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

51
docs/_modules/rl_coach/agents/agent.html
View File

@@ -8,7 +8,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>rl_coach.agents.agent &mdash; Reinforcement Learning Coach 0.11.0 documentation</title>
<title>rl_coach.agents.agent &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" >
@@ -702,6 +705,7 @@
<span class="bp">self</span><span class="o">.</span><span class="n">agent_logger</span><span class="o">.</span><span class="n">create_signal_value</span><span class="p">(</span><span class="s1">&#39;Inverse Propensity Score&#39;</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">nan</span><span class="p">,</span> <span class="n">overwrite</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">agent_logger</span><span class="o">.</span><span class="n">create_signal_value</span><span class="p">(</span><span class="s1">&#39;Direct Method Reward&#39;</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">nan</span><span class="p">,</span> <span class="n">overwrite</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">agent_logger</span><span class="o">.</span><span class="n">create_signal_value</span><span class="p">(</span><span class="s1">&#39;Doubly Robust&#39;</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">nan</span><span class="p">,</span> <span class="n">overwrite</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">agent_logger</span><span class="o">.</span><span class="n">create_signal_value</span><span class="p">(</span><span class="s1">&#39;Weighted Importance Sampling&#39;</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">nan</span><span class="p">,</span> <span class="n">overwrite</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">agent_logger</span><span class="o">.</span><span class="n">create_signal_value</span><span class="p">(</span><span class="s1">&#39;Sequential Doubly Robust&#39;</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">nan</span><span class="p">,</span> <span class="n">overwrite</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
<span class="k">for</span> <span class="n">signal</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">episode_signals</span><span class="p">:</span>
@@ -876,7 +880,7 @@
<span class="c1"># we either go sequentially through the entire replay buffer in the batch RL mode,</span>
<span class="c1"># or sample randomly for the basic RL case.</span>
<span class="n">training_schedule</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">call_memory</span><span class="p">(</span><span class="s1">&#39;get_shuffled_data_generator&#39;</span><span class="p">,</span> <span class="n">batch_size</span><span class="p">)</span> <span class="k">if</span> \
<span class="n">training_schedule</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">call_memory</span><span class="p">(</span><span class="s1">&#39;get_shuffled_training_data_generator&#39;</span><span class="p">,</span> <span class="n">batch_size</span><span class="p">)</span> <span class="k">if</span> \
<span class="bp">self</span><span class="o">.</span><span class="n">ap</span><span class="o">.</span><span class="n">is_batch_rl_training</span> <span class="k">else</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">call_memory</span><span class="p">(</span><span class="s1">&#39;sample&#39;</span><span class="p">,</span> <span class="n">batch_size</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">ap</span><span class="o">.</span><span class="n">algorithm</span><span class="o">.</span><span class="n">num_consecutive_training_steps</span><span class="p">)]</span>
@@ -1238,7 +1242,7 @@
<div role="contentinfo">
<p>
&copy; Copyright 2018, Intel AI Lab
&copy; Copyright 2018-2019, Intel AI Lab
</p>
</div>
@@ -1255,27 +1259,16 @@
<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>