weighted using the beta value defined by beta_entropy.</li>
|
||||
</ul>
|
||||
</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
</dd></dl>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
<footer>
|
||||
|
||||
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
|
||||
|
||||
<a href="../imitation/bc.html" class="btn btn-neutral float-right" title="Behavioral Cloning" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a>
|
||||
|
||||
|
||||
<a href="ac.html" class="btn btn-neutral" title="Actor-Critic" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left"></span> Previous</a>
|
||||
|
||||
</div>
|
||||
|
||||
|
||||
<hr/>
|
||||
|
||||
<div role="contentinfo">
|
||||
<p>
|
||||
© Copyright 2018, 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" 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>
|
||||
|
||||
<script type="text/javascript">
|
||||
jQuery(function () {
|
||||
SphinxRtdTheme.Navigation.enable(true);
|
||||
});
|
||||
</script>
|
||||
|
||||
</body>
|
||||
</html>
|
||||
@@ -107,6 +107,7 @@
|
||||
<ul class="current">
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="../index.html">Agents</a><ul class="current">
|
||||
<li class="toctree-l2"><a class="reference internal" href="ac.html">Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="acer.html">ACER</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/bc.html">Behavioral Cloning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/bs_dqn.html">Bootstrapped DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/categorical_dqn.html">Categorical DQN</a></li>
|
||||
@@ -342,7 +343,8 @@ Can be used to define a schedule over the clipping of the likelihood ratio.</li>
|
||||
<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 async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></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>
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -107,6 +107,7 @@
|
||||
<ul class="current">
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="../index.html">Agents</a><ul class="current">
|
||||
<li class="toctree-l2"><a class="reference internal" href="ac.html">Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="acer.html">ACER</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/bc.html">Behavioral Cloning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/bs_dqn.html">Bootstrapped DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/categorical_dqn.html">Categorical DQN</a></li>
|
||||
@@ -333,7 +334,8 @@ values. If set to False, the terminal states reward will be taken as the target
|
||||
<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 async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></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>
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -237,7 +237,8 @@ to add exploration noise to the action. When testing, use the mean vector <span
|
||||
<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 async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></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>
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -107,6 +107,7 @@
|
||||
<ul class="current">
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="../index.html">Agents</a><ul class="current">
|
||||
<li class="toctree-l2"><a class="reference internal" href="ac.html">Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="acer.html">ACER</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/bc.html">Behavioral Cloning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/bs_dqn.html">Bootstrapped DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/categorical_dqn.html">Categorical DQN</a></li>
|
||||
@@ -324,7 +325,8 @@ are used in the batch.</li>
|
||||
<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 async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></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>
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -107,6 +107,7 @@
|
||||
<ul class="current">
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="../index.html">Agents</a><ul class="current">
|
||||
<li class="toctree-l2"><a class="reference internal" href="ac.html">Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="acer.html">ACER</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/bc.html">Behavioral Cloning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/bs_dqn.html">Bootstrapped DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/categorical_dqn.html">Categorical DQN</a></li>
|
||||
@@ -343,7 +344,8 @@ is weighted using the <span class="math notranslate nohighlight">\(eta\)</span>
|
||||
<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 async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></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>
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -107,6 +107,7 @@
|
||||
<ul class="current">
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="../index.html">Agents</a><ul class="current">
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/ac.html">Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/acer.html">ACER</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/bc.html">Behavioral Cloning</a></li>
|
||||
<li class="toctree-l2 current"><a class="current reference internal" href="#">Bootstrapped DQN</a><ul>
|
||||
<li class="toctree-l3"><a class="reference internal" href="#network-structure">Network Structure</a></li>
|
||||
@@ -297,7 +298,8 @@ Then, train the online network according to the calculated targets.</p>
|
||||
<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 async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></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>
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -107,6 +107,7 @@
|
||||
<ul class="current">
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="../index.html">Agents</a><ul class="current">
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/ac.html">Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/acer.html">ACER</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/bc.html">Behavioral Cloning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="bs_dqn.html">Bootstrapped DQN</a></li>
|
||||
<li class="toctree-l2 current"><a class="current reference internal" href="#">Categorical DQN</a><ul>
|
||||
@@ -313,7 +314,8 @@ For the C51 algorithm described in the paper, the number of atoms is 51.</li>
|
||||
<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 async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></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>
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -107,6 +107,7 @@
|
||||
<ul class="current">
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="../index.html">Agents</a><ul class="current">
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/ac.html">Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/acer.html">ACER</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/bc.html">Behavioral Cloning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="bs_dqn.html">Bootstrapped DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="categorical_dqn.html">Categorical DQN</a></li>
|
||||
@@ -226,7 +227,7 @@
|
||||
<h3>Training the network<a class="headerlink" href="#training-the-network" title="Permalink to this headline">¶</a></h3>
|
||||
<ol class="arabic simple">
|
||||
<li>Sample a batch of transitions from the replay buffer.</li>
|
||||
<li>Using the next states from the sampled batch, run the online network in order to find the $Q$ maximizing
|
||||
<li>Using the next states from the sampled batch, run the online network in order to find the <span class="math notranslate nohighlight">\(Q\)</span> maximizing
|
||||
action <span class="math notranslate nohighlight">\(argmax_a Q(s_{t+1},a)\)</span>. For these actions, use the corresponding next states and run the target
|
||||
network to calculate <span class="math notranslate nohighlight">\(Q(s_{t+1},argmax_a Q(s_{t+1},a))\)</span>.</li>
|
||||
<li>In order to zero out the updates for the actions that were not played (resulting from zeroing the MSE loss),
|
||||
@@ -286,7 +287,8 @@ Set those values as the targets for the actions that were not actually played.</
|
||||
<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 async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></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>
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -107,6 +107,7 @@
|
||||
<ul class="current">
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="../index.html">Agents</a><ul class="current">
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/ac.html">Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/acer.html">ACER</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/bc.html">Behavioral Cloning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="bs_dqn.html">Bootstrapped DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="categorical_dqn.html">Categorical DQN</a></li>
|
||||
@@ -231,7 +232,7 @@ the actions <span class="math notranslate nohighlight">\(Q(s_{t+1},a)\)</span>,
|
||||
<li>In order to zero out the updates for the actions that were not played (resulting from zeroing the MSE loss),
|
||||
use the current states from the sampled batch, and run the online network to get the current Q values predictions.
|
||||
Set those values as the targets for the actions that were not actually played.</li>
|
||||
<li>For each action that was played, use the following equation for calculating the targets of the network: $$ y_t=r(s_t,a_t)+γcdot max_a {Q(s_{t+1},a)} $$
|
||||
<li>For each action that was played, use the following equation for calculating the targets of the network:
|
||||
<span class="math notranslate nohighlight">\(y_t=r(s_t,a_t )+\gamma \cdot max_a Q(s_{t+1})\)</span></li>
|
||||
<li>Finally, train the online network using the current states as inputs, and with the aforementioned targets.</li>
|
||||
<li>Once in every few thousand steps, copy the weights from the online network to the target network.</li>
|
||||
@@ -290,7 +291,8 @@ Set those values as the targets for the actions that were not actually played.</
|
||||
<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 async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></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>
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -107,6 +107,7 @@
|
||||
<ul class="current">
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="../index.html">Agents</a><ul class="current">
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/ac.html">Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/acer.html">ACER</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/bc.html">Behavioral Cloning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="bs_dqn.html">Bootstrapped DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="categorical_dqn.html">Categorical DQN</a></li>
|
||||
@@ -277,7 +278,8 @@ single action has been taken at this state.</p>
|
||||
<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 async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></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>
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -107,6 +107,7 @@
|
||||
<ul class="current">
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="../index.html">Agents</a><ul class="current">
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/ac.html">Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/acer.html">ACER</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/bc.html">Behavioral Cloning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="bs_dqn.html">Bootstrapped DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="categorical_dqn.html">Categorical DQN</a></li>
|
||||
@@ -297,7 +298,8 @@ the single-step bootstrapped targets.</td>
|
||||
<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 async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></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>
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -107,6 +107,7 @@
|
||||
<ul class="current">
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="../index.html">Agents</a><ul class="current">
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/ac.html">Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/acer.html">ACER</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/bc.html">Behavioral Cloning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="bs_dqn.html">Bootstrapped DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="categorical_dqn.html">Categorical DQN</a></li>
|
||||
@@ -314,7 +315,8 @@ please refer to the original paper (<a class="reference external" href="https://
|
||||
<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 async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></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>
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -107,6 +107,7 @@
|
||||
<ul class="current">
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="../index.html">Agents</a><ul class="current">
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/ac.html">Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/acer.html">ACER</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/bc.html">Behavioral Cloning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="bs_dqn.html">Bootstrapped DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="categorical_dqn.html">Categorical DQN</a></li>
|
||||
@@ -290,7 +291,8 @@ After every training step, use a soft update in order to copy the weights from t
|
||||
<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 async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></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>
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -107,6 +107,7 @@
|
||||
<ul class="current">
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="../index.html">Agents</a><ul class="current">
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/ac.html">Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/acer.html">ACER</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/bc.html">Behavioral Cloning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="bs_dqn.html">Bootstrapped DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="categorical_dqn.html">Categorical DQN</a></li>
|
||||
@@ -339,7 +340,8 @@ when the state was first seen, and not the latest, most up-to-date network value
|
||||
<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 async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></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>
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -107,6 +107,7 @@
|
||||
<ul class="current">
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="../index.html">Agents</a><ul class="current">
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/ac.html">Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/acer.html">ACER</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/bc.html">Behavioral Cloning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="bs_dqn.html">Bootstrapped DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="categorical_dqn.html">Categorical DQN</a></li>
|
||||
@@ -317,7 +318,8 @@ seen values, since it is not based on bootstrapping the current network values.<
|
||||
<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 async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></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>
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -107,6 +107,7 @@
|
||||
<ul class="current">
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="../index.html">Agents</a><ul class="current">
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/ac.html">Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/acer.html">ACER</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/bc.html">Behavioral Cloning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="bs_dqn.html">Bootstrapped DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="categorical_dqn.html">Categorical DQN</a></li>
|
||||
@@ -303,7 +304,8 @@ It describes the interval [-k, k] in which the huber loss acts as a MSE loss.</l
|
||||
<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 async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></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>
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -107,6 +107,7 @@
|
||||
<ul class="current">
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="../index.html">Agents</a><ul class="current">
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/ac.html">Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/acer.html">ACER</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/bc.html">Behavioral Cloning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="bs_dqn.html">Bootstrapped DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="categorical_dqn.html">Categorical DQN</a></li>
|
||||
@@ -325,7 +326,8 @@ transitions into the memory, and to do so we need the entire episode first.</li>
|
||||
<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 async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></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>
|
||||
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user