mirror of
https://github.com/gryf/coach.git
synced 2026-03-13 21:25:51 +01:00
update of api docstrings across coach and tutorials [WIP] (#91)
* updating the documentation website * adding the built docs * update of api docstrings across coach and tutorials 0-2 * added some missing api documentation * New Sphinx based documentation
This commit is contained in:
Itai Caspi
@@ -0,0 +1,535 @@
|
||||
|
||||
|
||||
<!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>rl_coach.memories.episodic.episodic_experience_replay — Reinforcement Learning Coach 0.11.0 documentation</title>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<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 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">
|
||||
|
||||
|
||||
|
||||
<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="../../../../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>
|
||||
</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>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/agents/index.html">Agents</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/architectures/index.html">Architectures</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/environments/index.html">Environments</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/exploration_policies/index.html">Exploration Policies</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/filters/index.html">Filters</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/memories/index.html">Memories</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/core_types.html">Core Types</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/spaces.html">Spaces</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/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">Module code</a> »</li>
|
||||
|
||||
<li>rl_coach.memories.episodic.episodic_experience_replay</li>
|
||||
|
||||
|
||||
<li class="wy-breadcrumbs-aside">
|
||||
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
|
||||
|
||||
<hr/>
|
||||
</div>
|
||||
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
|
||||
<div itemprop="articleBody">
|
||||
|
||||
<h1>Source code for rl_coach.memories.episodic.episodic_experience_replay</h1><div class="highlight"><pre>
|
||||
<span></span><span class="c1">#</span>
|
||||
<span class="c1"># Copyright (c) 2017 Intel Corporation</span>
|
||||
<span class="c1">#</span>
|
||||
<span class="c1"># Licensed under the Apache License, Version 2.0 (the "License");</span>
|
||||
<span class="c1"># you may not use this file except in compliance with the License.</span>
|
||||
<span class="c1"># You may obtain a copy of the License at</span>
|
||||
<span class="c1">#</span>
|
||||
<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
|
||||
<span class="c1">#</span>
|
||||
<span class="c1"># Unless required by applicable law or agreed to in writing, software</span>
|
||||
<span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span>
|
||||
<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
|
||||
<span class="c1"># See the License for the specific language governing permissions and</span>
|
||||
<span class="c1"># limitations under the License.</span>
|
||||
<span class="c1">#</span>
|
||||
|
||||
<span class="kn">from</span> <span class="nn">typing</span> <span class="k">import</span> <span class="n">List</span><span class="p">,</span> <span class="n">Tuple</span><span class="p">,</span> <span class="n">Union</span><span class="p">,</span> <span class="n">Dict</span><span class="p">,</span> <span class="n">Any</span>
|
||||
|
||||
<span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
|
||||
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.core_types</span> <span class="k">import</span> <span class="n">Transition</span><span class="p">,</span> <span class="n">Episode</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.memories.memory</span> <span class="k">import</span> <span class="n">Memory</span><span class="p">,</span> <span class="n">MemoryGranularity</span><span class="p">,</span> <span class="n">MemoryParameters</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.utils</span> <span class="k">import</span> <span class="n">ReaderWriterLock</span>
|
||||
|
||||
|
||||
<span class="k">class</span> <span class="nc">EpisodicExperienceReplayParameters</span><span class="p">(</span><span class="n">MemoryParameters</span><span class="p">):</span>
|
||||
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">max_size</span> <span class="o">=</span> <span class="p">(</span><span class="n">MemoryGranularity</span><span class="o">.</span><span class="n">Transitions</span><span class="p">,</span> <span class="mi">1000000</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">n_step</span> <span class="o">=</span> <span class="o">-</span><span class="mi">1</span>
|
||||
|
||||
<span class="nd">@property</span>
|
||||
<span class="k">def</span> <span class="nf">path</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="k">return</span> <span class="s1">'rl_coach.memories.episodic.episodic_experience_replay:EpisodicExperienceReplay'</span>
|
||||
|
||||
|
||||
<div class="viewcode-block" id="EpisodicExperienceReplay"><a class="viewcode-back" href="../../../../components/memories/index.html#rl_coach.memories.episodic.EpisodicExperienceReplay">[docs]</a><span class="k">class</span> <span class="nc">EpisodicExperienceReplay</span><span class="p">(</span><span class="n">Memory</span><span class="p">):</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> A replay buffer that stores episodes of transitions. The additional structure allows performing various</span>
|
||||
<span class="sd"> calculations of total return and other values that depend on the sequential behavior of the transitions</span>
|
||||
<span class="sd"> in the episode.</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">max_size</span><span class="p">:</span> <span class="n">Tuple</span><span class="p">[</span><span class="n">MemoryGranularity</span><span class="p">,</span> <span class="nb">int</span><span class="p">]</span><span class="o">=</span><span class="p">(</span><span class="n">MemoryGranularity</span><span class="o">.</span><span class="n">Transitions</span><span class="p">,</span> <span class="mi">1000000</span><span class="p">),</span> <span class="n">n_step</span><span class="o">=-</span><span class="mi">1</span><span class="p">):</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> :param max_size: the maximum number of transitions or episodes to hold in the memory</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">max_size</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">n_step</span> <span class="o">=</span> <span class="n">n_step</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_buffer</span> <span class="o">=</span> <span class="p">[</span><span class="n">Episode</span><span class="p">(</span><span class="n">n_step</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">n_step</span><span class="p">)]</span> <span class="c1"># list of episodes</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">transitions</span> <span class="o">=</span> <span class="p">[]</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_length</span> <span class="o">=</span> <span class="mi">1</span> <span class="c1"># the episodic replay buffer starts with a single empty episode</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_num_transitions</span> <span class="o">=</span> <span class="mi">0</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_num_transitions_in_complete_episodes</span> <span class="o">=</span> <span class="mi">0</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reader_writer_lock</span> <span class="o">=</span> <span class="n">ReaderWriterLock</span><span class="p">()</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">length</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">lock</span><span class="p">:</span> <span class="nb">bool</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span> <span class="o">-></span> <span class="nb">int</span><span class="p">:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Get the number of episodes in the ER (even if they are not complete)</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="n">length</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_length</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_length</span> <span class="ow">is</span> <span class="ow">not</span> <span class="mi">0</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">_buffer</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">is_empty</span><span class="p">():</span>
|
||||
<span class="n">length</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_length</span> <span class="o">-</span> <span class="mi">1</span>
|
||||
|
||||
<span class="k">return</span> <span class="n">length</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">num_complete_episodes</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="sd">""" Get the number of complete episodes in ER """</span>
|
||||
<span class="n">length</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_length</span> <span class="o">-</span> <span class="mi">1</span>
|
||||
|
||||
<span class="k">return</span> <span class="n">length</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">num_transitions</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_num_transitions</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">num_transitions_in_complete_episodes</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_num_transitions_in_complete_episodes</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">sample</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">size</span><span class="p">:</span> <span class="nb">int</span><span class="p">)</span> <span class="o">-></span> <span class="n">List</span><span class="p">[</span><span class="n">Transition</span><span class="p">]:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Sample a batch of transitions form the replay buffer. If the requested size is larger than the number</span>
|
||||
<span class="sd"> of samples available in the replay buffer then the batch will return empty.</span>
|
||||
<span class="sd"> :param size: the size of the batch to sample</span>
|
||||
<span class="sd"> :return: a batch (list) of selected transitions from the replay buffer</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reader_writer_lock</span><span class="o">.</span><span class="n">lock_writing</span><span class="p">()</span>
|
||||
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_complete_episodes</span><span class="p">()</span> <span class="o">>=</span> <span class="mi">1</span><span class="p">:</span>
|
||||
<span class="n">transitions_idx</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">num_transitions_in_complete_episodes</span><span class="p">(),</span> <span class="n">size</span><span class="o">=</span><span class="n">size</span><span class="p">)</span>
|
||||
<span class="n">batch</span> <span class="o">=</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">transitions</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="n">transitions_idx</span><span class="p">]</span>
|
||||
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"The episodic replay buffer cannot be sampled since there are no complete episodes yet. "</span>
|
||||
<span class="s2">"There is currently 1 episodes with </span><span class="si">{}</span><span class="s2"> transitions"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_buffer</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">length</span><span class="p">()))</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reader_writer_lock</span><span class="o">.</span><span class="n">release_writing</span><span class="p">()</span>
|
||||
|
||||
<span class="k">return</span> <span class="n">batch</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_enforce_max_length</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Make sure that the size of the replay buffer does not pass the maximum size allowed.</span>
|
||||
<span class="sd"> If it passes the max size, the oldest episode in the replay buffer will be removed.</span>
|
||||
<span class="sd"> :return: None</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="n">granularity</span><span class="p">,</span> <span class="n">size</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">max_size</span>
|
||||
<span class="k">if</span> <span class="n">granularity</span> <span class="o">==</span> <span class="n">MemoryGranularity</span><span class="o">.</span><span class="n">Transitions</span><span class="p">:</span>
|
||||
<span class="k">while</span> <span class="n">size</span> <span class="o">!=</span> <span class="mi">0</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_transitions</span><span class="p">()</span> <span class="o">></span> <span class="n">size</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_remove_episode</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
|
||||
<span class="k">elif</span> <span class="n">granularity</span> <span class="o">==</span> <span class="n">MemoryGranularity</span><span class="o">.</span><span class="n">Episodes</span><span class="p">:</span>
|
||||
<span class="k">while</span> <span class="bp">self</span><span class="o">.</span><span class="n">length</span><span class="p">()</span> <span class="o">></span> <span class="n">size</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_remove_episode</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_update_episode</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">episode</span><span class="p">:</span> <span class="n">Episode</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="n">episode</span><span class="o">.</span><span class="n">update_transitions_rewards_and_bootstrap_data</span><span class="p">()</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">verify_last_episode_is_closed</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Verify that there is no open episodes in the replay buffer</span>
|
||||
<span class="sd"> :return: None</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reader_writer_lock</span><span class="o">.</span><span class="n">lock_writing_and_reading</span><span class="p">()</span>
|
||||
|
||||
<span class="n">last_episode</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="kc">False</span><span class="p">)</span>
|
||||
<span class="k">if</span> <span class="n">last_episode</span> <span class="ow">and</span> <span class="n">last_episode</span><span class="o">.</span><span class="n">length</span><span class="p">()</span> <span class="o">></span> <span class="mi">0</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">close_last_episode</span><span class="p">(</span><span class="n">lock</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reader_writer_lock</span><span class="o">.</span><span class="n">release_writing_and_reading</span><span class="p">()</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">close_last_episode</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">lock</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Close the last episode in the replay buffer and open a new one</span>
|
||||
<span class="sd"> :return: None</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="k">if</span> <span class="n">lock</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reader_writer_lock</span><span class="o">.</span><span class="n">lock_writing_and_reading</span><span class="p">()</span>
|
||||
|
||||
<span class="n">last_episode</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_buffer</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_num_transitions_in_complete_episodes</span> <span class="o">+=</span> <span class="n">last_episode</span><span class="o">.</span><span class="n">length</span><span class="p">()</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_length</span> <span class="o">+=</span> <span class="mi">1</span>
|
||||
|
||||
<span class="c1"># create a new Episode for the next transitions to be placed into</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_buffer</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">Episode</span><span class="p">(</span><span class="n">n_step</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">n_step</span><span class="p">))</span>
|
||||
|
||||
<span class="c1"># if update episode adds to the buffer, a new Episode needs to be ready first</span>
|
||||
<span class="c1"># it would be better if this were less state full</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_update_episode</span><span class="p">(</span><span class="n">last_episode</span><span class="p">)</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_enforce_max_length</span><span class="p">()</span>
|
||||
|
||||
<span class="k">if</span> <span class="n">lock</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reader_writer_lock</span><span class="o">.</span><span class="n">release_writing_and_reading</span><span class="p">()</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">store</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">transition</span><span class="p">:</span> <span class="n">Transition</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Store a new transition in the memory. If the transition game_over flag is on, this closes the episode and</span>
|
||||
<span class="sd"> creates a new empty episode.</span>
|
||||
<span class="sd"> Warning! using the episodic memory by storing individual transitions instead of episodes will use the default</span>
|
||||
<span class="sd"> Episode class parameters in order to create new episodes.</span>
|
||||
<span class="sd"> :param transition: a transition to store</span>
|
||||
<span class="sd"> :return: None</span>
|
||||
<span class="sd"> """</span>
|
||||
|
||||
<span class="c1"># Calling super.store() so that in case a memory backend is used, the memory backend can store this transition.</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">store</span><span class="p">(</span><span class="n">transition</span><span class="p">)</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reader_writer_lock</span><span class="o">.</span><span class="n">lock_writing_and_reading</span><span class="p">()</span>
|
||||
|
||||
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_buffer</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_buffer</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">Episode</span><span class="p">(</span><span class="n">n_step</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">n_step</span><span class="p">))</span>
|
||||
<span class="n">last_episode</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_buffer</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
|
||||
<span class="n">last_episode</span><span class="o">.</span><span class="n">insert</span><span class="p">(</span><span class="n">transition</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">transitions</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">transition</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_num_transitions</span> <span class="o">+=</span> <span class="mi">1</span>
|
||||
<span class="k">if</span> <span class="n">transition</span><span class="o">.</span><span class="n">game_over</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">close_last_episode</span><span class="p">(</span><span class="kc">False</span><span class="p">)</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_enforce_max_length</span><span class="p">()</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reader_writer_lock</span><span class="o">.</span><span class="n">release_writing_and_reading</span><span class="p">()</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">store_episode</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">episode</span><span class="p">:</span> <span class="n">Episode</span><span class="p">,</span> <span class="n">lock</span><span class="p">:</span> <span class="nb">bool</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Store a new episode in the memory.</span>
|
||||
<span class="sd"> :param episode: the new episode to store</span>
|
||||
<span class="sd"> :return: None</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="c1"># Calling super.store() so that in case a memory backend is used, the memory backend can store this episode.</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">store_episode</span><span class="p">(</span><span class="n">episode</span><span class="p">)</span>
|
||||
|
||||
<span class="k">if</span> <span class="n">lock</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reader_writer_lock</span><span class="o">.</span><span class="n">lock_writing_and_reading</span><span class="p">()</span>
|
||||
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_buffer</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">length</span><span class="p">()</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_buffer</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span> <span class="o">=</span> <span class="n">episode</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_buffer</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">episode</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">transitions</span><span class="o">.</span><span class="n">extend</span><span class="p">(</span><span class="n">episode</span><span class="o">.</span><span class="n">transitions</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_num_transitions</span> <span class="o">+=</span> <span class="n">episode</span><span class="o">.</span><span class="n">length</span><span class="p">()</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">close_last_episode</span><span class="p">(</span><span class="kc">False</span><span class="p">)</span>
|
||||
|
||||
<span class="k">if</span> <span class="n">lock</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reader_writer_lock</span><span class="o">.</span><span class="n">release_writing_and_reading</span><span class="p">()</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">get_episode</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">episode_index</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">lock</span><span class="p">:</span> <span class="nb">bool</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> <span class="o">-></span> <span class="n">Union</span><span class="p">[</span><span class="kc">None</span><span class="p">,</span> <span class="n">Episode</span><span class="p">]:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Returns the episode in the given index. If the episode does not exist, returns None instead.</span>
|
||||
<span class="sd"> :param episode_index: the index of the episode to return</span>
|
||||
<span class="sd"> :return: the corresponding episode</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="k">if</span> <span class="n">lock</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reader_writer_lock</span><span class="o">.</span><span class="n">lock_writing</span><span class="p">()</span>
|
||||
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">length</span><span class="p">()</span> <span class="o">==</span> <span class="mi">0</span> <span class="ow">or</span> <span class="n">episode_index</span> <span class="o">>=</span> <span class="bp">self</span><span class="o">.</span><span class="n">length</span><span class="p">():</span>
|
||||
<span class="n">episode</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="n">episode</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_buffer</span><span class="p">[</span><span class="n">episode_index</span><span class="p">]</span>
|
||||
|
||||
<span class="k">if</span> <span class="n">lock</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reader_writer_lock</span><span class="o">.</span><span class="n">release_writing</span><span class="p">()</span>
|
||||
<span class="k">return</span> <span class="n">episode</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_remove_episode</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">episode_index</span><span class="p">:</span> <span class="nb">int</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Remove the episode in the given index (even if it is not complete yet)</span>
|
||||
<span class="sd"> :param episode_index: the index of the episode to remove</span>
|
||||
<span class="sd"> :return: None</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_buffer</span><span class="p">)</span> <span class="o">></span> <span class="n">episode_index</span><span class="p">:</span>
|
||||
<span class="n">episode_length</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_buffer</span><span class="p">[</span><span class="n">episode_index</span><span class="p">]</span><span class="o">.</span><span class="n">length</span><span class="p">()</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_length</span> <span class="o">-=</span> <span class="mi">1</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_num_transitions</span> <span class="o">-=</span> <span class="n">episode_length</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_num_transitions_in_complete_episodes</span> <span class="o">-=</span> <span class="n">episode_length</span>
|
||||
<span class="k">del</span> <span class="bp">self</span><span class="o">.</span><span class="n">transitions</span><span class="p">[:</span><span class="n">episode_length</span><span class="p">]</span>
|
||||
<span class="k">del</span> <span class="bp">self</span><span class="o">.</span><span class="n">_buffer</span><span class="p">[</span><span class="n">episode_index</span><span class="p">]</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">remove_episode</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">episode_index</span><span class="p">:</span> <span class="nb">int</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Remove the episode in the given index (even if it is not complete yet)</span>
|
||||
<span class="sd"> :param episode_index: the index of the episode to remove</span>
|
||||
<span class="sd"> :return: None</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reader_writer_lock</span><span class="o">.</span><span class="n">lock_writing_and_reading</span><span class="p">()</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_remove_episode</span><span class="p">(</span><span class="n">episode_index</span><span class="p">)</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reader_writer_lock</span><span class="o">.</span><span class="n">release_writing_and_reading</span><span class="p">()</span>
|
||||
|
||||
<span class="c1"># for API compatibility</span>
|
||||
<span class="k">def</span> <span class="nf">get</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">episode_index</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">lock</span><span class="p">:</span> <span class="nb">bool</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> <span class="o">-></span> <span class="n">Union</span><span class="p">[</span><span class="kc">None</span><span class="p">,</span> <span class="n">Episode</span><span class="p">]:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Returns the episode in the given index. If the episode does not exist, returns None instead.</span>
|
||||
<span class="sd"> :param episode_index: the index of the episode to return</span>
|
||||
<span class="sd"> :return: the corresponding episode</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_episode</span><span class="p">(</span><span class="n">episode_index</span><span class="p">,</span> <span class="n">lock</span><span class="p">)</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">get_last_complete_episode</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">Union</span><span class="p">[</span><span class="kc">None</span><span class="p">,</span> <span class="n">Episode</span><span class="p">]:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Returns the last complete episode in the memory or None if there are no complete episodes</span>
|
||||
<span class="sd"> :return: None or the last complete episode</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reader_writer_lock</span><span class="o">.</span><span class="n">lock_writing</span><span class="p">()</span>
|
||||
|
||||
<span class="n">last_complete_episode_index</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_complete_episodes</span><span class="p">()</span> <span class="o">-</span> <span class="mi">1</span>
|
||||
<span class="n">episode</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
<span class="k">if</span> <span class="n">last_complete_episode_index</span> <span class="o">>=</span> <span class="mi">0</span><span class="p">:</span>
|
||||
<span class="n">episode</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">last_complete_episode_index</span><span class="p">)</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reader_writer_lock</span><span class="o">.</span><span class="n">release_writing</span><span class="p">()</span>
|
||||
|
||||
<span class="k">return</span> <span class="n">episode</span>
|
||||
|
||||
<span class="c1"># for API compatibility</span>
|
||||
<span class="k">def</span> <span class="nf">remove</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">episode_index</span><span class="p">:</span> <span class="nb">int</span><span class="p">):</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Remove the episode in the given index (even if it is not complete yet)</span>
|
||||
<span class="sd"> :param episode_index: the index of the episode to remove</span>
|
||||
<span class="sd"> :return: None</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">remove_episode</span><span class="p">(</span><span class="n">episode_index</span><span class="p">)</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">clean</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Clean the memory by removing all the episodes</span>
|
||||
<span class="sd"> :return: None</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reader_writer_lock</span><span class="o">.</span><span class="n">lock_writing_and_reading</span><span class="p">()</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">transitions</span> <span class="o">=</span> <span class="p">[]</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_buffer</span> <span class="o">=</span> <span class="p">[</span><span class="n">Episode</span><span class="p">(</span><span class="n">n_step</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">n_step</span><span class="p">)]</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_length</span> <span class="o">=</span> <span class="mi">1</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_num_transitions</span> <span class="o">=</span> <span class="mi">0</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_num_transitions_in_complete_episodes</span> <span class="o">=</span> <span class="mi">0</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reader_writer_lock</span><span class="o">.</span><span class="n">release_writing_and_reading</span><span class="p">()</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">mean_reward</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">:</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Get the mean reward in the replay buffer</span>
|
||||
<span class="sd"> :return: the mean reward</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reader_writer_lock</span><span class="o">.</span><span class="n">lock_writing</span><span class="p">()</span>
|
||||
|
||||
<span class="n">mean</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">mean</span><span class="p">([</span><span class="n">transition</span><span class="o">.</span><span class="n">reward</span> <span class="k">for</span> <span class="n">transition</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">transitions</span><span class="p">])</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">reader_writer_lock</span><span class="o">.</span><span class="n">release_writing</span><span class="p">()</span>
|
||||
<span class="k">return</span> <span class="n">mean</span></div>
|
||||
</pre></div>
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
<footer>
|
||||
|
||||
|
||||
<hr/>
|
||||
|
||||
<div role="contentinfo">
|
||||
<p>
|
||||
© Copyright 2018, 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" 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 async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.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>
|
||||
|
||||
</body>
|
||||
</html>
|
||||
@@ -0,0 +1,375 @@
|
||||
|
||||
|
||||
<!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>rl_coach.memories.episodic.episodic_hindsight_experience_replay — Reinforcement Learning Coach 0.11.0 documentation</title>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<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 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">
|
||||
|
||||
|
||||
|
||||
<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="../../../../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>
|
||||
</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>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/agents/index.html">Agents</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/architectures/index.html">Architectures</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/environments/index.html">Environments</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/exploration_policies/index.html">Exploration Policies</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/filters/index.html">Filters</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/memories/index.html">Memories</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/core_types.html">Core Types</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/spaces.html">Spaces</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/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">Module code</a> »</li>
|
||||
|
||||
<li>rl_coach.memories.episodic.episodic_hindsight_experience_replay</li>
|
||||
|
||||
|
||||
<li class="wy-breadcrumbs-aside">
|
||||
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
|
||||
|
||||
<hr/>
|
||||
</div>
|
||||
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
|
||||
<div itemprop="articleBody">
|
||||
|
||||
<h1>Source code for rl_coach.memories.episodic.episodic_hindsight_experience_replay</h1><div class="highlight"><pre>
|
||||
<span></span><span class="c1">#</span>
|
||||
<span class="c1"># Copyright (c) 2017 Intel Corporation</span>
|
||||
<span class="c1">#</span>
|
||||
<span class="c1"># Licensed under the Apache License, Version 2.0 (the "License");</span>
|
||||
<span class="c1"># you may not use this file except in compliance with the License.</span>
|
||||
<span class="c1"># You may obtain a copy of the License at</span>
|
||||
<span class="c1">#</span>
|
||||
<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
|
||||
<span class="c1">#</span>
|
||||
<span class="c1"># Unless required by applicable law or agreed to in writing, software</span>
|
||||
<span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span>
|
||||
<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
|
||||
<span class="c1"># See the License for the specific language governing permissions and</span>
|
||||
<span class="c1"># limitations under the License.</span>
|
||||
<span class="c1">#</span>
|
||||
|
||||
<span class="kn">import</span> <span class="nn">copy</span>
|
||||
<span class="kn">from</span> <span class="nn">enum</span> <span class="k">import</span> <span class="n">Enum</span>
|
||||
<span class="kn">from</span> <span class="nn">typing</span> <span class="k">import</span> <span class="n">Tuple</span><span class="p">,</span> <span class="n">List</span>
|
||||
|
||||
<span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
|
||||
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.core_types</span> <span class="k">import</span> <span class="n">Episode</span><span class="p">,</span> <span class="n">Transition</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.memories.episodic.episodic_experience_replay</span> <span class="k">import</span> <span class="n">EpisodicExperienceReplayParameters</span><span class="p">,</span> \
|
||||
<span class="n">EpisodicExperienceReplay</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.memories.non_episodic.experience_replay</span> <span class="k">import</span> <span class="n">MemoryGranularity</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.spaces</span> <span class="k">import</span> <span class="n">GoalsSpace</span>
|
||||
|
||||
|
||||
<span class="k">class</span> <span class="nc">HindsightGoalSelectionMethod</span><span class="p">(</span><span class="n">Enum</span><span class="p">):</span>
|
||||
<span class="n">Future</span> <span class="o">=</span> <span class="mi">0</span>
|
||||
<span class="n">Final</span> <span class="o">=</span> <span class="mi">1</span>
|
||||
<span class="n">Episode</span> <span class="o">=</span> <span class="mi">2</span>
|
||||
<span class="n">Random</span> <span class="o">=</span> <span class="mi">3</span>
|
||||
|
||||
|
||||
<span class="k">class</span> <span class="nc">EpisodicHindsightExperienceReplayParameters</span><span class="p">(</span><span class="n">EpisodicExperienceReplayParameters</span><span class="p">):</span>
|
||||
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">hindsight_transitions_per_regular_transition</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">hindsight_goal_selection_method</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">goals_space</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
|
||||
<span class="nd">@property</span>
|
||||
<span class="k">def</span> <span class="nf">path</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="k">return</span> <span class="s1">'rl_coach.memories.episodic.episodic_hindsight_experience_replay:EpisodicHindsightExperienceReplay'</span>
|
||||
|
||||
|
||||
<div class="viewcode-block" id="EpisodicHindsightExperienceReplay"><a class="viewcode-back" href="../../../../components/memories/index.html#rl_coach.memories.episodic.EpisodicHindsightExperienceReplay">[docs]</a><span class="k">class</span> <span class="nc">EpisodicHindsightExperienceReplay</span><span class="p">(</span><span class="n">EpisodicExperienceReplay</span><span class="p">):</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Implements Hindsight Experience Replay as described in the following paper: https://arxiv.org/pdf/1707.01495.pdf</span>
|
||||
|
||||
<span class="sd"> """</span>
|
||||
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">max_size</span><span class="p">:</span> <span class="n">Tuple</span><span class="p">[</span><span class="n">MemoryGranularity</span><span class="p">,</span> <span class="nb">int</span><span class="p">],</span>
|
||||
<span class="n">hindsight_transitions_per_regular_transition</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
|
||||
<span class="n">hindsight_goal_selection_method</span><span class="p">:</span> <span class="n">HindsightGoalSelectionMethod</span><span class="p">,</span>
|
||||
<span class="n">goals_space</span><span class="p">:</span> <span class="n">GoalsSpace</span><span class="p">):</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> :param max_size: The maximum size of the memory. should be defined in a granularity of Transitions</span>
|
||||
<span class="sd"> :param hindsight_transitions_per_regular_transition: The number of hindsight artificial transitions to generate</span>
|
||||
<span class="sd"> for each actual transition</span>
|
||||
<span class="sd"> :param hindsight_goal_selection_method: The method that will be used for generating the goals for the</span>
|
||||
<span class="sd"> hindsight transitions. Should be one of HindsightGoalSelectionMethod</span>
|
||||
<span class="sd"> :param goals_space: A GoalsSpace which defines the base properties of the goals space</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">max_size</span><span class="p">)</span>
|
||||
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">hindsight_transitions_per_regular_transition</span> <span class="o">=</span> <span class="n">hindsight_transitions_per_regular_transition</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">hindsight_goal_selection_method</span> <span class="o">=</span> <span class="n">hindsight_goal_selection_method</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">goals_space</span> <span class="o">=</span> <span class="n">goals_space</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">last_episode_start_idx</span> <span class="o">=</span> <span class="mi">0</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_sample_goal</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">episode_transitions</span><span class="p">:</span> <span class="n">List</span><span class="p">,</span> <span class="n">transition_index</span><span class="p">:</span> <span class="nb">int</span><span class="p">):</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Sample a single goal state according to the sampling method</span>
|
||||
<span class="sd"> :param episode_transitions: a list of all the transitions in the current episode</span>
|
||||
<span class="sd"> :param transition_index: the transition to start sampling from</span>
|
||||
<span class="sd"> :return: a goal corresponding to the sampled state</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">hindsight_goal_selection_method</span> <span class="o">==</span> <span class="n">HindsightGoalSelectionMethod</span><span class="o">.</span><span class="n">Future</span><span class="p">:</span>
|
||||
<span class="c1"># states that were observed in the same episode after the transition that is being replayed</span>
|
||||
<span class="n">selected_transition</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">choice</span><span class="p">(</span><span class="n">episode_transitions</span><span class="p">[</span><span class="n">transition_index</span><span class="o">+</span><span class="mi">1</span><span class="p">:])</span>
|
||||
<span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">hindsight_goal_selection_method</span> <span class="o">==</span> <span class="n">HindsightGoalSelectionMethod</span><span class="o">.</span><span class="n">Final</span><span class="p">:</span>
|
||||
<span class="c1"># the final state in the episode</span>
|
||||
<span class="n">selected_transition</span> <span class="o">=</span> <span class="n">episode_transitions</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
|
||||
<span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">hindsight_goal_selection_method</span> <span class="o">==</span> <span class="n">HindsightGoalSelectionMethod</span><span class="o">.</span><span class="n">Episode</span><span class="p">:</span>
|
||||
<span class="c1"># a random state from the episode</span>
|
||||
<span class="n">selected_transition</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">choice</span><span class="p">(</span><span class="n">episode_transitions</span><span class="p">)</span>
|
||||
<span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">hindsight_goal_selection_method</span> <span class="o">==</span> <span class="n">HindsightGoalSelectionMethod</span><span class="o">.</span><span class="n">Random</span><span class="p">:</span>
|
||||
<span class="c1"># a random state from the entire replay buffer</span>
|
||||
<span class="n">selected_transition</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">choice</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">transitions</span><span class="p">)</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"Invalid goal selection method was used for the hindsight goal selection"</span><span class="p">)</span>
|
||||
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">goals_space</span><span class="o">.</span><span class="n">goal_from_state</span><span class="p">(</span><span class="n">selected_transition</span><span class="o">.</span><span class="n">state</span><span class="p">)</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">_sample_goals</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">episode_transitions</span><span class="p">:</span> <span class="n">List</span><span class="p">,</span> <span class="n">transition_index</span><span class="p">:</span> <span class="nb">int</span><span class="p">):</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Sample a batch of goal states according to the sampling method</span>
|
||||
<span class="sd"> :param episode_transitions: a list of all the transitions in the current episode</span>
|
||||
<span class="sd"> :param transition_index: the transition to start sampling from</span>
|
||||
<span class="sd"> :return: a goal corresponding to the sampled state</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="k">return</span> <span class="p">[</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">_sample_goal</span><span class="p">(</span><span class="n">episode_transitions</span><span class="p">,</span> <span class="n">transition_index</span><span class="p">)</span>
|
||||
<span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">hindsight_transitions_per_regular_transition</span><span class="p">)</span>
|
||||
<span class="p">]</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">store_episode</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">episode</span><span class="p">:</span> <span class="n">Episode</span><span class="p">,</span> <span class="n">lock</span><span class="p">:</span> <span class="nb">bool</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="c1"># generate hindsight transitions only when an episode is finished</span>
|
||||
<span class="n">last_episode_transitions</span> <span class="o">=</span> <span class="n">copy</span><span class="o">.</span><span class="n">copy</span><span class="p">(</span><span class="n">episode</span><span class="o">.</span><span class="n">transitions</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># cannot create a future hindsight goal in the last transition of an episode</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">hindsight_goal_selection_method</span> <span class="o">==</span> <span class="n">HindsightGoalSelectionMethod</span><span class="o">.</span><span class="n">Future</span><span class="p">:</span>
|
||||
<span class="n">relevant_base_transitions</span> <span class="o">=</span> <span class="n">last_episode_transitions</span><span class="p">[:</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="n">relevant_base_transitions</span> <span class="o">=</span> <span class="n">last_episode_transitions</span>
|
||||
|
||||
<span class="c1"># for each transition in the last episode, create a set of hindsight transitions</span>
|
||||
<span class="k">for</span> <span class="n">transition_index</span><span class="p">,</span> <span class="n">transition</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">relevant_base_transitions</span><span class="p">):</span>
|
||||
<span class="n">sampled_goals</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_sample_goals</span><span class="p">(</span><span class="n">last_episode_transitions</span><span class="p">,</span> <span class="n">transition_index</span><span class="p">)</span>
|
||||
<span class="k">for</span> <span class="n">goal</span> <span class="ow">in</span> <span class="n">sampled_goals</span><span class="p">:</span>
|
||||
<span class="n">hindsight_transition</span> <span class="o">=</span> <span class="n">copy</span><span class="o">.</span><span class="n">copy</span><span class="p">(</span><span class="n">transition</span><span class="p">)</span>
|
||||
|
||||
<span class="k">if</span> <span class="n">hindsight_transition</span><span class="o">.</span><span class="n">state</span><span class="p">[</span><span class="s1">'desired_goal'</span><span class="p">]</span><span class="o">.</span><span class="n">shape</span> <span class="o">!=</span> <span class="n">goal</span><span class="o">.</span><span class="n">shape</span><span class="p">:</span>
|
||||
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">((</span>
|
||||
<span class="s1">'goal shape </span><span class="si">{goal_shape}</span><span class="s1"> already in transition is '</span>
|
||||
<span class="s1">'different than the one sampled as a hindsight goal '</span>
|
||||
<span class="s1">'</span><span class="si">{hindsight_goal_shape}</span><span class="s1">.'</span>
|
||||
<span class="p">)</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
|
||||
<span class="n">goal_shape</span><span class="o">=</span><span class="n">hindsight_transition</span><span class="o">.</span><span class="n">state</span><span class="p">[</span><span class="s1">'desired_goal'</span><span class="p">]</span><span class="o">.</span><span class="n">shape</span><span class="p">,</span>
|
||||
<span class="n">hindsight_goal_shape</span><span class="o">=</span><span class="n">goal</span><span class="o">.</span><span class="n">shape</span><span class="p">,</span>
|
||||
<span class="p">))</span>
|
||||
|
||||
<span class="c1"># update the goal in the transition</span>
|
||||
<span class="n">hindsight_transition</span><span class="o">.</span><span class="n">state</span><span class="p">[</span><span class="s1">'desired_goal'</span><span class="p">]</span> <span class="o">=</span> <span class="n">goal</span>
|
||||
<span class="n">hindsight_transition</span><span class="o">.</span><span class="n">next_state</span><span class="p">[</span><span class="s1">'desired_goal'</span><span class="p">]</span> <span class="o">=</span> <span class="n">goal</span>
|
||||
|
||||
<span class="c1"># update the reward and terminal signal according to the goal</span>
|
||||
<span class="n">hindsight_transition</span><span class="o">.</span><span class="n">reward</span><span class="p">,</span> <span class="n">hindsight_transition</span><span class="o">.</span><span class="n">game_over</span> <span class="o">=</span> \
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">goals_space</span><span class="o">.</span><span class="n">get_reward_for_goal_and_state</span><span class="p">(</span><span class="n">goal</span><span class="p">,</span> <span class="n">hindsight_transition</span><span class="o">.</span><span class="n">next_state</span><span class="p">)</span>
|
||||
|
||||
<span class="n">hindsight_transition</span><span class="o">.</span><span class="n">n_step_discounted_rewards</span> <span class="o">=</span> <span class="kc">None</span>
|
||||
<span class="n">episode</span><span class="o">.</span><span class="n">insert</span><span class="p">(</span><span class="n">hindsight_transition</span><span class="p">)</span>
|
||||
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">store_episode</span><span class="p">(</span><span class="n">episode</span><span class="p">)</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">store</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">transition</span><span class="p">:</span> <span class="n">Transition</span><span class="p">):</span>
|
||||
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"An episodic HER cannot store a single transition. Only full episodes are to be stored."</span><span class="p">)</span></div>
|
||||
</pre></div>
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
<footer>
|
||||
|
||||
|
||||
<hr/>
|
||||
|
||||
<div role="contentinfo">
|
||||
<p>
|
||||
© Copyright 2018, 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" 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 async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.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>
|
||||
|
||||
</body>
|
||||
</html>
|
||||
@@ -0,0 +1,300 @@
|
||||
|
||||
|
||||
<!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>rl_coach.memories.episodic.episodic_hrl_hindsight_experience_replay — Reinforcement Learning Coach 0.11.0 documentation</title>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<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 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">
|
||||
|
||||
|
||||
|
||||
<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="../../../../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>
|
||||
</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>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/agents/index.html">Agents</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/architectures/index.html">Architectures</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/environments/index.html">Environments</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/exploration_policies/index.html">Exploration Policies</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/filters/index.html">Filters</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/memories/index.html">Memories</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/core_types.html">Core Types</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/spaces.html">Spaces</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/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">Module code</a> »</li>
|
||||
|
||||
<li>rl_coach.memories.episodic.episodic_hrl_hindsight_experience_replay</li>
|
||||
|
||||
|
||||
<li class="wy-breadcrumbs-aside">
|
||||
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
|
||||
|
||||
<hr/>
|
||||
</div>
|
||||
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
|
||||
<div itemprop="articleBody">
|
||||
|
||||
<h1>Source code for rl_coach.memories.episodic.episodic_hrl_hindsight_experience_replay</h1><div class="highlight"><pre>
|
||||
<span></span><span class="c1">#</span>
|
||||
<span class="c1"># Copyright (c) 2017 Intel Corporation</span>
|
||||
<span class="c1">#</span>
|
||||
<span class="c1"># Licensed under the Apache License, Version 2.0 (the "License");</span>
|
||||
<span class="c1"># you may not use this file except in compliance with the License.</span>
|
||||
<span class="c1"># You may obtain a copy of the License at</span>
|
||||
<span class="c1">#</span>
|
||||
<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
|
||||
<span class="c1">#</span>
|
||||
<span class="c1"># Unless required by applicable law or agreed to in writing, software</span>
|
||||
<span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span>
|
||||
<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
|
||||
<span class="c1"># See the License for the specific language governing permissions and</span>
|
||||
<span class="c1"># limitations under the License.</span>
|
||||
<span class="c1">#</span>
|
||||
|
||||
<span class="kn">from</span> <span class="nn">typing</span> <span class="k">import</span> <span class="n">Tuple</span>
|
||||
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.core_types</span> <span class="k">import</span> <span class="n">Episode</span><span class="p">,</span> <span class="n">Transition</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.memories.episodic.episodic_hindsight_experience_replay</span> <span class="k">import</span> <span class="n">HindsightGoalSelectionMethod</span><span class="p">,</span> \
|
||||
<span class="n">EpisodicHindsightExperienceReplay</span><span class="p">,</span> <span class="n">EpisodicHindsightExperienceReplayParameters</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.memories.non_episodic.experience_replay</span> <span class="k">import</span> <span class="n">MemoryGranularity</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.spaces</span> <span class="k">import</span> <span class="n">GoalsSpace</span>
|
||||
|
||||
|
||||
<span class="k">class</span> <span class="nc">EpisodicHRLHindsightExperienceReplayParameters</span><span class="p">(</span><span class="n">EpisodicHindsightExperienceReplayParameters</span><span class="p">):</span>
|
||||
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
|
||||
|
||||
<span class="nd">@property</span>
|
||||
<span class="k">def</span> <span class="nf">path</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="k">return</span> <span class="s1">'rl_coach.memories.episodic.episodic_hrl_hindsight_experience_replay:EpisodicHRLHindsightExperienceReplay'</span>
|
||||
|
||||
|
||||
<div class="viewcode-block" id="EpisodicHRLHindsightExperienceReplay"><a class="viewcode-back" href="../../../../components/memories/index.html#rl_coach.memories.episodic.EpisodicHRLHindsightExperienceReplay">[docs]</a><span class="k">class</span> <span class="nc">EpisodicHRLHindsightExperienceReplay</span><span class="p">(</span><span class="n">EpisodicHindsightExperienceReplay</span><span class="p">):</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> Implements HRL Hindsight Experience Replay as described in the following paper: https://arxiv.org/abs/1805.08180</span>
|
||||
|
||||
<span class="sd"> This is the memory you should use if you want a shared hindsight experience replay buffer between multiple workers</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">max_size</span><span class="p">:</span> <span class="n">Tuple</span><span class="p">[</span><span class="n">MemoryGranularity</span><span class="p">,</span> <span class="nb">int</span><span class="p">],</span>
|
||||
<span class="n">hindsight_transitions_per_regular_transition</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
|
||||
<span class="n">hindsight_goal_selection_method</span><span class="p">:</span> <span class="n">HindsightGoalSelectionMethod</span><span class="p">,</span>
|
||||
<span class="n">goals_space</span><span class="p">:</span> <span class="n">GoalsSpace</span><span class="p">,</span>
|
||||
<span class="p">):</span>
|
||||
<span class="sd">"""</span>
|
||||
<span class="sd"> :param max_size: The maximum size of the memory. should be defined in a granularity of Transitions</span>
|
||||
<span class="sd"> :param hindsight_transitions_per_regular_transition: The number of hindsight artificial transitions to generate</span>
|
||||
<span class="sd"> for each actual transition</span>
|
||||
<span class="sd"> :param hindsight_goal_selection_method: The method that will be used for generating the goals for the</span>
|
||||
<span class="sd"> hindsight transitions. Should be one of HindsightGoalSelectionMethod</span>
|
||||
<span class="sd"> :param goals_space: A GoalsSpace which defines the properties of the goals</span>
|
||||
<span class="sd"> :param do_action_hindsight: Replace the action (sub-goal) given to a lower layer, with the actual achieved goal</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">max_size</span><span class="p">,</span> <span class="n">hindsight_transitions_per_regular_transition</span><span class="p">,</span> <span class="n">hindsight_goal_selection_method</span><span class="p">,</span>
|
||||
<span class="n">goals_space</span><span class="p">)</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">store_episode</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">episode</span><span class="p">:</span> <span class="n">Episode</span><span class="p">,</span> <span class="n">lock</span><span class="p">:</span> <span class="nb">bool</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="c1"># for a layer producing sub-goals, we will replace in hindsight the action (sub-goal) given to the lower</span>
|
||||
<span class="c1"># level with the actual achieved goal. the achieved goal (and observation) seen is assumed to be the same</span>
|
||||
<span class="c1"># for all levels - we can use this level's achieved goal instead of the lower level's one</span>
|
||||
|
||||
<span class="c1"># Calling super.store() so that in case a memory backend is used, the memory backend can store this episode.</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">store_episode</span><span class="p">(</span><span class="n">episode</span><span class="p">)</span>
|
||||
|
||||
<span class="k">for</span> <span class="n">transition</span> <span class="ow">in</span> <span class="n">episode</span><span class="o">.</span><span class="n">transitions</span><span class="p">:</span>
|
||||
<span class="n">new_achieved_goal</span> <span class="o">=</span> <span class="n">transition</span><span class="o">.</span><span class="n">next_state</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">goals_space</span><span class="o">.</span><span class="n">goal_name</span><span class="p">]</span>
|
||||
<span class="n">transition</span><span class="o">.</span><span class="n">action</span> <span class="o">=</span> <span class="n">new_achieved_goal</span>
|
||||
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">store_episode</span><span class="p">(</span><span class="n">episode</span><span class="p">)</span>
|
||||
|
||||
<span class="k">def</span> <span class="nf">store</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">transition</span><span class="p">:</span> <span class="n">Transition</span><span class="p">):</span>
|
||||
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"An episodic HER cannot store a single transition. Only full episodes are to be stored."</span><span class="p">)</span></div>
|
||||
</pre></div>
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
<footer>
|
||||
|
||||
|
||||
<hr/>
|
||||
|
||||
<div role="contentinfo">
|
||||
<p>
|
||||
© Copyright 2018, 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" 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 async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.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>
|
||||
|
||||
</body>
|
||||
</html>
|
||||
@@ -0,0 +1,260 @@
|
||||
|
||||
|
||||
<!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>rl_coach.memories.episodic.single_episode_buffer — Reinforcement Learning Coach 0.11.0 documentation</title>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<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 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">
|
||||
|
||||
|
||||
|
||||
<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="../../../../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>
|
||||
</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>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/agents/index.html">Agents</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/architectures/index.html">Architectures</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/environments/index.html">Environments</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/exploration_policies/index.html">Exploration Policies</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/filters/index.html">Filters</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/memories/index.html">Memories</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/core_types.html">Core Types</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/spaces.html">Spaces</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../../components/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">Module code</a> »</li>
|
||||
|
||||
<li>rl_coach.memories.episodic.single_episode_buffer</li>
|
||||
|
||||
|
||||
<li class="wy-breadcrumbs-aside">
|
||||
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
|
||||
|
||||
<hr/>
|
||||
</div>
|
||||
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
|
||||
<div itemprop="articleBody">
|
||||
|
||||
<h1>Source code for rl_coach.memories.episodic.single_episode_buffer</h1><div class="highlight"><pre>
|
||||
<span></span><span class="c1">#</span>
|
||||
<span class="c1"># Copyright (c) 2017 Intel Corporation</span>
|
||||
<span class="c1">#</span>
|
||||
<span class="c1"># Licensed under the Apache License, Version 2.0 (the "License");</span>
|
||||
<span class="c1"># you may not use this file except in compliance with the License.</span>
|
||||
<span class="c1"># You may obtain a copy of the License at</span>
|
||||
<span class="c1">#</span>
|
||||
<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
|
||||
<span class="c1">#</span>
|
||||
<span class="c1"># Unless required by applicable law or agreed to in writing, software</span>
|
||||
<span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span>
|
||||
<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
|
||||
<span class="c1"># See the License for the specific language governing permissions and</span>
|
||||
<span class="c1"># limitations under the License.</span>
|
||||
<span class="c1">#</span>
|
||||
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.memories.episodic.episodic_experience_replay</span> <span class="k">import</span> <span class="n">EpisodicExperienceReplay</span>
|
||||
<span class="kn">from</span> <span class="nn">rl_coach.memories.memory</span> <span class="k">import</span> <span class="n">MemoryGranularity</span><span class="p">,</span> <span class="n">MemoryParameters</span>
|
||||
|
||||
|
||||
<span class="k">class</span> <span class="nc">SingleEpisodeBufferParameters</span><span class="p">(</span><span class="n">MemoryParameters</span><span class="p">):</span>
|
||||
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
|
||||
<span class="k">del</span> <span class="bp">self</span><span class="o">.</span><span class="n">max_size</span>
|
||||
|
||||
<span class="nd">@property</span>
|
||||
<span class="k">def</span> <span class="nf">path</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="k">return</span> <span class="s1">'rl_coach.memories.episodic.single_episode_buffer:SingleEpisodeBuffer'</span>
|
||||
|
||||
|
||||
<div class="viewcode-block" id="SingleEpisodeBuffer"><a class="viewcode-back" href="../../../../components/memories/index.html#rl_coach.memories.episodic.SingleEpisodeBuffer">[docs]</a><span class="k">class</span> <span class="nc">SingleEpisodeBuffer</span><span class="p">(</span><span class="n">EpisodicExperienceReplay</span><span class="p">):</span>
|
||||
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">((</span><span class="n">MemoryGranularity</span><span class="o">.</span><span class="n">Episodes</span><span class="p">,</span> <span class="mi">1</span><span class="p">))</span></div>
|
||||
</pre></div>
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
<footer>
|
||||
|
||||
|
||||
<hr/>
|
||||
|
||||
<div role="contentinfo">
|
||||
<p>
|
||||
© Copyright 2018, 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" 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 async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.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>
|
||||
|
||||
</body>
|
||||
</html>
|
||||
Reference in New Issue
Block a user