mirror of
https://github.com/gryf/coach.git
synced 2025-12-17 19:20:19 +01:00
347 lines
17 KiB
HTML
347 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>Twin Delayed Deep Deterministic Policy Gradient — 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="Soft Actor-Critic" href="sac.html" />
|
||
<link rel="prev" title="Deep Deterministic Policy Gradient" href="ddpg.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"><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>
|
||
<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 current"><a class="current reference internal" href="#">Twin Delayed Deep Deterministic Policy Gradient</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">Choosing an action</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="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>Twin Delayed Deep Deterministic Policy Gradient</li>
|
||
|
||
|
||
<li class="wy-breadcrumbs-aside">
|
||
|
||
|
||
<a href="../../../_sources/components/agents/policy_optimization/td3.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="twin-delayed-deep-deterministic-policy-gradient">
|
||
<h1>Twin Delayed Deep Deterministic Policy Gradient<a class="headerlink" href="#twin-delayed-deep-deterministic-policy-gradient" title="Permalink to this headline">¶</a></h1>
|
||
<p><strong>Actions space:</strong> Continuous</p>
|
||
<p><strong>References:</strong> <a class="reference external" href="https://arxiv.org/pdf/1802.09477">Addressing Function Approximation Error in Actor-Critic Methods</a></p>
|
||
<div class="section" id="network-structure">
|
||
<h2>Network Structure<a class="headerlink" href="#network-structure" title="Permalink to this headline">¶</a></h2>
|
||
<img alt="../../../_images/td3.png" class="align-center" src="../../../_images/td3.png" />
|
||
</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">
|
||
<h3>Choosing an action<a class="headerlink" href="#choosing-an-action" title="Permalink to this headline">¶</a></h3>
|
||
<p>Pass the current states through the actor network, and get an action mean vector <span class="math notranslate nohighlight">\(\mu\)</span>.
|
||
While in training phase, use a continuous exploration policy, such as a small zero-meaned gaussian noise,
|
||
to add exploration noise to the action. When testing, use the mean vector <span class="math notranslate nohighlight">\(\mu\)</span> as-is.</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>Start by sampling a batch of transitions from the experience replay.</p>
|
||
<ul>
|
||
<li><p>To train the two <strong>critic networks</strong>, use the following targets:</p>
|
||
<p><span class="math notranslate nohighlight">\(y_t=r(s_t,a_t )+\gamma \cdot \min_{i=1,2} Q_{i}(s_{t+1},\mu(s_{t+1} )+[\mathcal{N}(0,\,\sigma^{2})]^{MAX\_NOISE}_{MIN\_NOISE})\)</span></p>
|
||
<p>First run the actor target network, using the next states as the inputs, and get <span class="math notranslate nohighlight">\(\mu (s_{t+1} )\)</span>. Then, add a
|
||
clipped gaussian noise to these actions, and clip the resulting actions to the actions space.
|
||
Next, run the critic target networks using the next states and <span class="math notranslate nohighlight">\(\mu (s_{t+1} )+[\mathcal{N}(0,\,\sigma^{2})]^{MAX\_NOISE}_{MIN\_NOISE}\)</span>,
|
||
and use the minimum between the two critic networks predictions in order to calculate <span class="math notranslate nohighlight">\(y_t\)</span> according to the
|
||
equation above. To train the networks, use the current states and actions as the inputs, and <span class="math notranslate nohighlight">\(y_t\)</span>
|
||
as the targets.</p>
|
||
</li>
|
||
<li><p>To train the <strong>actor network</strong>, use the following equation:</p>
|
||
<p><span class="math notranslate nohighlight">\(\nabla_{\theta^\mu } J \approx E_{s_t \tilde{} \rho^\beta } [\nabla_a Q_{1}(s,a)|_{s=s_t,a=\mu (s_t ) } \cdot \nabla_{\theta^\mu} \mu(s)|_{s=s_t} ]\)</span></p>
|
||
<p>Use the actor’s online network to get the action mean values using the current states as the inputs.
|
||
Then, use the first critic’s online network in order to get the gradients of the critic output with respect to the
|
||
action mean values <span class="math notranslate nohighlight">\(\nabla _a Q_{1}(s,a)|_{s=s_t,a=\mu(s_t ) }\)</span>.
|
||
Using the chain rule, calculate the gradients of the actor’s output, with respect to the actor weights,
|
||
given <span class="math notranslate nohighlight">\(\nabla_a Q(s,a)\)</span>. Finally, apply those gradients to the actor network.</p>
|
||
<p>The actor’s training is done at a slower frequency than the critic’s training, in order to allow the critic to better fit the
|
||
current policy, before exercising the critic in order to train the actor.
|
||
Following the same, delayed, actor’s training cadence, do a soft update of the critic and actor target networks’ weights
|
||
from the online networks.</p>
|
||
</li>
|
||
</ul>
|
||
<dl class="class">
|
||
<dt id="rl_coach.agents.td3_agent.TD3AlgorithmParameters">
|
||
<em class="property">class </em><code class="sig-prename descclassname">rl_coach.agents.td3_agent.</code><code class="sig-name descname">TD3AlgorithmParameters</code><a class="reference internal" href="../../../_modules/rl_coach/agents/td3_agent.html#TD3AlgorithmParameters"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.td3_agent.TD3AlgorithmParameters" 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_copying_online_weights_to_target</strong> – (StepMethod)
|
||
The number of steps between copying the online network weights to the target network weights.</p></li>
|
||
<li><p><strong>rate_for_copying_weights_to_target</strong> – (float)
|
||
When copying the online network weights to the target network weights, a soft update will be used, which
|
||
weight the new online network weights by rate_for_copying_weights_to_target</p></li>
|
||
<li><p><strong>num_consecutive_playing_steps</strong> – (StepMethod)
|
||
The number of consecutive steps to act between every two training iterations</p></li>
|
||
<li><p><strong>use_target_network_for_evaluation</strong> – (bool)
|
||
If set to True, the target network will be used for predicting the actions when choosing actions to act.
|
||
Since the target network weights change more slowly, the predicted actions will be more consistent.</p></li>
|
||
<li><p><strong>action_penalty</strong> – (float)
|
||
The amount by which to penalize the network on high action feature (pre-activation) values.
|
||
This can prevent the actions features from saturating the TanH activation function, and therefore prevent the
|
||
gradients from becoming very low.</p></li>
|
||
<li><p><strong>clip_critic_targets</strong> – (Tuple[float, float] or None)
|
||
The range to clip the critic target to in order to prevent overestimation of the action values.</p></li>
|
||
<li><p><strong>use_non_zero_discount_for_terminal_states</strong> – (bool)
|
||
If set to True, the discount factor will be used for terminal states to bootstrap the next predicted state
|
||
values. If set to False, the terminal states reward will be taken as the target return for the network.</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="sac.html" class="btn btn-neutral float-right" title="Soft Actor-Critic" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a>
|
||
|
||
|
||
<a href="ddpg.html" class="btn btn-neutral float-left" title="Deep Deterministic Policy Gradient" 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> |