gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2025-12-18 03:30:19 +01:00
Code Issues Projects Releases Wiki Activity

Enabling Coach Documentation to be run even when environments are not installed (#326)

Browse Source
This commit is contained in:
anabwan
2019-05-27 10:46:07 +03:00
committed by Gal Leibovich
parent 2b7d536da4
commit 342b7184bc
157 changed files with 5167 additions and 7477 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
docs/_modules/rl_coach/memories/backend/redis.html
View File

@@ -8,7 +8,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>rl_coach.memories.backend.redis &mdash; Reinforcement Learning Coach 0.11.0 documentation</title>
<title>rl_coach.memories.backend.redis &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
@@ -17,13 +17,21 @@
<script type="text/javascript" src="../../../../_static/js/modernizr.min.js"></script>
<script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../../_static/doctools.js"></script>
<script type="text/javascript" src="../../../../_static/language_data.js"></script>
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/javascript" src="../../../../_static/js/theme.js"></script>
<link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" />
<link rel="stylesheet" href="../../../../_static/pygments.css" type="text/css" />
<link rel="stylesheet" href="../../../../_static/css/custom.css" type="text/css" />
@@ -31,21 +39,16 @@
<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">
<div class="wy-side-nav-search" >
@@ -415,7 +418,7 @@
<div role="contentinfo">
<p>
&copy; Copyright 2018, Intel AI Lab
&copy; Copyright 2018-2019, Intel AI Lab
</p>
</div>
@@ -432,27 +435,16 @@
<script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../../_static/doctools.js"></script>
<script type="text/javascript" src="../../../../_static/language_data.js"></script>
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/javascript" src="../../../../_static/js/theme.js"></script>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</script>
</body>
</html>

128
docs/_modules/rl_coach/memories/episodic/episodic_experience_replay.html
View File

@@ -8,7 +8,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>rl_coach.memories.episodic.episodic_experience_replay &mdash; Reinforcement Learning Coach 0.11.0 documentation</title>
<title>rl_coach.memories.episodic.episodic_experience_replay &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
@@ -17,13 +17,21 @@
<script type="text/javascript" src="../../../../_static/js/modernizr.min.js"></script>
<script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../../_static/doctools.js"></script>
<script type="text/javascript" src="../../../../_static/language_data.js"></script>
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/javascript" src="../../../../_static/js/theme.js"></script>
<link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" />
<link rel="stylesheet" href="../../../../_static/pygments.css" type="text/css" />
<link rel="stylesheet" href="../../../../_static/css/custom.css" type="text/css" />
@@ -31,21 +39,16 @@
<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">
<div class="wy-side-nav-search" >
@@ -195,6 +198,8 @@
<span class="c1"># limitations under the License.</span>
<span class="c1">#</span>
<span class="kn">import</span> <span class="nn">ast</span>
<span class="kn">from</span> <span class="nn">copy</span> <span class="k">import</span> <span class="n">deepcopy</span>
<span class="kn">import</span> <span class="nn">math</span>
<span class="kn">import</span> <span class="nn">pandas</span> <span class="k">as</span> <span class="nn">pd</span>
@@ -244,6 +249,10 @@
<span class="bp">self</span><span class="o">.</span><span class="n">last_training_set_episode_id</span> <span class="o">=</span> <span class="kc">None</span> <span class="c1"># used in batch-rl</span>
<span class="bp">self</span><span class="o">.</span><span class="n">last_training_set_transition_id</span> <span class="o">=</span> <span class="kc">None</span> <span class="c1"># used in batch-rl</span>
<span class="bp">self</span><span class="o">.</span><span class="n">train_to_eval_ratio</span> <span class="o">=</span> <span class="n">train_to_eval_ratio</span> <span class="c1"># used in batch-rl</span>
<span class="bp">self</span><span class="o">.</span><span class="n">evaluation_dataset_as_episodes</span> <span class="o">=</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">evaluation_dataset_as_transitions</span> <span class="o">=</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">frozen</span> <span class="o">=</span> <span class="kc">False</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">-&gt;</span> <span class="nb">int</span><span class="p">:</span>
<span class="sd">&quot;&quot;&quot;</span>
@@ -317,10 +326,12 @@
<span class="sd"> Shuffle all the episodes in the replay buffer</span>
<span class="sd"> :return:</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">assert_not_frozen</span><span class="p">()</span>
<span class="n">random</span><span class="o">.</span><span class="n">shuffle</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="bp">self</span><span class="o">.</span><span class="n">transitions</span> <span class="o">=</span> <span class="p">[</span><span class="n">t</span> <span class="k">for</span> <span class="n">e</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_buffer</span> <span class="k">for</span> <span class="n">t</span> <span class="ow">in</span> <span class="n">e</span><span class="o">.</span><span class="n">transitions</span><span class="p">]</span>
<span class="k">def</span> <span class="nf">get_shuffled_data_generator</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">-&gt;</span> <span class="n">List</span><span class="p">[</span><span class="n">Transition</span><span class="p">]:</span>
<span class="k">def</span> <span class="nf">get_shuffled_training_data_generator</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">-&gt;</span> <span class="n">List</span><span class="p">[</span><span class="n">Transition</span><span class="p">]:</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Get an generator for iterating through the shuffled replay buffer, for processing the data in epochs.</span>
<span class="sd"> If the requested size is larger than the number of samples available in the replay buffer then the batch will</span>
@@ -331,15 +342,6 @@
<span class="sd"> :return: a batch (list) of selected transitions from the replay buffer</span>
<span class="sd"> &quot;&quot;&quot;</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">last_training_set_transition_id</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">train_to_eval_ratio</span> <span class="o">&lt;</span> <span class="mi">0</span> <span class="ow">or</span> <span class="bp">self</span><span class="o">.</span><span class="n">train_to_eval_ratio</span> <span class="o">&gt;=</span> <span class="mi">1</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">&#39;train_to_eval_ratio should be in the (0, 1] range.&#39;</span><span class="p">)</span>
<span class="n">transition</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">transitions</span><span class="p">[</span><span class="nb">round</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">train_to_eval_ratio</span> <span class="o">*</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">episode_num</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_episode_for_transition</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">last_training_set_episode_id</span> <span class="o">=</span> <span class="n">episode_num</span>
<span class="bp">self</span><span class="o">.</span><span class="n">last_training_set_transition_id</span> <span class="o">=</span> \
<span class="nb">len</span><span class="p">([</span><span class="n">t</span> <span class="k">for</span> <span class="n">e</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_all_complete_episodes_from_to</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">last_training_set_episode_id</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)</span> <span class="k">for</span> <span class="n">t</span> <span class="ow">in</span> <span class="n">e</span><span class="p">])</span>
<span class="n">shuffled_transition_indices</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">last_training_set_transition_id</span><span class="p">))</span>
<span class="n">random</span><span class="o">.</span><span class="n">shuffle</span><span class="p">(</span><span class="n">shuffled_transition_indices</span><span class="p">)</span>
@@ -436,6 +438,7 @@
<span class="sd"> :param transition: a transition to store</span>
<span class="sd"> :return: None</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">assert_not_frozen</span><span class="p">()</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>
@@ -461,6 +464,8 @@
<span class="sd"> :param episode: the new episode to store</span>
<span class="sd"> :return: None</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">assert_not_frozen</span><span class="p">()</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>
@@ -502,6 +507,8 @@
<span class="sd"> :param episode_index: the index of the episode to remove</span>
<span class="sd"> :return: None</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">assert_not_frozen</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">&gt;</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>
@@ -561,6 +568,7 @@
<span class="sd"> Clean the memory by removing all the episodes</span>
<span class="sd"> :return: None</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">assert_not_frozen</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="bp">self</span><span class="o">.</span><span class="n">transitions</span> <span class="o">=</span> <span class="p">[]</span>
@@ -589,6 +597,8 @@
<span class="sd"> The csv file is assumed to include a list of transitions.</span>
<span class="sd"> :param csv_dataset: A construct which holds the dataset parameters</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">assert_not_frozen</span><span class="p">()</span>
<span class="n">df</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">read_csv</span><span class="p">(</span><span class="n">csv_dataset</span><span class="o">.</span><span class="n">filepath</span><span class="p">)</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">df</span><span class="p">)</span> <span class="o">&gt;</span> <span class="bp">self</span><span class="o">.</span><span class="n">max_size</span><span class="p">[</span><span class="mi">1</span><span class="p">]:</span>
<span class="n">screen</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span><span class="s2">&quot;Warning! The number of transitions to load into the replay buffer (</span><span class="si">{}</span><span class="s2">) is &quot;</span>
@@ -625,7 +635,58 @@
<span class="n">progress_bar</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">episode_ids</span><span class="p">))</span>
<span class="n">progress_bar</span><span class="o">.</span><span class="n">close</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">shuffle_episodes</span><span class="p">()</span></div>
<span class="bp">self</span><span class="o">.</span><span class="n">shuffle_episodes</span><span class="p">()</span>
<span class="k">def</span> <span class="nf">freeze</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Freezing the replay buffer does not allow any new transitions to be added to the memory.</span>
<span class="sd"> Useful when working with a dataset (e.g. batch-rl or imitation learning).</span>
<span class="sd"> :return: None</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">frozen</span> <span class="o">=</span> <span class="kc">True</span>
<span class="k">def</span> <span class="nf">assert_not_frozen</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Check that the memory is not frozen, and can be changed.</span>
<span class="sd"> :return:</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">assert</span> <span class="bp">self</span><span class="o">.</span><span class="n">frozen</span> <span class="ow">is</span> <span class="kc">False</span><span class="p">,</span> <span class="s2">&quot;Memory is frozen, and cannot be changed.&quot;</span>
<span class="k">def</span> <span class="nf">prepare_evaluation_dataset</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Gather the memory content that will be used for off-policy evaluation in episodes and transitions format</span>
<span class="sd"> :return:</span>
<span class="sd"> &quot;&quot;&quot;</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">_split_training_and_evaluation_datasets</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">evaluation_dataset_as_episodes</span> <span class="o">=</span> <span class="n">deepcopy</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">get_all_complete_episodes_from_to</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">get_last_training_set_episode_id</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_complete_episodes</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">evaluation_dataset_as_episodes</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">&#39;train_to_eval_ratio is too high causing the evaluation set to be empty. &#39;</span>
<span class="s1">&#39;Consider decreasing its value.&#39;</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">evaluation_dataset_as_transitions</span> <span class="o">=</span> <span class="p">[</span><span class="n">t</span> <span class="k">for</span> <span class="n">e</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">evaluation_dataset_as_episodes</span>
<span class="k">for</span> <span class="n">t</span> <span class="ow">in</span> <span class="n">e</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_and_reading</span><span class="p">()</span>
<span class="k">def</span> <span class="nf">_split_training_and_evaluation_datasets</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> If the data in the buffer was not split to training and evaluation yet, split it accordingly.</span>
<span class="sd"> :return: None</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">last_training_set_transition_id</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">train_to_eval_ratio</span> <span class="o">&lt;</span> <span class="mi">0</span> <span class="ow">or</span> <span class="bp">self</span><span class="o">.</span><span class="n">train_to_eval_ratio</span> <span class="o">&gt;=</span> <span class="mi">1</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">&#39;train_to_eval_ratio should be in the (0, 1] range.&#39;</span><span class="p">)</span>
<span class="n">transition</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">transitions</span><span class="p">[</span><span class="nb">round</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">train_to_eval_ratio</span> <span class="o">*</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">episode_num</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_episode_for_transition</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">last_training_set_episode_id</span> <span class="o">=</span> <span class="n">episode_num</span>
<span class="bp">self</span><span class="o">.</span><span class="n">last_training_set_transition_id</span> <span class="o">=</span> \
<span class="nb">len</span><span class="p">([</span><span class="n">t</span> <span class="k">for</span> <span class="n">e</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_all_complete_episodes_from_to</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">last_training_set_episode_id</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)</span> <span class="k">for</span> <span class="n">t</span> <span class="ow">in</span> <span class="n">e</span><span class="p">])</span></div>
</pre></div>
</div>
@@ -638,7 +699,7 @@
<div role="contentinfo">
<p>
&copy; Copyright 2018, Intel AI Lab
&copy; Copyright 2018-2019, Intel AI Lab
</p>
</div>
@@ -655,27 +716,16 @@
<script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../../_static/doctools.js"></script>
<script type="text/javascript" src="../../../../_static/language_data.js"></script>
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/javascript" src="../../../../_static/js/theme.js"></script>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</script>
</body>
</html>

48
docs/_modules/rl_coach/memories/episodic/episodic_hindsight_experience_replay.html
View File

@@ -8,7 +8,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>rl_coach.memories.episodic.episodic_hindsight_experience_replay &mdash; Reinforcement Learning Coach 0.11.0 documentation</title>
<title>rl_coach.memories.episodic.episodic_hindsight_experience_replay &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
@@ -17,13 +17,21 @@
<script type="text/javascript" src="../../../../_static/js/modernizr.min.js"></script>
<script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../../_static/doctools.js"></script>
<script type="text/javascript" src="../../../../_static/language_data.js"></script>
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/javascript" src="../../../../_static/js/theme.js"></script>
<link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" />
<link rel="stylesheet" href="../../../../_static/pygments.css" type="text/css" />
<link rel="stylesheet" href="../../../../_static/css/custom.css" type="text/css" />
@@ -31,21 +39,16 @@
<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">
<div class="wy-side-nav-search" >
@@ -338,7 +341,7 @@
<div role="contentinfo">
<p>
&copy; Copyright 2018, Intel AI Lab
&copy; Copyright 2018-2019, Intel AI Lab
</p>
</div>
@@ -355,27 +358,16 @@
<script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../../_static/doctools.js"></script>
<script type="text/javascript" src="../../../../_static/language_data.js"></script>
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/javascript" src="../../../../_static/js/theme.js"></script>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</script>
</body>
</html>

48
docs/_modules/rl_coach/memories/episodic/episodic_hrl_hindsight_experience_replay.html
View File

@@ -8,7 +8,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>rl_coach.memories.episodic.episodic_hrl_hindsight_experience_replay &mdash; Reinforcement Learning Coach 0.11.0 documentation</title>
<title>rl_coach.memories.episodic.episodic_hrl_hindsight_experience_replay &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
@@ -17,13 +17,21 @@
<script type="text/javascript" src="../../../../_static/js/modernizr.min.js"></script>
<script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../../_static/doctools.js"></script>
<script type="text/javascript" src="../../../../_static/language_data.js"></script>
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/javascript" src="../../../../_static/js/theme.js"></script>
<link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" />
<link rel="stylesheet" href="../../../../_static/pygments.css" type="text/css" />
<link rel="stylesheet" href="../../../../_static/css/custom.css" type="text/css" />
@@ -31,21 +39,16 @@
<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">
<div class="wy-side-nav-search" >
@@ -263,7 +266,7 @@
<div role="contentinfo">
<p>
&copy; Copyright 2018, Intel AI Lab
&copy; Copyright 2018-2019, Intel AI Lab
</p>
</div>
@@ -280,27 +283,16 @@
<script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../../_static/doctools.js"></script>
<script type="text/javascript" src="../../../../_static/language_data.js"></script>
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/javascript" src="../../../../_static/js/theme.js"></script>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</script>
</body>
</html>

48
docs/_modules/rl_coach/memories/episodic/single_episode_buffer.html
View File

@@ -8,7 +8,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>rl_coach.memories.episodic.single_episode_buffer &mdash; Reinforcement Learning Coach 0.11.0 documentation</title>
<title>rl_coach.memories.episodic.single_episode_buffer &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
@@ -17,13 +17,21 @@
<script type="text/javascript" src="../../../../_static/js/modernizr.min.js"></script>
<script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../../_static/doctools.js"></script>
<script type="text/javascript" src="../../../../_static/language_data.js"></script>
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/javascript" src="../../../../_static/js/theme.js"></script>
<link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" />
<link rel="stylesheet" href="../../../../_static/pygments.css" type="text/css" />
<link rel="stylesheet" href="../../../../_static/css/custom.css" type="text/css" />
@@ -31,21 +39,16 @@
<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">
<div class="wy-side-nav-search" >
@@ -223,7 +226,7 @@
<div role="contentinfo">
<p>
&copy; Copyright 2018, Intel AI Lab
&copy; Copyright 2018-2019, Intel AI Lab
</p>
</div>
@@ -240,27 +243,16 @@
<script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../../_static/doctools.js"></script>
<script type="text/javascript" src="../../../../_static/language_data.js"></script>
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/javascript" src="../../../../_static/js/theme.js"></script>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</script>
</body>
</html>

48
docs/_modules/rl_coach/memories/non_episodic/balanced_experience_replay.html
View File

@@ -8,7 +8,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>rl_coach.memories.non_episodic.balanced_experience_replay &mdash; Reinforcement Learning Coach 0.11.0 documentation</title>
<title>rl_coach.memories.non_episodic.balanced_experience_replay &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
@@ -17,13 +17,21 @@
<script type="text/javascript" src="../../../../_static/js/modernizr.min.js"></script>
<script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../../_static/doctools.js"></script>
<script type="text/javascript" src="../../../../_static/language_data.js"></script>
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/javascript" src="../../../../_static/js/theme.js"></script>
<link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" />
<link rel="stylesheet" href="../../../../_static/pygments.css" type="text/css" />
<link rel="stylesheet" href="../../../../_static/css/custom.css" type="text/css" />
@@ -31,21 +39,16 @@
<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">
<div class="wy-side-nav-search" >
@@ -363,7 +366,7 @@
<div role="contentinfo">
<p>
&copy; Copyright 2018, Intel AI Lab
&copy; Copyright 2018-2019, Intel AI Lab
</p>
</div>
@@ -380,27 +383,16 @@
<script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../../_static/doctools.js"></script>
<script type="text/javascript" src="../../../../_static/language_data.js"></script>
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/javascript" src="../../../../_static/js/theme.js"></script>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</script>
</body>
</html>

48
docs/_modules/rl_coach/memories/non_episodic/differentiable_neural_dictionary.html
View File

@@ -8,7 +8,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>rl_coach.memories.non_episodic.differentiable_neural_dictionary &mdash; Reinforcement Learning Coach 0.11.0 documentation</title>
<title>rl_coach.memories.non_episodic.differentiable_neural_dictionary &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
@@ -17,13 +17,21 @@
<script type="text/javascript" src="../../../../_static/js/modernizr.min.js"></script>
<script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../../_static/doctools.js"></script>
<script type="text/javascript" src="../../../../_static/language_data.js"></script>
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/javascript" src="../../../../_static/js/theme.js"></script>
<link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" />
<link rel="stylesheet" href="../../../../_static/pygments.css" type="text/css" />
<link rel="stylesheet" href="../../../../_static/css/custom.css" type="text/css" />
@@ -31,21 +39,16 @@
<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">
<div class="wy-side-nav-search" >
@@ -486,7 +489,7 @@
<div role="contentinfo">
<p>
&copy; Copyright 2018, Intel AI Lab
&copy; Copyright 2018-2019, Intel AI Lab
</p>
</div>
@@ -503,27 +506,16 @@
<script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../../_static/doctools.js"></script>
<script type="text/javascript" src="../../../../_static/language_data.js"></script>
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/javascript" src="../../../../_static/js/theme.js"></script>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</script>
</body>
</html>

75
docs/_modules/rl_coach/memories/non_episodic/experience_replay.html
View File

@@ -8,7 +8,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>rl_coach.memories.non_episodic.experience_replay &mdash; Reinforcement Learning Coach 0.11.0 documentation</title>
<title>rl_coach.memories.non_episodic.experience_replay &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
@@ -17,13 +17,21 @@
<script type="text/javascript" src="../../../../_static/js/modernizr.min.js"></script>
<script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../../_static/doctools.js"></script>
<script type="text/javascript" src="../../../../_static/language_data.js"></script>
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/javascript" src="../../../../_static/js/theme.js"></script>
<link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" />
<link rel="stylesheet" href="../../../../_static/pygments.css" type="text/css" />
<link rel="stylesheet" href="../../../../_static/css/custom.css" type="text/css" />
@@ -31,21 +39,16 @@
<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">
<div class="wy-side-nav-search" >
@@ -234,6 +237,7 @@
<span class="bp">self</span><span class="o">.</span><span class="n">allow_duplicates_in_batch_sampling</span> <span class="o">=</span> <span class="n">allow_duplicates_in_batch_sampling</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="bp">self</span><span class="o">.</span><span class="n">frozen</span> <span class="o">=</span> <span class="kc">False</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="o">-&gt;</span> <span class="nb">int</span><span class="p">:</span>
<span class="sd">&quot;&quot;&quot;</span>
@@ -271,7 +275,7 @@
<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">get_shuffled_data_generator</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">-&gt;</span> <span class="n">List</span><span class="p">[</span><span class="n">Transition</span><span class="p">]:</span>
<span class="k">def</span> <span class="nf">get_shuffled_training_data_generator</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">-&gt;</span> <span class="n">List</span><span class="p">[</span><span class="n">Transition</span><span class="p">]:</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Get an generator for iterating through the shuffled replay buffer, for processing the data in epochs.</span>
<span class="sd"> If the requested size is larger than the number of samples available in the replay buffer then the batch will</span>
@@ -315,6 +319,8 @@
<span class="sd"> locks and then calls store with lock = True</span>
<span class="sd"> :return: None</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">assert_not_frozen</span><span class="p">()</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="k">if</span> <span class="n">lock</span><span class="p">:</span>
@@ -355,6 +361,8 @@
<span class="sd"> :param transition_index: the index of the transition to remove</span>
<span class="sd"> :return: None</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">assert_not_frozen</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>
@@ -387,6 +395,8 @@
<span class="sd"> Clean the memory by removing all the episodes</span>
<span class="sd"> :return: None</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">assert_not_frozen</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>
@@ -422,6 +432,8 @@
<span class="sd"> The pickle file is assumed to include a list of transitions.</span>
<span class="sd"> :param file_path: The path to a pickle file to restore</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">assert_not_frozen</span><span class="p">()</span>
<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">file_path</span><span class="p">,</span> <span class="s1">&#39;rb&#39;</span><span class="p">)</span> <span class="k">as</span> <span class="n">file</span><span class="p">:</span>
<span class="n">transitions</span> <span class="o">=</span> <span class="n">pickle</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="n">file</span><span class="p">)</span>
<span class="n">num_transitions</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">transitions</span><span class="p">)</span>
@@ -438,8 +450,22 @@
<span class="k">if</span> <span class="n">transition_idx</span> <span class="o">%</span> <span class="mi">100</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
<span class="n">progress_bar</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">transition_idx</span><span class="p">)</span>
<span class="n">progress_bar</span><span class="o">.</span><span class="n">close</span><span class="p">()</span></div>
<span class="n">progress_bar</span><span class="o">.</span><span class="n">close</span><span class="p">()</span>
<span class="k">def</span> <span class="nf">freeze</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Freezing the replay buffer does not allow any new transitions to be added to the memory.</span>
<span class="sd"> Useful when working with a dataset (e.g. batch-rl or imitation learning).</span>
<span class="sd"> :return: None</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">frozen</span> <span class="o">=</span> <span class="kc">True</span>
<span class="k">def</span> <span class="nf">assert_not_frozen</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Check that the memory is not frozen, and can be changed.</span>
<span class="sd"> :return:</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">assert</span> <span class="bp">self</span><span class="o">.</span><span class="n">frozen</span> <span class="ow">is</span> <span class="kc">False</span><span class="p">,</span> <span class="s2">&quot;Memory is frozen, and cannot be changed.&quot;</span></div>
</pre></div>
</div>
@@ -452,7 +478,7 @@
<div role="contentinfo">
<p>
&copy; Copyright 2018, Intel AI Lab
&copy; Copyright 2018-2019, Intel AI Lab
</p>
</div>
@@ -469,27 +495,16 @@
<script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../../_static/doctools.js"></script>
<script type="text/javascript" src="../../../../_static/language_data.js"></script>
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/javascript" src="../../../../_static/js/theme.js"></script>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</script>
</body>
</html>

48
docs/_modules/rl_coach/memories/non_episodic/prioritized_experience_replay.html
View File

@@ -8,7 +8,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>rl_coach.memories.non_episodic.prioritized_experience_replay &mdash; Reinforcement Learning Coach 0.11.0 documentation</title>
<title>rl_coach.memories.non_episodic.prioritized_experience_replay &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
@@ -17,13 +17,21 @@
<script type="text/javascript" src="../../../../_static/js/modernizr.min.js"></script>
<script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../../_static/doctools.js"></script>
<script type="text/javascript" src="../../../../_static/language_data.js"></script>
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/javascript" src="../../../../_static/js/theme.js"></script>
<link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" />
<link rel="stylesheet" href="../../../../_static/pygments.css" type="text/css" />
<link rel="stylesheet" href="../../../../_static/css/custom.css" type="text/css" />
@@ -31,21 +39,16 @@
<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">
<div class="wy-side-nav-search" >
@@ -489,7 +492,7 @@
<div role="contentinfo">
<p>
&copy; Copyright 2018, Intel AI Lab
&copy; Copyright 2018-2019, Intel AI Lab
</p>
</div>
@@ -506,27 +509,16 @@
<script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../../_static/doctools.js"></script>
<script type="text/javascript" src="../../../../_static/language_data.js"></script>
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/javascript" src="../../../../_static/js/theme.js"></script>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</script>
</body>
</html>

48
docs/_modules/rl_coach/memories/non_episodic/transition_collection.html
View File

@@ -8,7 +8,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>rl_coach.memories.non_episodic.transition_collection &mdash; Reinforcement Learning Coach 0.11.0 documentation</title>
<title>rl_coach.memories.non_episodic.transition_collection &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
@@ -17,13 +17,21 @@
<script type="text/javascript" src="../../../../_static/js/modernizr.min.js"></script>
<script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../../_static/doctools.js"></script>
<script type="text/javascript" src="../../../../_static/language_data.js"></script>
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/javascript" src="../../../../_static/js/theme.js"></script>
<link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" />
<link rel="stylesheet" href="../../../../_static/pygments.css" type="text/css" />
<link rel="stylesheet" href="../../../../_static/css/custom.css" type="text/css" />
@@ -31,21 +39,16 @@
<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">
<div class="wy-side-nav-search" >
@@ -243,7 +246,7 @@
<div role="contentinfo">
<p>
&copy; Copyright 2018, Intel AI Lab
&copy; Copyright 2018-2019, Intel AI Lab
</p>
</div>
@@ -260,27 +263,16 @@
<script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../../_static/doctools.js"></script>
<script type="text/javascript" src="../../../../_static/language_data.js"></script>
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/javascript" src="../../../../_static/js/theme.js"></script>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</script>
</body>
</html>