mirror of
https://github.com/gryf/coach.git
synced 2025-12-18 03:30:19 +01:00
Enabling Coach Documentation to be run even when environments are not installed (#326)
This commit is contained in:
anabwan
@@ -8,7 +8,7 @@
|
||||
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
|
||||
<title>Memories — Reinforcement Learning Coach 0.11.0 documentation</title>
|
||||
<title>Memories — Reinforcement Learning Coach 0.12.1 documentation</title>
|
||||
|
||||
|
||||
|
||||
@@ -17,13 +17,21 @@
|
||||
|
||||
|
||||
|
||||
<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" />
|
||||
@@ -33,21 +41,16 @@
|
||||
<link rel="prev" title="Output Filters" href="../filters/output_filters.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">
|
||||
<div class="wy-side-nav-search" >
|
||||
|
||||
|
||||
|
||||
@@ -210,14 +213,11 @@
|
||||
<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>
|
||||
<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>max_size</strong> – the maximum number of transitions or episodes to hold in the memory</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
<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>
|
||||
@@ -227,22 +227,18 @@ in the episode.</p>
|
||||
<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>
|
||||
<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>max_size</strong> – The maximum size of the memory. should be defined in a granularity of Transitions</li>
|
||||
<li><strong>hindsight_transitions_per_regular_transition</strong> – The number of hindsight artificial transitions to generate
|
||||
for each actual transition</li>
|
||||
<li><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</li>
|
||||
<li><strong>goals_space</strong> – A GoalsSpace which defines the base properties of the goals space</li>
|
||||
<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>
|
||||
</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
</div>
|
||||
@@ -253,23 +249,19 @@ hindsight transitions. Should be one of HindsightGoalSelectionMethod</li>
|
||||
<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>
|
||||
<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>max_size</strong> – The maximum size of the memory. should be defined in a granularity of Transitions</li>
|
||||
<li><strong>hindsight_transitions_per_regular_transition</strong> – The number of hindsight artificial transitions to generate
|
||||
for each actual transition</li>
|
||||
<li><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</li>
|
||||
<li><strong>goals_space</strong> – A GoalsSpace which defines the properties of the goals</li>
|
||||
<li><strong>do_action_hindsight</strong> – Replace the action (sub-goal) given to a lower layer, with the actual achieved goal</li>
|
||||
<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>
|
||||
</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
</div>
|
||||
@@ -289,21 +281,17 @@ hindsight transitions. Should be one of HindsightGoalSelectionMethod</li>
|
||||
<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><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>max_size</strong> – the maximum number of transitions or episodes to hold in the memory</li>
|
||||
<li><strong>allow_duplicates_in_batch_sampling</strong> – allow having the same transition multiple times in a batch</li>
|
||||
<li><strong>num_classes</strong> – the number of classes in the replayed data</li>
|
||||
<li><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</li>
|
||||
<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>
|
||||
</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
</div>
|
||||
@@ -321,18 +309,14 @@ this parameter determines the key to retrieve the class index value</li>
|
||||
<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>
|
||||
<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>max_size</strong> – the maximum number of transitions or episodes to hold in the memory</li>
|
||||
<li><strong>allow_duplicates_in_batch_sampling</strong> – allow having the same transition multiple times in a batch</li>
|
||||
<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>
|
||||
</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
</div>
|
||||
@@ -343,21 +327,17 @@ this parameter determines the key to retrieve the class index value</li>
|
||||
<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 = <rl_coach.schedules.ConstantSchedule object>, 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>
|
||||
<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>max_size</strong> – the maximum number of transitions or episodes to hold in the memory</li>
|
||||
<li><strong>alpha</strong> – the alpha prioritization coefficient</li>
|
||||
<li><strong>beta</strong> – the beta parameter used for importance sampling</li>
|
||||
<li><strong>epsilon</strong> – a small value added to the priority of each transition</li>
|
||||
<li><strong>allow_duplicates_in_batch_sampling</strong> – allow having the same transition multiple times in a batch</li>
|
||||
<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>
|
||||
</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
</div>
|
||||
@@ -385,7 +365,7 @@ are constructed on top of.</p>
|
||||
<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" title="Output Filters" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left"></span> Previous</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>
|
||||
|
||||
@@ -394,7 +374,7 @@ are constructed on top of.</p>
|
||||
|
||||
<div role="contentinfo">
|
||||
<p>
|
||||
© Copyright 2018, Intel AI Lab
|
||||
© Copyright 2018-2019, Intel AI Lab
|
||||
|
||||
</p>
|
||||
</div>
|
||||
@@ -411,27 +391,16 @@ are constructed on top of.</p>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<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>
|
||||
</script>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
Reference in New Issue
Block a user