mirror of
https://github.com/gryf/coach.git
synced 2025-12-17 19:20:19 +01:00
354 lines
26 KiB
HTML
354 lines
26 KiB
HTML
|
|
|
|
<!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.agents.policy_gradients_agent — Reinforcement Learning Coach 0.12.0 documentation</title>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<script type="text/javascript" src="../../../_static/js/modernizr.min.js"></script>
|
|
|
|
|
|
<script type="text/javascript" id="documentation_options" data-url_root="../../../" src="../../../_static/documentation_options.js"></script>
|
|
<script type="text/javascript" src="../../../_static/jquery.js"></script>
|
|
<script type="text/javascript" src="../../../_static/underscore.js"></script>
|
|
<script type="text/javascript" src="../../../_static/doctools.js"></script>
|
|
<script type="text/javascript" src="../../../_static/language_data.js"></script>
|
|
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
|
|
|
|
<script type="text/javascript" src="../../../_static/js/theme.js"></script>
|
|
|
|
|
|
|
|
|
|
<link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
|
|
<link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
|
|
<link rel="stylesheet" href="../../../_static/css/custom.css" type="text/css" />
|
|
<link rel="index" title="Index" href="../../../genindex.html" />
|
|
<link rel="search" title="Search" href="../../../search.html" />
|
|
<link href="../../../_static/css/custom.css" rel="stylesheet" type="text/css">
|
|
|
|
</head>
|
|
|
|
<body class="wy-body-for-nav">
|
|
|
|
|
|
<div class="wy-grid-for-nav">
|
|
|
|
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
|
|
<div class="wy-side-scroll">
|
|
<div class="wy-side-nav-search" >
|
|
|
|
|
|
|
|
<a href="../../../index.html" class="icon icon-home"> Reinforcement Learning Coach
|
|
|
|
|
|
|
|
|
|
<img src="../../../_static/dark_logo.png" class="logo" alt="Logo"/>
|
|
|
|
</a>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<div role="search">
|
|
<form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get">
|
|
<input type="text" name="q" placeholder="Search docs" />
|
|
<input type="hidden" name="check_keywords" value="yes" />
|
|
<input type="hidden" name="area" value="default" />
|
|
</form>
|
|
</div>
|
|
|
|
|
|
</div>
|
|
|
|
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<p class="caption"><span class="caption-text">Intro</span></p>
|
|
<ul>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../usage.html">Usage</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../dist_usage.html">Usage - Distributed Coach</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../features/index.html">Features</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../selecting_an_algorithm.html">Selecting an Algorithm</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../dashboard.html">Coach Dashboard</a></li>
|
|
</ul>
|
|
<p class="caption"><span class="caption-text">Design</span></p>
|
|
<ul>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../design/control_flow.html">Control Flow</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../design/network.html">Network Design</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../design/horizontal_scaling.html">Distributed Coach - Horizontal Scale-Out</a></li>
|
|
</ul>
|
|
<p class="caption"><span class="caption-text">Contributing</span></p>
|
|
<ul>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../contributing/add_agent.html">Adding a New Agent</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../contributing/add_env.html">Adding a New Environment</a></li>
|
|
</ul>
|
|
<p class="caption"><span class="caption-text">Components</span></p>
|
|
<ul>
|
|
<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/data_stores/index.html">Data Stores</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/memory_backends/index.html">Memory Backends</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../components/orchestrators/index.html">Orchestrators</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.agents.policy_gradients_agent</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.agents.policy_gradients_agent</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">Union</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.agents.policy_optimization_agent</span> <span class="k">import</span> <span class="n">PolicyOptimizationAgent</span><span class="p">,</span> <span class="n">PolicyGradientRescaler</span>
|
|
<span class="kn">from</span> <span class="nn">rl_coach.architectures.embedder_parameters</span> <span class="k">import</span> <span class="n">InputEmbedderParameters</span>
|
|
<span class="kn">from</span> <span class="nn">rl_coach.architectures.head_parameters</span> <span class="k">import</span> <span class="n">PolicyHeadParameters</span>
|
|
<span class="kn">from</span> <span class="nn">rl_coach.architectures.middleware_parameters</span> <span class="k">import</span> <span class="n">FCMiddlewareParameters</span>
|
|
<span class="kn">from</span> <span class="nn">rl_coach.base_parameters</span> <span class="k">import</span> <span class="n">NetworkParameters</span><span class="p">,</span> <span class="n">AlgorithmParameters</span><span class="p">,</span> \
|
|
<span class="n">AgentParameters</span>
|
|
|
|
<span class="kn">from</span> <span class="nn">rl_coach.exploration_policies.additive_noise</span> <span class="k">import</span> <span class="n">AdditiveNoiseParameters</span>
|
|
<span class="kn">from</span> <span class="nn">rl_coach.exploration_policies.categorical</span> <span class="k">import</span> <span class="n">CategoricalParameters</span>
|
|
<span class="kn">from</span> <span class="nn">rl_coach.logger</span> <span class="k">import</span> <span class="n">screen</span>
|
|
<span class="kn">from</span> <span class="nn">rl_coach.memories.episodic.single_episode_buffer</span> <span class="k">import</span> <span class="n">SingleEpisodeBufferParameters</span>
|
|
<span class="kn">from</span> <span class="nn">rl_coach.spaces</span> <span class="k">import</span> <span class="n">DiscreteActionSpace</span><span class="p">,</span> <span class="n">BoxActionSpace</span>
|
|
|
|
|
|
<span class="k">class</span> <span class="nc">PolicyGradientNetworkParameters</span><span class="p">(</span><span class="n">NetworkParameters</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">input_embedders_parameters</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'observation'</span><span class="p">:</span> <span class="n">InputEmbedderParameters</span><span class="p">()}</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">middleware_parameters</span> <span class="o">=</span> <span class="n">FCMiddlewareParameters</span><span class="p">()</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">heads_parameters</span> <span class="o">=</span> <span class="p">[</span><span class="n">PolicyHeadParameters</span><span class="p">()]</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">async_training</span> <span class="o">=</span> <span class="kc">True</span>
|
|
|
|
|
|
<div class="viewcode-block" id="PolicyGradientAlgorithmParameters"><a class="viewcode-back" href="../../../components/agents/policy_optimization/pg.html#rl_coach.agents.policy_gradients_agent.PolicyGradientAlgorithmParameters">[docs]</a><span class="k">class</span> <span class="nc">PolicyGradientAlgorithmParameters</span><span class="p">(</span><span class="n">AlgorithmParameters</span><span class="p">):</span>
|
|
<span class="sd">"""</span>
|
|
<span class="sd"> :param policy_gradient_rescaler: (PolicyGradientRescaler)</span>
|
|
<span class="sd"> The rescaler type to use for the policy gradient loss. For policy gradients, we calculate log probability of</span>
|
|
<span class="sd"> the action and then multiply it by the policy gradient rescaler. The most basic rescaler is the discounter</span>
|
|
<span class="sd"> return, but there are other rescalers that are intended for reducing the variance of the updates.</span>
|
|
|
|
<span class="sd"> :param apply_gradients_every_x_episodes: (int)</span>
|
|
<span class="sd"> The number of episodes between applying the accumulated gradients to the network. After every</span>
|
|
<span class="sd"> num_steps_between_gradient_updates steps, the agent will calculate the gradients for the collected data,</span>
|
|
<span class="sd"> it will then accumulate it in internal accumulators, and will only apply them to the network once in every</span>
|
|
<span class="sd"> apply_gradients_every_x_episodes episodes.</span>
|
|
|
|
<span class="sd"> :param beta_entropy: (float)</span>
|
|
<span class="sd"> A factor which defines the amount of entropy regularization to apply to the network. The entropy of the actions</span>
|
|
<span class="sd"> will be added to the loss and scaled by the given beta factor.</span>
|
|
|
|
<span class="sd"> :param num_steps_between_gradient_updates: (int)</span>
|
|
<span class="sd"> The number of steps between calculating gradients for the collected data. In the A3C paper, this parameter is</span>
|
|
<span class="sd"> called t_max. Since this algorithm is on-policy, only the steps collected between each two gradient calculations</span>
|
|
<span class="sd"> are used in the batch.</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="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">policy_gradient_rescaler</span> <span class="o">=</span> <span class="n">PolicyGradientRescaler</span><span class="o">.</span><span class="n">FUTURE_RETURN_NORMALIZED_BY_TIMESTEP</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">apply_gradients_every_x_episodes</span> <span class="o">=</span> <span class="mi">5</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">beta_entropy</span> <span class="o">=</span> <span class="mi">0</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">num_steps_between_gradient_updates</span> <span class="o">=</span> <span class="mi">20000</span> <span class="c1"># this is called t_max in all the papers</span></div>
|
|
|
|
|
|
<span class="k">class</span> <span class="nc">PolicyGradientsAgentParameters</span><span class="p">(</span><span class="n">AgentParameters</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">algorithm</span><span class="o">=</span><span class="n">PolicyGradientAlgorithmParameters</span><span class="p">(),</span>
|
|
<span class="n">exploration</span><span class="o">=</span><span class="p">{</span><span class="n">DiscreteActionSpace</span><span class="p">:</span> <span class="n">CategoricalParameters</span><span class="p">(),</span>
|
|
<span class="n">BoxActionSpace</span><span class="p">:</span> <span class="n">AdditiveNoiseParameters</span><span class="p">()},</span>
|
|
<span class="n">memory</span><span class="o">=</span><span class="n">SingleEpisodeBufferParameters</span><span class="p">(),</span>
|
|
<span class="n">networks</span><span class="o">=</span><span class="p">{</span><span class="s2">"main"</span><span class="p">:</span> <span class="n">PolicyGradientNetworkParameters</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.agents.policy_gradients_agent:PolicyGradientsAgent'</span>
|
|
|
|
|
|
<span class="k">class</span> <span class="nc">PolicyGradientsAgent</span><span class="p">(</span><span class="n">PolicyOptimizationAgent</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="n">agent_parameters</span><span class="p">,</span> <span class="n">parent</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="s1">'LevelManager'</span><span class="p">,</span> <span class="s1">'CompositeAgent'</span><span class="p">]</span><span class="o">=</span><span class="kc">None</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">agent_parameters</span><span class="p">,</span> <span class="n">parent</span><span class="p">)</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">returns_mean</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">register_signal</span><span class="p">(</span><span class="s1">'Returns Mean'</span><span class="p">)</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">returns_variance</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">register_signal</span><span class="p">(</span><span class="s1">'Returns Variance'</span><span class="p">)</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">last_gradient_update_step_idx</span> <span class="o">=</span> <span class="mi">0</span>
|
|
|
|
<span class="k">def</span> <span class="nf">learn_from_batch</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">batch</span><span class="p">):</span>
|
|
<span class="c1"># batch contains a list of episodes to learn from</span>
|
|
<span class="n">network_keys</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">ap</span><span class="o">.</span><span class="n">network_wrappers</span><span class="p">[</span><span class="s1">'main'</span><span class="p">]</span><span class="o">.</span><span class="n">input_embedders_parameters</span><span class="o">.</span><span class="n">keys</span><span class="p">()</span>
|
|
|
|
<span class="n">total_returns</span> <span class="o">=</span> <span class="n">batch</span><span class="o">.</span><span class="n">n_step_discounted_rewards</span><span class="p">()</span>
|
|
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">reversed</span><span class="p">(</span><span class="nb">range</span><span class="p">(</span><span class="n">batch</span><span class="o">.</span><span class="n">size</span><span class="p">)):</span>
|
|
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">policy_gradient_rescaler</span> <span class="o">==</span> <span class="n">PolicyGradientRescaler</span><span class="o">.</span><span class="n">TOTAL_RETURN</span><span class="p">:</span>
|
|
<span class="n">total_returns</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="n">total_returns</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
|
|
<span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">policy_gradient_rescaler</span> <span class="o">==</span> <span class="n">PolicyGradientRescaler</span><span class="o">.</span><span class="n">FUTURE_RETURN</span><span class="p">:</span>
|
|
<span class="c1"># just take the total return as it is</span>
|
|
<span class="k">pass</span>
|
|
<span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">policy_gradient_rescaler</span> <span class="o">==</span> <span class="n">PolicyGradientRescaler</span><span class="o">.</span><span class="n">FUTURE_RETURN_NORMALIZED_BY_EPISODE</span><span class="p">:</span>
|
|
<span class="c1"># we can get a single transition episode while playing Doom Basic, causing the std to be 0</span>
|
|
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">std_discounted_return</span> <span class="o">!=</span> <span class="mi">0</span><span class="p">:</span>
|
|
<span class="n">total_returns</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="p">(</span><span class="n">total_returns</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">mean_discounted_return</span><span class="p">)</span> <span class="o">/</span> <span class="bp">self</span><span class="o">.</span><span class="n">std_discounted_return</span>
|
|
<span class="k">else</span><span class="p">:</span>
|
|
<span class="n">total_returns</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="mi">0</span>
|
|
<span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">policy_gradient_rescaler</span> <span class="o">==</span> <span class="n">PolicyGradientRescaler</span><span class="o">.</span><span class="n">FUTURE_RETURN_NORMALIZED_BY_TIMESTEP</span><span class="p">:</span>
|
|
<span class="n">total_returns</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">-=</span> <span class="bp">self</span><span class="o">.</span><span class="n">mean_return_over_multiple_episodes</span><span class="p">[</span><span class="n">i</span><span class="p">]</span>
|
|
<span class="k">else</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">"WARNING: The requested policy gradient rescaler is not available"</span><span class="p">)</span>
|
|
|
|
<span class="n">targets</span> <span class="o">=</span> <span class="n">total_returns</span>
|
|
<span class="n">actions</span> <span class="o">=</span> <span class="n">batch</span><span class="o">.</span><span class="n">actions</span><span class="p">()</span>
|
|
<span class="k">if</span> <span class="nb">type</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">spaces</span><span class="o">.</span><span class="n">action</span><span class="p">)</span> <span class="o">!=</span> <span class="n">DiscreteActionSpace</span> <span class="ow">and</span> <span class="nb">len</span><span class="p">(</span><span class="n">actions</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span> <span class="o"><</span> <span class="mi">2</span><span class="p">:</span>
|
|
<span class="n">actions</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">expand_dims</span><span class="p">(</span><span class="n">actions</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">returns_mean</span><span class="o">.</span><span class="n">add_sample</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">mean</span><span class="p">(</span><span class="n">total_returns</span><span class="p">))</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">returns_variance</span><span class="o">.</span><span class="n">add_sample</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">std</span><span class="p">(</span><span class="n">total_returns</span><span class="p">))</span>
|
|
|
|
<span class="n">result</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">networks</span><span class="p">[</span><span class="s1">'main'</span><span class="p">]</span><span class="o">.</span><span class="n">online_network</span><span class="o">.</span><span class="n">accumulate_gradients</span><span class="p">(</span>
|
|
<span class="p">{</span><span class="o">**</span><span class="n">batch</span><span class="o">.</span><span class="n">states</span><span class="p">(</span><span class="n">network_keys</span><span class="p">),</span> <span class="s1">'output_0_0'</span><span class="p">:</span> <span class="n">actions</span><span class="p">},</span> <span class="n">targets</span>
|
|
<span class="p">)</span>
|
|
<span class="n">total_loss</span><span class="p">,</span> <span class="n">losses</span><span class="p">,</span> <span class="n">unclipped_grads</span> <span class="o">=</span> <span class="n">result</span><span class="p">[:</span><span class="mi">3</span><span class="p">]</span>
|
|
|
|
<span class="k">return</span> <span class="n">total_loss</span><span class="p">,</span> <span class="n">losses</span><span class="p">,</span> <span class="n">unclipped_grads</span>
|
|
</pre></div>
|
|
|
|
</div>
|
|
|
|
</div>
|
|
<footer>
|
|
|
|
|
|
<hr/>
|
|
|
|
<div role="contentinfo">
|
|
<p>
|
|
© Copyright 2018-2019, Intel AI Lab
|
|
|
|
</p>
|
|
</div>
|
|
Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
|
|
|
|
</footer>
|
|
|
|
</div>
|
|
</div>
|
|
|
|
</section>
|
|
|
|
</div>
|
|
|
|
|
|
|
|
<script type="text/javascript">
|
|
jQuery(function () {
|
|
SphinxRtdTheme.Navigation.enable(true);
|
|
});
|
|
</script>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
</body>
|
|
</html> |