mirror of
https://github.com/gryf/coach.git
synced 2025-12-17 19:20:19 +01:00
359 lines
29 KiB
HTML
359 lines
29 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.qr_dqn_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.qr_dqn_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.qr_dqn_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">copy</span> <span class="k">import</span> <span class="n">copy</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.dqn_agent</span> <span class="k">import</span> <span class="n">DQNAgentParameters</span><span class="p">,</span> <span class="n">DQNNetworkParameters</span><span class="p">,</span> <span class="n">DQNAlgorithmParameters</span>
|
|
<span class="kn">from</span> <span class="nn">rl_coach.agents.value_optimization_agent</span> <span class="k">import</span> <span class="n">ValueOptimizationAgent</span>
|
|
<span class="kn">from</span> <span class="nn">rl_coach.architectures.head_parameters</span> <span class="k">import</span> <span class="n">QuantileRegressionQHeadParameters</span>
|
|
<span class="kn">from</span> <span class="nn">rl_coach.core_types</span> <span class="k">import</span> <span class="n">StateType</span>
|
|
<span class="kn">from</span> <span class="nn">rl_coach.schedules</span> <span class="k">import</span> <span class="n">LinearSchedule</span>
|
|
|
|
|
|
<span class="k">class</span> <span class="nc">QuantileRegressionDQNNetworkParameters</span><span class="p">(</span><span class="n">DQNNetworkParameters</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">heads_parameters</span> <span class="o">=</span> <span class="p">[</span><span class="n">QuantileRegressionQHeadParameters</span><span class="p">()]</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">learning_rate</span> <span class="o">=</span> <span class="mf">0.00005</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">optimizer_epsilon</span> <span class="o">=</span> <span class="mf">0.01</span> <span class="o">/</span> <span class="mi">32</span>
|
|
|
|
|
|
<div class="viewcode-block" id="QuantileRegressionDQNAlgorithmParameters"><a class="viewcode-back" href="../../../components/agents/value_optimization/qr_dqn.html#rl_coach.agents.qr_dqn_agent.QuantileRegressionDQNAlgorithmParameters">[docs]</a><span class="k">class</span> <span class="nc">QuantileRegressionDQNAlgorithmParameters</span><span class="p">(</span><span class="n">DQNAlgorithmParameters</span><span class="p">):</span>
|
|
<span class="sd">"""</span>
|
|
<span class="sd"> :param atoms: (int)</span>
|
|
<span class="sd"> the number of atoms to predict for each action</span>
|
|
|
|
<span class="sd"> :param huber_loss_interval: (float)</span>
|
|
<span class="sd"> One of the huber loss parameters, and is referred to as :math:`\kapa` in the paper.</span>
|
|
<span class="sd"> It describes the interval [-k, k] in which the huber loss acts as a MSE loss.</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">atoms</span> <span class="o">=</span> <span class="mi">200</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">huber_loss_interval</span> <span class="o">=</span> <span class="mi">1</span> <span class="c1"># called k in the paper</span></div>
|
|
|
|
|
|
<span class="k">class</span> <span class="nc">QuantileRegressionDQNAgentParameters</span><span class="p">(</span><span class="n">DQNAgentParameters</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">algorithm</span> <span class="o">=</span> <span class="n">QuantileRegressionDQNAlgorithmParameters</span><span class="p">()</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">network_wrappers</span> <span class="o">=</span> <span class="p">{</span><span class="s2">"main"</span><span class="p">:</span> <span class="n">QuantileRegressionDQNNetworkParameters</span><span class="p">()}</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">exploration</span><span class="o">.</span><span class="n">epsilon_schedule</span> <span class="o">=</span> <span class="n">LinearSchedule</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mf">0.01</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">exploration</span><span class="o">.</span><span class="n">evaluation_epsilon</span> <span class="o">=</span> <span class="mf">0.001</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.qr_dqn_agent:QuantileRegressionDQNAgent'</span>
|
|
|
|
|
|
<span class="c1"># Quantile Regression Deep Q Network - https://arxiv.org/pdf/1710.10044v1.pdf</span>
|
|
<span class="k">class</span> <span class="nc">QuantileRegressionDQNAgent</span><span class="p">(</span><span class="n">ValueOptimizationAgent</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">quantile_probabilities</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">ones</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">atoms</span><span class="p">)</span> <span class="o">/</span> <span class="nb">float</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">atoms</span><span class="p">)</span>
|
|
|
|
<span class="k">def</span> <span class="nf">get_q_values</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">quantile_values</span><span class="p">):</span>
|
|
<span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">quantile_values</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">quantile_probabilities</span><span class="p">)</span>
|
|
|
|
<span class="c1"># prediction's format is (batch,actions,atoms)</span>
|
|
<span class="k">def</span> <span class="nf">get_all_q_values_for_states</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">states</span><span class="p">:</span> <span class="n">StateType</span><span class="p">):</span>
|
|
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">exploration_policy</span><span class="o">.</span><span class="n">requires_action_values</span><span class="p">():</span>
|
|
<span class="n">quantile_values</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_prediction</span><span class="p">(</span><span class="n">states</span><span class="p">)</span>
|
|
<span class="n">actions_q_values</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_q_values</span><span class="p">(</span><span class="n">quantile_values</span><span class="p">)</span>
|
|
<span class="k">else</span><span class="p">:</span>
|
|
<span class="n">actions_q_values</span> <span class="o">=</span> <span class="kc">None</span>
|
|
<span class="k">return</span> <span class="n">actions_q_values</span>
|
|
|
|
<span class="c1"># prediction's format is (batch,actions,atoms)</span>
|
|
<span class="k">def</span> <span class="nf">get_all_q_values_for_states_and_softmax_probabilities</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">states</span><span class="p">:</span> <span class="n">StateType</span><span class="p">):</span>
|
|
<span class="n">actions_q_values</span><span class="p">,</span> <span class="n">softmax_probabilities</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> <span class="kc">None</span>
|
|
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">exploration_policy</span><span class="o">.</span><span class="n">requires_action_values</span><span class="p">():</span>
|
|
<span class="n">outputs</span> <span class="o">=</span> <span class="n">copy</span><span class="p">(</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">outputs</span><span class="p">)</span>
|
|
<span class="n">outputs</span><span class="o">.</span><span class="n">append</span><span class="p">(</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">output_heads</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">softmax</span><span class="p">)</span>
|
|
<span class="n">quantile_values</span><span class="p">,</span> <span class="n">softmax_probabilities</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_prediction</span><span class="p">(</span><span class="n">states</span><span class="p">,</span> <span class="n">outputs</span><span class="p">)</span>
|
|
<span class="n">actions_q_values</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_q_values</span><span class="p">(</span><span class="n">quantile_values</span><span class="p">)</span>
|
|
|
|
<span class="k">return</span> <span class="n">actions_q_values</span><span class="p">,</span> <span class="n">softmax_probabilities</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="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="c1"># get the quantiles of the next states and current states</span>
|
|
<span class="n">next_state_quantiles</span><span class="p">,</span> <span class="n">current_quantiles</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">parallel_prediction</span><span class="p">([</span>
|
|
<span class="p">(</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">target_network</span><span class="p">,</span> <span class="n">batch</span><span class="o">.</span><span class="n">next_states</span><span class="p">(</span><span class="n">network_keys</span><span class="p">)),</span>
|
|
<span class="p">(</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="p">,</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="p">])</span>
|
|
|
|
<span class="c1"># add Q value samples for logging</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">q_values</span><span class="o">.</span><span class="n">add_sample</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">get_q_values</span><span class="p">(</span><span class="n">current_quantiles</span><span class="p">))</span>
|
|
|
|
<span class="c1"># get the optimal actions to take for the next states</span>
|
|
<span class="n">target_actions</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">argmax</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">get_q_values</span><span class="p">(</span><span class="n">next_state_quantiles</span><span class="p">),</span> <span class="n">axis</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
|
|
|
|
<span class="c1"># calculate the Bellman update</span>
|
|
<span class="n">batch_idx</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="n">batch</span><span class="o">.</span><span class="n">size</span><span class="p">))</span>
|
|
|
|
<span class="n">TD_targets</span> <span class="o">=</span> <span class="n">batch</span><span class="o">.</span><span class="n">rewards</span><span class="p">(</span><span class="kc">True</span><span class="p">)</span> <span class="o">+</span> <span class="p">(</span><span class="mf">1.0</span> <span class="o">-</span> <span class="n">batch</span><span class="o">.</span><span class="n">game_overs</span><span class="p">(</span><span class="kc">True</span><span class="p">))</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">algorithm</span><span class="o">.</span><span class="n">discount</span> \
|
|
<span class="o">*</span> <span class="n">next_state_quantiles</span><span class="p">[</span><span class="n">batch_idx</span><span class="p">,</span> <span class="n">target_actions</span><span class="p">]</span>
|
|
|
|
<span class="c1"># get the locations of the selected actions within the batch for indexing purposes</span>
|
|
<span class="n">actions_locations</span> <span class="o">=</span> <span class="p">[[</span><span class="n">b</span><span class="p">,</span> <span class="n">a</span><span class="p">]</span> <span class="k">for</span> <span class="n">b</span><span class="p">,</span> <span class="n">a</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="n">batch_idx</span><span class="p">,</span> <span class="n">batch</span><span class="o">.</span><span class="n">actions</span><span class="p">())]</span>
|
|
|
|
<span class="c1"># calculate the cumulative quantile probabilities and reorder them to fit the sorted quantiles order</span>
|
|
<span class="n">cumulative_probabilities</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</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">ap</span><span class="o">.</span><span class="n">algorithm</span><span class="o">.</span><span class="n">atoms</span> <span class="o">+</span> <span class="mi">1</span><span class="p">))</span> <span class="o">/</span> <span class="nb">float</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">atoms</span><span class="p">)</span> <span class="c1"># tau_i</span>
|
|
<span class="n">quantile_midpoints</span> <span class="o">=</span> <span class="mf">0.5</span><span class="o">*</span><span class="p">(</span><span class="n">cumulative_probabilities</span><span class="p">[</span><span class="mi">1</span><span class="p">:]</span> <span class="o">+</span> <span class="n">cumulative_probabilities</span><span class="p">[:</span><span class="o">-</span><span class="mi">1</span><span class="p">])</span> <span class="c1"># tau^hat_i</span>
|
|
<span class="n">quantile_midpoints</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">tile</span><span class="p">(</span><span class="n">quantile_midpoints</span><span class="p">,</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="mi">1</span><span class="p">))</span>
|
|
<span class="n">sorted_quantiles</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">argsort</span><span class="p">(</span><span class="n">current_quantiles</span><span class="p">[</span><span class="n">batch_idx</span><span class="p">,</span> <span class="n">batch</span><span class="o">.</span><span class="n">actions</span><span class="p">()])</span>
|
|
<span class="k">for</span> <span class="n">idx</span> <span class="ow">in</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="n">quantile_midpoints</span><span class="p">[</span><span class="n">idx</span><span class="p">,</span> <span class="p">:]</span> <span class="o">=</span> <span class="n">quantile_midpoints</span><span class="p">[</span><span class="n">idx</span><span class="p">,</span> <span class="n">sorted_quantiles</span><span class="p">[</span><span class="n">idx</span><span class="p">]]</span>
|
|
|
|
<span class="c1"># train</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">train_and_sync_networks</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_locations</span><span class="p">,</span>
|
|
<span class="s1">'output_0_1'</span><span class="p">:</span> <span class="n">quantile_midpoints</span><span class="p">,</span>
|
|
<span class="p">},</span> <span class="n">TD_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> |