mirror of
https://github.com/gryf/coach.git
synced 2025-12-17 11:10:20 +01:00
6d40ad1650
* updating the documentation website * adding the built docs * update of api docstrings across coach and tutorials 0-2 * added some missing api documentation * New Sphinx based documentation
435 lines
40 KiB
HTML
435 lines
40 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.nec_agent — Reinforcement Learning Coach 0.11.0 documentation</title>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
|
|
<link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
|
|
<link rel="stylesheet" href="../../../_static/css/custom.css" type="text/css" />
|
|
<link rel="index" title="Index" href="../../../genindex.html" />
|
|
<link rel="search" title="Search" href="../../../search.html" />
|
|
<link href="../../../_static/css/custom.css" rel="stylesheet" type="text/css">
|
|
|
|
|
|
|
|
<script src="../../../_static/js/modernizr.min.js"></script>
|
|
|
|
</head>
|
|
|
|
<body class="wy-body-for-nav">
|
|
|
|
|
|
<div class="wy-grid-for-nav">
|
|
|
|
|
|
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
|
|
<div class="wy-side-scroll">
|
|
<div class="wy-side-nav-search">
|
|
|
|
|
|
|
|
<a href="../../../index.html" class="icon icon-home"> Reinforcement Learning Coach
|
|
|
|
|
|
|
|
|
|
<img src="../../../_static/dark_logo.png" class="logo" alt="Logo"/>
|
|
|
|
</a>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<div role="search">
|
|
<form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get">
|
|
<input type="text" name="q" placeholder="Search docs" />
|
|
<input type="hidden" name="check_keywords" value="yes" />
|
|
<input type="hidden" name="area" value="default" />
|
|
</form>
|
|
</div>
|
|
|
|
|
|
</div>
|
|
|
|
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<p class="caption"><span class="caption-text">Intro</span></p>
|
|
<ul>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../usage.html">Usage</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../features/index.html">Features</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../selecting_an_algorithm.html">Selecting an Algorithm</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../dashboard.html">Coach Dashboard</a></li>
|
|
</ul>
|
|
<p class="caption"><span class="caption-text">Design</span></p>
|
|
<ul>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../design/control_flow.html">Control Flow</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../design/network.html">Network Design</a></li>
|
|
</ul>
|
|
<p class="caption"><span class="caption-text">Contributing</span></p>
|
|
<ul>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../contributing/add_agent.html">Adding a New Agent</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../contributing/add_env.html">Adding a New Environment</a></li>
|
|
</ul>
|
|
<p class="caption"><span class="caption-text">Components</span></p>
|
|
<ul>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../components/agents/index.html">Agents</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../components/architectures/index.html">Architectures</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../components/environments/index.html">Environments</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../components/exploration_policies/index.html">Exploration Policies</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../components/filters/index.html">Filters</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../components/memories/index.html">Memories</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../components/core_types.html">Core Types</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../components/spaces.html">Spaces</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../components/additional_parameters.html">Additional Parameters</a></li>
|
|
</ul>
|
|
|
|
|
|
|
|
</div>
|
|
</div>
|
|
</nav>
|
|
|
|
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
|
|
|
|
|
|
<nav class="wy-nav-top" aria-label="top navigation">
|
|
|
|
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
|
|
<a href="../../../index.html">Reinforcement Learning Coach</a>
|
|
|
|
</nav>
|
|
|
|
|
|
<div class="wy-nav-content">
|
|
|
|
<div class="rst-content">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<div role="navigation" aria-label="breadcrumbs navigation">
|
|
|
|
<ul class="wy-breadcrumbs">
|
|
|
|
<li><a href="../../../index.html">Docs</a> »</li>
|
|
|
|
<li><a href="../../index.html">Module code</a> »</li>
|
|
|
|
<li>rl_coach.agents.nec_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.nec_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">import</span> <span class="nn">os</span>
|
|
<span class="kn">import</span> <span class="nn">pickle</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.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.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">DNDQHeadParameters</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">AlgorithmParameters</span><span class="p">,</span> <span class="n">NetworkParameters</span><span class="p">,</span> <span class="n">AgentParameters</span>
|
|
|
|
<span class="kn">from</span> <span class="nn">rl_coach.core_types</span> <span class="k">import</span> <span class="n">RunPhase</span><span class="p">,</span> <span class="n">EnvironmentSteps</span><span class="p">,</span> <span class="n">Episode</span><span class="p">,</span> <span class="n">StateType</span>
|
|
<span class="kn">from</span> <span class="nn">rl_coach.exploration_policies.e_greedy</span> <span class="k">import</span> <span class="n">EGreedyParameters</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.episodic_experience_replay</span> <span class="k">import</span> <span class="n">EpisodicExperienceReplayParameters</span><span class="p">,</span> <span class="n">MemoryGranularity</span>
|
|
<span class="kn">from</span> <span class="nn">rl_coach.schedules</span> <span class="k">import</span> <span class="n">ConstantSchedule</span>
|
|
|
|
|
|
<span class="k">class</span> <span class="nc">NECNetworkParameters</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">DNDQHeadParameters</span><span class="p">()]</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">optimizer_type</span> <span class="o">=</span> <span class="s1">'Adam'</span>
|
|
|
|
|
|
<div class="viewcode-block" id="NECAlgorithmParameters"><a class="viewcode-back" href="../../../components/agents/value_optimization/nec.html#rl_coach.agents.nec_agent.NECAlgorithmParameters">[docs]</a><span class="k">class</span> <span class="nc">NECAlgorithmParameters</span><span class="p">(</span><span class="n">AlgorithmParameters</span><span class="p">):</span>
|
|
<span class="sd">"""</span>
|
|
<span class="sd"> :param dnd_size: (int)</span>
|
|
<span class="sd"> Defines the number of transitions that will be stored in each one of the DNDs. Note that the total number</span>
|
|
<span class="sd"> of transitions that will be stored is dnd_size x num_actions.</span>
|
|
|
|
<span class="sd"> :param l2_norm_added_delta: (float)</span>
|
|
<span class="sd"> A small value that will be added when calculating the weight of each of the DND entries. This follows the</span>
|
|
<span class="sd"> :math:`\delta` patameter defined in the paper.</span>
|
|
|
|
<span class="sd"> :param new_value_shift_coefficient: (float)</span>
|
|
<span class="sd"> In the case where a ew embedding that was added to the DND was already present, the value that will be stored</span>
|
|
<span class="sd"> in the DND is a mix between the existing value and the new value. The mix rate is defined by</span>
|
|
<span class="sd"> new_value_shift_coefficient.</span>
|
|
|
|
<span class="sd"> :param number_of_knn: (int)</span>
|
|
<span class="sd"> The number of neighbors that will be retrieved for each DND query.</span>
|
|
|
|
<span class="sd"> :param DND_key_error_threshold: (float)</span>
|
|
<span class="sd"> When the DND is queried for a specific embedding, this threshold will be used to determine if the embedding</span>
|
|
<span class="sd"> exists in the DND, since exact matches of embeddings are very rare.</span>
|
|
|
|
<span class="sd"> :param propagate_updates_to_DND: (bool)</span>
|
|
<span class="sd"> If set to True, when the gradients of the network will be calculated, the gradients will also be</span>
|
|
<span class="sd"> backpropagated through the keys of the DND. The keys will then be updated as well, as if they were regular</span>
|
|
<span class="sd"> network weights.</span>
|
|
|
|
<span class="sd"> :param n_step: (int)</span>
|
|
<span class="sd"> The bootstrap length that will be used when calculating the state values to store in the DND.</span>
|
|
|
|
<span class="sd"> :param bootstrap_total_return_from_old_policy: (bool)</span>
|
|
<span class="sd"> If set to True, the bootstrap that will be used to calculate each state-action value, is the network value</span>
|
|
<span class="sd"> when the state was first seen, and not the latest, most up-to-date network value.</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">dnd_size</span> <span class="o">=</span> <span class="mi">500000</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">l2_norm_added_delta</span> <span class="o">=</span> <span class="mf">0.001</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">new_value_shift_coefficient</span> <span class="o">=</span> <span class="mf">0.1</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">number_of_knn</span> <span class="o">=</span> <span class="mi">50</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">DND_key_error_threshold</span> <span class="o">=</span> <span class="mi">0</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">num_consecutive_playing_steps</span> <span class="o">=</span> <span class="n">EnvironmentSteps</span><span class="p">(</span><span class="mi">4</span><span class="p">)</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">propagate_updates_to_DND</span> <span class="o">=</span> <span class="kc">False</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">n_step</span> <span class="o">=</span> <span class="mi">100</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">bootstrap_total_return_from_old_policy</span> <span class="o">=</span> <span class="kc">True</span></div>
|
|
|
|
|
|
<span class="k">class</span> <span class="nc">NECMemoryParameters</span><span class="p">(</span><span class="n">EpisodicExperienceReplayParameters</span><span class="p">):</span>
|
|
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">max_size</span> <span class="o">=</span> <span class="p">(</span><span class="n">MemoryGranularity</span><span class="o">.</span><span class="n">Transitions</span><span class="p">,</span> <span class="mi">100000</span><span class="p">)</span>
|
|
|
|
|
|
<span class="k">class</span> <span class="nc">NECAgentParameters</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">NECAlgorithmParameters</span><span class="p">(),</span>
|
|
<span class="n">exploration</span><span class="o">=</span><span class="n">EGreedyParameters</span><span class="p">(),</span>
|
|
<span class="n">memory</span><span class="o">=</span><span class="n">NECMemoryParameters</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">NECNetworkParameters</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">ConstantSchedule</span><span class="p">(</span><span class="mf">0.1</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">0.01</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.nec_agent:NECAgent'</span>
|
|
|
|
|
|
<span class="c1"># Neural Episodic Control - https://arxiv.org/pdf/1703.01988.pdf</span>
|
|
<span class="k">class</span> <span class="nc">NECAgent</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">current_episode_state_embeddings</span> <span class="o">=</span> <span class="p">[]</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">training_started</span> <span class="o">=</span> <span class="kc">False</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">current_episode_buffer</span> <span class="o">=</span> \
|
|
<span class="n">Episode</span><span class="p">(</span><span class="n">discount</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="p">,</span>
|
|
<span class="n">n_step</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">n_step</span><span class="p">,</span>
|
|
<span class="n">bootstrap_total_return_from_old_policy</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">bootstrap_total_return_from_old_policy</span><span class="p">)</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="k">if</span> <span class="ow">not</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">DND</span><span class="o">.</span><span class="n">has_enough_entries</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">number_of_knn</span><span class="p">):</span>
|
|
<span class="k">return</span> <span class="mi">0</span><span class="p">,</span> <span class="p">[],</span> <span class="mi">0</span>
|
|
<span class="k">else</span><span class="p">:</span>
|
|
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">training_started</span><span class="p">:</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">training_started</span> <span class="o">=</span> <span class="kc">True</span>
|
|
<span class="n">screen</span><span class="o">.</span><span class="n">log_title</span><span class="p">(</span><span class="s2">"Finished collecting initial entries in DND. Starting to train network..."</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="n">TD_targets</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">predict</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="n">bootstrapped_return_from_old_policy</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="c1"># only update the action that we have actually done in this transition</span>
|
|
<span class="k">for</span> <span class="n">i</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">network_wrappers</span><span class="p">[</span><span class="s1">'main'</span><span class="p">]</span><span class="o">.</span><span class="n">batch_size</span><span class="p">):</span>
|
|
<span class="n">TD_targets</span><span class="p">[</span><span class="n">i</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="n">i</span><span class="p">]]</span> <span class="o">=</span> <span class="n">bootstrapped_return_from_old_policy</span><span class="p">[</span><span class="n">i</span><span class="p">]</span>
|
|
|
|
<span class="c1"># set the gradients to fetch for the DND update</span>
|
|
<span class="n">fetches</span> <span class="o">=</span> <span class="p">[]</span>
|
|
<span class="n">head</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">output_heads</span><span class="p">[</span><span class="mi">0</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">algorithm</span><span class="o">.</span><span class="n">propagate_updates_to_DND</span><span class="p">:</span>
|
|
<span class="n">fetches</span> <span class="o">=</span> <span class="p">[</span><span class="n">head</span><span class="o">.</span><span class="n">dnd_embeddings_grad</span><span class="p">,</span> <span class="n">head</span><span class="o">.</span><span class="n">dnd_values_grad</span><span class="p">,</span> <span class="n">head</span><span class="o">.</span><span class="n">dnd_indices</span><span class="p">]</span>
|
|
|
|
<span class="c1"># train the neural network</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="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="n">TD_targets</span><span class="p">,</span> <span class="n">fetches</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="c1"># update the DND keys and values using the extracted gradients</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">algorithm</span><span class="o">.</span><span class="n">propagate_updates_to_DND</span><span class="p">:</span>
|
|
<span class="n">embedding_gradients</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">swapaxes</span><span class="p">(</span><span class="n">result</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">][</span><span class="mi">0</span><span class="p">],</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
|
|
<span class="n">value_gradients</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">swapaxes</span><span class="p">(</span><span class="n">result</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">][</span><span class="mi">1</span><span class="p">],</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
|
|
<span class="n">indices</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">swapaxes</span><span class="p">(</span><span class="n">result</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">][</span><span class="mi">2</span><span class="p">],</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
|
|
<span class="n">head</span><span class="o">.</span><span class="n">DND</span><span class="o">.</span><span class="n">update_keys_and_values</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="n">embedding_gradients</span><span class="p">,</span> <span class="n">value_gradients</span><span class="p">,</span> <span class="n">indices</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>
|
|
|
|
<span class="k">def</span> <span class="nf">act</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">phase</span> <span class="o">==</span> <span class="n">RunPhase</span><span class="o">.</span><span class="n">HEATUP</span><span class="p">:</span>
|
|
<span class="c1"># get embedding in heatup (otherwise we get it through get_prediction)</span>
|
|
<span class="n">embedding</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">predict</span><span class="p">(</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">prepare_batch_for_inference</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">curr_state</span><span class="p">,</span> <span class="s1">'main'</span><span class="p">),</span>
|
|
<span class="n">outputs</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">state_embedding</span><span class="p">)</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">current_episode_state_embeddings</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">embedding</span><span class="p">)</span>
|
|
|
|
<span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">act</span><span class="p">()</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="c1"># we need to store the state embeddings regardless if the action is random or not</span>
|
|
<span class="k">return</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="k">def</span> <span class="nf">get_prediction</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="c1"># get the actions q values and the state embedding</span>
|
|
<span class="n">embedding</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">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">predict</span><span class="p">(</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">prepare_batch_for_inference</span><span class="p">(</span><span class="n">states</span><span class="p">,</span> <span class="s1">'main'</span><span class="p">),</span>
|
|
<span class="n">outputs</span><span class="o">=</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">state_embedding</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">output</span><span class="p">]</span>
|
|
<span class="p">)</span>
|
|
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">phase</span> <span class="o">!=</span> <span class="n">RunPhase</span><span class="o">.</span><span class="n">TEST</span><span class="p">:</span>
|
|
<span class="c1"># store the state embedding for inserting it to the DND later</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">current_episode_state_embeddings</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">embedding</span><span class="o">.</span><span class="n">squeeze</span><span class="p">())</span>
|
|
<span class="n">actions_q_values</span> <span class="o">=</span> <span class="n">actions_q_values</span><span class="p">[</span><span class="mi">0</span><span class="p">][</span><span class="mi">0</span><span class="p">]</span>
|
|
<span class="k">return</span> <span class="n">actions_q_values</span>
|
|
|
|
<span class="k">def</span> <span class="nf">reset_internal_state</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="n">reset_internal_state</span><span class="p">()</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">current_episode_state_embeddings</span> <span class="o">=</span> <span class="p">[]</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">current_episode_buffer</span> <span class="o">=</span> \
|
|
<span class="n">Episode</span><span class="p">(</span><span class="n">discount</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="p">,</span>
|
|
<span class="n">n_step</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">n_step</span><span class="p">,</span>
|
|
<span class="n">bootstrap_total_return_from_old_policy</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">bootstrap_total_return_from_old_policy</span><span class="p">)</span>
|
|
|
|
<span class="k">def</span> <span class="nf">handle_episode_ended</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="n">handle_episode_ended</span><span class="p">()</span>
|
|
|
|
<span class="c1"># get the last full episode that we have collected</span>
|
|
<span class="n">episode</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">'get_last_complete_episode'</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">episode</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">phase</span> <span class="o">!=</span> <span class="n">RunPhase</span><span class="o">.</span><span class="n">TEST</span><span class="p">:</span>
|
|
<span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">current_episode_state_embeddings</span><span class="p">)</span> <span class="o">==</span> <span class="n">episode</span><span class="o">.</span><span class="n">length</span><span class="p">()</span>
|
|
<span class="n">discounted_rewards</span> <span class="o">=</span> <span class="n">episode</span><span class="o">.</span><span class="n">get_transitions_attribute</span><span class="p">(</span><span class="s1">'n_step_discounted_rewards'</span><span class="p">)</span>
|
|
<span class="n">actions</span> <span class="o">=</span> <span class="n">episode</span><span class="o">.</span><span class="n">get_transitions_attribute</span><span class="p">(</span><span class="s1">'action'</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">DND</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">current_episode_state_embeddings</span><span class="p">,</span>
|
|
<span class="n">actions</span><span class="p">,</span> <span class="n">discounted_rewards</span><span class="p">)</span>
|
|
|
|
<span class="k">def</span> <span class="nf">save_checkpoint</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">checkpoint_id</span><span class="p">):</span>
|
|
<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</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">task_parameters</span><span class="o">.</span><span class="n">checkpoint_save_dir</span><span class="p">,</span> <span class="nb">str</span><span class="p">(</span><span class="n">checkpoint_id</span><span class="p">)</span> <span class="o">+</span> <span class="s1">'.dnd'</span><span class="p">),</span> <span class="s1">'wb'</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
|
|
<span class="n">pickle</span><span class="o">.</span><span class="n">dump</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">DND</span><span class="p">,</span> <span class="n">f</span><span class="p">,</span> <span class="n">pickle</span><span class="o">.</span><span class="n">HIGHEST_PROTOCOL</span><span class="p">)</span>
|
|
</pre></div>
|
|
|
|
</div>
|
|
|
|
</div>
|
|
<footer>
|
|
|
|
|
|
<hr/>
|
|
|
|
<div role="contentinfo">
|
|
<p>
|
|
© Copyright 2018, Intel AI Lab
|
|
|
|
</p>
|
|
</div>
|
|
Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
|
|
|
|
</footer>
|
|
|
|
</div>
|
|
</div>
|
|
|
|
</section>
|
|
|
|
</div>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<script type="text/javascript" id="documentation_options" data-url_root="../../../" src="../../../_static/documentation_options.js"></script>
|
|
<script type="text/javascript" src="../../../_static/jquery.js"></script>
|
|
<script type="text/javascript" src="../../../_static/underscore.js"></script>
|
|
<script type="text/javascript" src="../../../_static/doctools.js"></script>
|
|
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></script>
|
|
|
|
|
|
|
|
|
|
<script type="text/javascript" src="../../../_static/js/theme.js"></script>
|
|
|
|
<script type="text/javascript">
|
|
jQuery(function () {
|
|
SphinxRtdTheme.Navigation.enable(true);
|
|
});
|
|
</script>
|
|
|
|
</body>
|
|
</html> |