mirror of
https://github.com/gryf/coach.git
synced 2025-12-17 19:20:19 +01:00
367 lines
17 KiB
HTML
367 lines
17 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>ACER — 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="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">
|
||
|
||
</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="sac.html">Soft Actor-Critic</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><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><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><p><strong>Accumulate gradients:</strong></p>
|
||
<blockquote>
|
||
<div><p><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>
|
||
<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>
|
||
</div></blockquote>
|
||
</li>
|
||
<li><p><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><dl class="field-list simple">
|
||
<dt class="field-odd">Parameters</dt>
|
||
<dd class="field-odd"><ul class="simple">
|
||
<li><p><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.</p></li>
|
||
<li><p><strong>ratio_of_replay</strong> – (int)
|
||
The number of off-policy training iterations in each ACER iteration.</p></li>
|
||
<li><p><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.</p></li>
|
||
<li><p><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.</p></li>
|
||
<li><p><strong>importance_weight_truncation</strong> – (float)
|
||
The clipping constant for the importance weight truncation (not used in the Q-retrace calculation).</p></li>
|
||
<li><p><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.</p></li>
|
||
<li><p><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.</p></li>
|
||
<li><p><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.</p></li>
|
||
</ul>
|
||
</dd>
|
||
</dl>
|
||
</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 float-left" title="Actor-Critic" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left"></span> Previous</a>
|
||
|
||
</div>
|
||
|
||
|
||
<hr/>
|
||
|
||
<div role="contentinfo">
|
||
<p>
|
||
© Copyright 2018-2019, 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> |