mirror of
https://github.com/gryf/coach.git
synced 2025-12-17 19:20:19 +01:00
348 lines
17 KiB
HTML
348 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>Clipped Proximal Policy Optimization — 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="Deep Deterministic Policy Gradient" href="ddpg.html" />
|
||
<link rel="prev" title="Conditional Imitation Learning" href="../imitation/cil.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 current"><a class="current reference internal" href="#">Clipped Proximal Policy Optimization</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-continuous-action">Choosing an action - Continuous 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="ddpg.html">Deep Deterministic Policy Gradient</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="td3.html">Twin Delayed 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>Clipped Proximal Policy Optimization</li>
|
||
|
||
|
||
<li class="wy-breadcrumbs-aside">
|
||
|
||
|
||
<a href="../../../_sources/components/agents/policy_optimization/cppo.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="clipped-proximal-policy-optimization">
|
||
<h1>Clipped Proximal Policy Optimization<a class="headerlink" href="#clipped-proximal-policy-optimization" title="Permalink to this headline">¶</a></h1>
|
||
<p><strong>Actions space:</strong> Discrete | Continuous</p>
|
||
<p><strong>References:</strong> <a class="reference external" href="https://arxiv.org/pdf/1707.06347.pdf">Proximal Policy Optimization Algorithms</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/ppo.png" class="align-center" src="../../../_images/ppo.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-continuous-action">
|
||
<h3>Choosing an action - Continuous action<a class="headerlink" href="#choosing-an-action-continuous-action" title="Permalink to this headline">¶</a></h3>
|
||
<p>Same as in PPO.</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>Very similar to PPO, with several small (but very simplifying) changes:</p>
|
||
<ol class="arabic">
|
||
<li><p>Train both the value and policy networks, simultaneously, by defining a single loss function,
|
||
which is the sum of each of the networks loss functions. Then, back propagate gradients only once from this unified loss function.</p></li>
|
||
<li><p>The unified network’s optimizer is set to Adam (instead of L-BFGS for the value network as in PPO).</p></li>
|
||
<li><p>Value targets are now also calculated based on the GAE advantages.
|
||
In this method, the <span class="math notranslate nohighlight">\(V\)</span> values are predicted from the critic network, and then added to the GAE based advantages,
|
||
in order to get a <span class="math notranslate nohighlight">\(Q\)</span> value for each action. Now, since our critic network is predicting a <span class="math notranslate nohighlight">\(V\)</span> value for
|
||
each state, setting the <span class="math notranslate nohighlight">\(Q\)</span> calculated action-values as a target, will on average serve as a <span class="math notranslate nohighlight">\(V\)</span> state-value target.</p></li>
|
||
<li><p>Instead of adapting the penalizing KL divergence coefficient used in PPO, the likelihood ratio
|
||
<span class="math notranslate nohighlight">\(r_t(\theta) =\frac{\pi_{\theta}(a|s)}{\pi_{\theta_{old}}(a|s)}\)</span> is clipped, to achieve a similar effect.
|
||
This is done by defining the policy’s loss function to be the minimum between the standard surrogate loss and an epsilon
|
||
clipped surrogate loss:</p>
|
||
<p><span class="math notranslate nohighlight">\(L^{CLIP}(\theta)=E_{t}[min(r_t(\theta)\cdot \hat{A}_t, clip(r_t(\theta), 1-\epsilon, 1+\epsilon) \cdot \hat{A}_t)]\)</span></p>
|
||
</li>
|
||
</ol>
|
||
<dl class="class">
|
||
<dt id="rl_coach.agents.clipped_ppo_agent.ClippedPPOAlgorithmParameters">
|
||
<em class="property">class </em><code class="sig-prename descclassname">rl_coach.agents.clipped_ppo_agent.</code><code class="sig-name descname">ClippedPPOAlgorithmParameters</code><a class="reference internal" href="../../../_modules/rl_coach/agents/clipped_ppo_agent.html#ClippedPPOAlgorithmParameters"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.clipped_ppo_agent.ClippedPPOAlgorithmParameters" 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>policy_gradient_rescaler</strong> – (PolicyGradientRescaler)
|
||
This represents how the critic will be used to update the actor. The critic value function is typically used
|
||
to rescale the gradients calculated by the actor. There are several ways for doing this, such as using the
|
||
advantage of the action, or the generalized advantage estimation (GAE) value.</p></li>
|
||
<li><p><strong>gae_lambda</strong> – (float)
|
||
The <span class="math notranslate nohighlight">\(\lambda\)</span> value is used within the GAE function in order to weight different bootstrap length
|
||
estimations. Typical values are in the range 0.9-1, and define an exponential decay over the different
|
||
n-step estimations.</p></li>
|
||
<li><p><strong>clip_likelihood_ratio_using_epsilon</strong> – (float)
|
||
If not None, the likelihood ratio between the current and new policy in the PPO loss function will be
|
||
clipped to the range [1-clip_likelihood_ratio_using_epsilon, 1+clip_likelihood_ratio_using_epsilon].
|
||
This is typically used in the Clipped PPO version of PPO, and should be set to None in regular PPO
|
||
implementations.</p></li>
|
||
<li><p><strong>value_targets_mix_fraction</strong> – (float)
|
||
The targets for the value network are an exponential weighted moving average which uses this mix fraction to
|
||
define how much of the new targets will be taken into account when calculating the loss.
|
||
This value should be set to the range (0,1], where 1 means that only the new targets will be taken into account.</p></li>
|
||
<li><p><strong>estimate_state_value_using_gae</strong> – (bool)
|
||
If set to True, the state value will be estimated using the GAE technique.</p></li>
|
||
<li><p><strong>use_kl_regularization</strong> – (bool)
|
||
If set to True, the loss function will be regularized using the KL diveregence between the current and new
|
||
policy, to bound the change of the policy during the network update.</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 <span class="math notranslate nohighlight">\(eta\)</span> value defined by beta_entropy.</p></li>
|
||
<li><p><strong>optimization_epochs</strong> – (int)
|
||
For each training phase, the collected dataset will be used for multiple epochs, which are defined by the
|
||
optimization_epochs value.</p></li>
|
||
<li><p><strong>optimization_epochs</strong> – (Schedule)
|
||
Can be used to define a schedule over the clipping of the likelihood ratio.</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="ddpg.html" class="btn btn-neutral float-right" title="Deep Deterministic Policy Gradient" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a>
|
||
|
||
|
||
<a href="../imitation/cil.html" class="btn btn-neutral float-left" title="Conditional Imitation Learning" 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> |