1
0
mirror of https://github.com/gryf/coach.git synced 2025-12-17 19:20:19 +01:00
Files
coach/docs/components/memories/index.html
anabwan ddffac8570 fixed release version (#333)
* fixed release version

* update docs
2019-05-28 11:11:15 +03:00

406 lines
23 KiB
HTML
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
<!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>Memories &mdash; 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="Memory Backends" href="../memory_backends/index.html" />
<link rel="prev" title="Output Filters" href="../filters/output_filters.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"><a class="reference internal" href="../agents/index.html">Agents</a></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 current"><a class="current reference internal" href="#">Memories</a><ul>
<li class="toctree-l2"><a class="reference internal" href="#episodic-memories">Episodic Memories</a><ul>
<li class="toctree-l3"><a class="reference internal" href="#episodicexperiencereplay">EpisodicExperienceReplay</a></li>
<li class="toctree-l3"><a class="reference internal" href="#episodichindsightexperiencereplay">EpisodicHindsightExperienceReplay</a></li>
<li class="toctree-l3"><a class="reference internal" href="#episodichrlhindsightexperiencereplay">EpisodicHRLHindsightExperienceReplay</a></li>
<li class="toctree-l3"><a class="reference internal" href="#singleepisodebuffer">SingleEpisodeBuffer</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="#non-episodic-memories">Non-Episodic Memories</a><ul>
<li class="toctree-l3"><a class="reference internal" href="#balancedexperiencereplay">BalancedExperienceReplay</a></li>
<li class="toctree-l3"><a class="reference internal" href="#qdnd">QDND</a></li>
<li class="toctree-l3"><a class="reference internal" href="#experiencereplay">ExperienceReplay</a></li>
<li class="toctree-l3"><a class="reference internal" href="#prioritizedexperiencereplay">PrioritizedExperienceReplay</a></li>
<li class="toctree-l3"><a class="reference internal" href="#transitioncollection">TransitionCollection</a></li>
</ul>
</li>
</ul>
</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> &raquo;</li>
<li>Memories</li>
<li class="wy-breadcrumbs-aside">
<a href="../../_sources/components/memories/index.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="memories">
<h1>Memories<a class="headerlink" href="#memories" title="Permalink to this headline"></a></h1>
<div class="section" id="episodic-memories">
<h2>Episodic Memories<a class="headerlink" href="#episodic-memories" title="Permalink to this headline"></a></h2>
<div class="section" id="episodicexperiencereplay">
<h3>EpisodicExperienceReplay<a class="headerlink" href="#episodicexperiencereplay" title="Permalink to this headline"></a></h3>
<dl class="class">
<dt id="rl_coach.memories.episodic.EpisodicExperienceReplay">
<em class="property">class </em><code class="descclassname">rl_coach.memories.episodic.</code><code class="descname">EpisodicExperienceReplay</code><span class="sig-paren">(</span><em>max_size: Tuple[rl_coach.memories.memory.MemoryGranularity</em>, <em>int] = (&lt;MemoryGranularity.Transitions: 0&gt;</em>, <em>1000000)</em>, <em>n_step=-1</em>, <em>train_to_eval_ratio: int = 1</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/memories/episodic/episodic_experience_replay.html#EpisodicExperienceReplay"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.memories.episodic.EpisodicExperienceReplay" title="Permalink to this definition"></a></dt>
<dd><p>A replay buffer that stores episodes of transitions. The additional structure allows performing various
calculations of total return and other values that depend on the sequential behavior of the transitions
in the episode.</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters</dt>
<dd class="field-odd"><p><strong>max_size</strong> the maximum number of transitions or episodes to hold in the memory</p>
</dd>
</dl>
</dd></dl>
</div>
<div class="section" id="episodichindsightexperiencereplay">
<h3>EpisodicHindsightExperienceReplay<a class="headerlink" href="#episodichindsightexperiencereplay" title="Permalink to this headline"></a></h3>
<dl class="class">
<dt id="rl_coach.memories.episodic.EpisodicHindsightExperienceReplay">
<em class="property">class </em><code class="descclassname">rl_coach.memories.episodic.</code><code class="descname">EpisodicHindsightExperienceReplay</code><span class="sig-paren">(</span><em>max_size: Tuple[rl_coach.memories.memory.MemoryGranularity, int], hindsight_transitions_per_regular_transition: int, hindsight_goal_selection_method: rl_coach.memories.episodic.episodic_hindsight_experience_replay.HindsightGoalSelectionMethod, goals_space: rl_coach.spaces.GoalsSpace</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/memories/episodic/episodic_hindsight_experience_replay.html#EpisodicHindsightExperienceReplay"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.memories.episodic.EpisodicHindsightExperienceReplay" title="Permalink to this definition"></a></dt>
<dd><p>Implements Hindsight Experience Replay as described in the following paper: <a class="reference external" href="https://arxiv.org/pdf/1707.01495.pdf">https://arxiv.org/pdf/1707.01495.pdf</a></p>
<dl class="field-list simple">
<dt class="field-odd">Parameters</dt>
<dd class="field-odd"><ul class="simple">
<li><p><strong>max_size</strong> The maximum size of the memory. should be defined in a granularity of Transitions</p></li>
<li><p><strong>hindsight_transitions_per_regular_transition</strong> The number of hindsight artificial transitions to generate
for each actual transition</p></li>
<li><p><strong>hindsight_goal_selection_method</strong> The method that will be used for generating the goals for the
hindsight transitions. Should be one of HindsightGoalSelectionMethod</p></li>
<li><p><strong>goals_space</strong> A GoalsSpace which defines the base properties of the goals space</p></li>
</ul>
</dd>
</dl>
</dd></dl>
</div>
<div class="section" id="episodichrlhindsightexperiencereplay">
<h3>EpisodicHRLHindsightExperienceReplay<a class="headerlink" href="#episodichrlhindsightexperiencereplay" title="Permalink to this headline"></a></h3>
<dl class="class">
<dt id="rl_coach.memories.episodic.EpisodicHRLHindsightExperienceReplay">
<em class="property">class </em><code class="descclassname">rl_coach.memories.episodic.</code><code class="descname">EpisodicHRLHindsightExperienceReplay</code><span class="sig-paren">(</span><em>max_size: Tuple[rl_coach.memories.memory.MemoryGranularity, int], hindsight_transitions_per_regular_transition: int, hindsight_goal_selection_method: rl_coach.memories.episodic.episodic_hindsight_experience_replay.HindsightGoalSelectionMethod, goals_space: rl_coach.spaces.GoalsSpace</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/memories/episodic/episodic_hrl_hindsight_experience_replay.html#EpisodicHRLHindsightExperienceReplay"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.memories.episodic.EpisodicHRLHindsightExperienceReplay" title="Permalink to this definition"></a></dt>
<dd><p>Implements HRL Hindsight Experience Replay as described in the following paper: <a class="reference external" href="https://arxiv.org/abs/1805.08180">https://arxiv.org/abs/1805.08180</a></p>
<p>This is the memory you should use if you want a shared hindsight experience replay buffer between multiple workers</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters</dt>
<dd class="field-odd"><ul class="simple">
<li><p><strong>max_size</strong> The maximum size of the memory. should be defined in a granularity of Transitions</p></li>
<li><p><strong>hindsight_transitions_per_regular_transition</strong> The number of hindsight artificial transitions to generate
for each actual transition</p></li>
<li><p><strong>hindsight_goal_selection_method</strong> The method that will be used for generating the goals for the
hindsight transitions. Should be one of HindsightGoalSelectionMethod</p></li>
<li><p><strong>goals_space</strong> A GoalsSpace which defines the properties of the goals</p></li>
<li><p><strong>do_action_hindsight</strong> Replace the action (sub-goal) given to a lower layer, with the actual achieved goal</p></li>
</ul>
</dd>
</dl>
</dd></dl>
</div>
<div class="section" id="singleepisodebuffer">
<h3>SingleEpisodeBuffer<a class="headerlink" href="#singleepisodebuffer" title="Permalink to this headline"></a></h3>
<dl class="class">
<dt id="rl_coach.memories.episodic.SingleEpisodeBuffer">
<em class="property">class </em><code class="descclassname">rl_coach.memories.episodic.</code><code class="descname">SingleEpisodeBuffer</code><a class="reference internal" href="../../_modules/rl_coach/memories/episodic/single_episode_buffer.html#SingleEpisodeBuffer"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.memories.episodic.SingleEpisodeBuffer" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
</div>
</div>
<div class="section" id="non-episodic-memories">
<h2>Non-Episodic Memories<a class="headerlink" href="#non-episodic-memories" title="Permalink to this headline"></a></h2>
<div class="section" id="balancedexperiencereplay">
<h3>BalancedExperienceReplay<a class="headerlink" href="#balancedexperiencereplay" title="Permalink to this headline"></a></h3>
<dl class="class">
<dt id="rl_coach.memories.non_episodic.BalancedExperienceReplay">
<em class="property">class </em><code class="descclassname">rl_coach.memories.non_episodic.</code><code class="descname">BalancedExperienceReplay</code><span class="sig-paren">(</span><em>max_size: Tuple[rl_coach.memories.memory.MemoryGranularity, int], allow_duplicates_in_batch_sampling: bool = True, num_classes: int = 0, state_key_with_the_class_index: Any = 'class'</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/memories/non_episodic/balanced_experience_replay.html#BalancedExperienceReplay"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.memories.non_episodic.BalancedExperienceReplay" 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>max_size</strong> the maximum number of transitions or episodes to hold in the memory</p></li>
<li><p><strong>allow_duplicates_in_batch_sampling</strong> allow having the same transition multiple times in a batch</p></li>
<li><p><strong>num_classes</strong> the number of classes in the replayed data</p></li>
<li><p><strong>state_key_with_the_class_index</strong> the class index is assumed to be a value in the state dictionary.
this parameter determines the key to retrieve the class index value</p></li>
</ul>
</dd>
</dl>
</dd></dl>
</div>
<div class="section" id="qdnd">
<h3>QDND<a class="headerlink" href="#qdnd" title="Permalink to this headline"></a></h3>
<dl class="class">
<dt id="rl_coach.memories.non_episodic.QDND">
<em class="property">class </em><code class="descclassname">rl_coach.memories.non_episodic.</code><code class="descname">QDND</code><span class="sig-paren">(</span><em>dict_size</em>, <em>key_width</em>, <em>num_actions</em>, <em>new_value_shift_coefficient=0.1</em>, <em>key_error_threshold=0.01</em>, <em>learning_rate=0.01</em>, <em>num_neighbors=50</em>, <em>return_additional_data=False</em>, <em>override_existing_keys=False</em>, <em>rebuild_on_every_update=False</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/memories/non_episodic/differentiable_neural_dictionary.html#QDND"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.memories.non_episodic.QDND" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
</div>
<div class="section" id="experiencereplay">
<h3>ExperienceReplay<a class="headerlink" href="#experiencereplay" title="Permalink to this headline"></a></h3>
<dl class="class">
<dt id="rl_coach.memories.non_episodic.ExperienceReplay">
<em class="property">class </em><code class="descclassname">rl_coach.memories.non_episodic.</code><code class="descname">ExperienceReplay</code><span class="sig-paren">(</span><em>max_size: Tuple[rl_coach.memories.memory.MemoryGranularity, int], allow_duplicates_in_batch_sampling: bool = True</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/memories/non_episodic/experience_replay.html#ExperienceReplay"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.memories.non_episodic.ExperienceReplay" title="Permalink to this definition"></a></dt>
<dd><p>A regular replay buffer which stores transition without any additional structure</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters</dt>
<dd class="field-odd"><ul class="simple">
<li><p><strong>max_size</strong> the maximum number of transitions or episodes to hold in the memory</p></li>
<li><p><strong>allow_duplicates_in_batch_sampling</strong> allow having the same transition multiple times in a batch</p></li>
</ul>
</dd>
</dl>
</dd></dl>
</div>
<div class="section" id="prioritizedexperiencereplay">
<h3>PrioritizedExperienceReplay<a class="headerlink" href="#prioritizedexperiencereplay" title="Permalink to this headline"></a></h3>
<dl class="class">
<dt id="rl_coach.memories.non_episodic.PrioritizedExperienceReplay">
<em class="property">class </em><code class="descclassname">rl_coach.memories.non_episodic.</code><code class="descname">PrioritizedExperienceReplay</code><span class="sig-paren">(</span><em>max_size: Tuple[rl_coach.memories.memory.MemoryGranularity, int], alpha: float = 0.6, beta: rl_coach.schedules.Schedule = &lt;rl_coach.schedules.ConstantSchedule object&gt;, epsilon: float = 1e-06, allow_duplicates_in_batch_sampling: bool = True</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/memories/non_episodic/prioritized_experience_replay.html#PrioritizedExperienceReplay"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.memories.non_episodic.PrioritizedExperienceReplay" title="Permalink to this definition"></a></dt>
<dd><p>This is the proportional sampling variant of the prioritized experience replay as described
in <a class="reference external" href="https://arxiv.org/pdf/1511.05952.pdf">https://arxiv.org/pdf/1511.05952.pdf</a>.</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters</dt>
<dd class="field-odd"><ul class="simple">
<li><p><strong>max_size</strong> the maximum number of transitions or episodes to hold in the memory</p></li>
<li><p><strong>alpha</strong> the alpha prioritization coefficient</p></li>
<li><p><strong>beta</strong> the beta parameter used for importance sampling</p></li>
<li><p><strong>epsilon</strong> a small value added to the priority of each transition</p></li>
<li><p><strong>allow_duplicates_in_batch_sampling</strong> allow having the same transition multiple times in a batch</p></li>
</ul>
</dd>
</dl>
</dd></dl>
</div>
<div class="section" id="transitioncollection">
<h3>TransitionCollection<a class="headerlink" href="#transitioncollection" title="Permalink to this headline"></a></h3>
<dl class="class">
<dt id="rl_coach.memories.non_episodic.TransitionCollection">
<em class="property">class </em><code class="descclassname">rl_coach.memories.non_episodic.</code><code class="descname">TransitionCollection</code><a class="reference internal" href="../../_modules/rl_coach/memories/non_episodic/transition_collection.html#TransitionCollection"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.memories.non_episodic.TransitionCollection" title="Permalink to this definition"></a></dt>
<dd><p>Simple python implementation of transitions collection non-episodic memories
are constructed on top of.</p>
</dd></dl>
</div>
</div>
</div>
</div>
</div>
<footer>
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
<a href="../memory_backends/index.html" class="btn btn-neutral float-right" title="Memory Backends" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a>
<a href="../filters/output_filters.html" class="btn btn-neutral float-left" title="Output Filters" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left"></span> Previous</a>
</div>
<hr/>
<div role="contentinfo">
<p>
&copy; 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>