mirror of
https://github.com/gryf/coach.git
synced 2025-12-17 19:20:19 +01:00
74db141d5e
* SAC algorithm * SAC - updates to agent (learn_from_batch), sac_head and sac_q_head to fix problem in gradient calculation. Now SAC agents is able to train. gym_environment - fixing an error in access to gym.spaces * Soft Actor Critic - code cleanup * code cleanup * V-head initialization fix * SAC benchmarks * SAC Documentation * typo fix * documentation fixes * documentation and version update * README typo
876 lines
50 KiB
HTML
876 lines
50 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>Agents — 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 rel="next" title="Actor-Critic" href="policy_optimization/ac.html" />
|
||
<link rel="prev" title="Adding a New Environment" href="../../contributing/add_env.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="../../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 class="current">
|
||
<li class="toctree-l1 current"><a class="current reference internal" href="#">Agents</a><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="policy_optimization/ac.html">Actor-Critic</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="policy_optimization/acer.html">ACER</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="imitation/bc.html">Behavioral Cloning</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="value_optimization/bs_dqn.html">Bootstrapped DQN</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="value_optimization/categorical_dqn.html">Categorical DQN</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="imitation/cil.html">Conditional Imitation Learning</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="policy_optimization/cppo.html">Clipped Proximal Policy Optimization</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="policy_optimization/ddpg.html">Deep Deterministic Policy Gradient</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="policy_optimization/sac.html">Soft Actor-Critic</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="other/dfp.html">Direct Future Prediction</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="value_optimization/double_dqn.html">Double DQN</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="value_optimization/dqn.html">Deep Q Networks</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="value_optimization/dueling_dqn.html">Dueling DQN</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="value_optimization/mmc.html">Mixed Monte Carlo</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="value_optimization/n_step.html">N-Step Q Learning</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="value_optimization/naf.html">Normalized Advantage Functions</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="value_optimization/nec.html">Neural Episodic Control</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="value_optimization/pal.html">Persistent Advantage Learning</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="policy_optimization/pg.html">Policy Gradient</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="policy_optimization/ppo.html">Proximal Policy Optimization</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="value_optimization/rainbow.html">Rainbow</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="value_optimization/qr_dqn.html">Quantile Regression DQN</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../architectures/index.html">Architectures</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../data_stores/index.html">Data Stores</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../environments/index.html">Environments</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../exploration_policies/index.html">Exploration Policies</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../filters/index.html">Filters</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../memories/index.html">Memories</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../memory_backends/index.html">Memory Backends</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../orchestrators/index.html">Orchestrators</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../core_types.html">Core Types</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../spaces.html">Spaces</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../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>Agents</li>
|
||
|
||
|
||
<li class="wy-breadcrumbs-aside">
|
||
|
||
|
||
<a href="../../_sources/components/agents/index.rst.txt" rel="nofollow"> View page source</a>
|
||
|
||
|
||
</li>
|
||
|
||
</ul>
|
||
|
||
|
||
<hr/>
|
||
</div>
|
||
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
|
||
<div itemprop="articleBody">
|
||
|
||
<div class="section" id="agents">
|
||
<h1>Agents<a class="headerlink" href="#agents" title="Permalink to this headline">¶</a></h1>
|
||
<p>Coach supports many state-of-the-art reinforcement learning algorithms, which are separated into three main classes -
|
||
value optimization, policy optimization and imitation learning.
|
||
A detailed description of those algorithms can be found by navigating to each of the algorithm pages.</p>
|
||
<a class="reference internal image-reference" href="../../_images/algorithms.png"><img alt="../../_images/algorithms.png" class="align-center" src="../../_images/algorithms.png" style="width: 600px;" /></a>
|
||
<div class="toctree-wrapper compound">
|
||
<p class="caption"><span class="caption-text">Agents</span></p>
|
||
<ul>
|
||
<li class="toctree-l1"><a class="reference internal" href="policy_optimization/ac.html">Actor-Critic</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="policy_optimization/acer.html">ACER</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="imitation/bc.html">Behavioral Cloning</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="value_optimization/bs_dqn.html">Bootstrapped DQN</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="value_optimization/categorical_dqn.html">Categorical DQN</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="imitation/cil.html">Conditional Imitation Learning</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="policy_optimization/cppo.html">Clipped Proximal Policy Optimization</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="policy_optimization/ddpg.html">Deep Deterministic Policy Gradient</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="policy_optimization/sac.html">Soft Actor-Critic</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="other/dfp.html">Direct Future Prediction</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="value_optimization/double_dqn.html">Double DQN</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="value_optimization/dqn.html">Deep Q Networks</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="value_optimization/dueling_dqn.html">Dueling DQN</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="value_optimization/mmc.html">Mixed Monte Carlo</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="value_optimization/n_step.html">N-Step Q Learning</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="value_optimization/naf.html">Normalized Advantage Functions</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="value_optimization/nec.html">Neural Episodic Control</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="value_optimization/pal.html">Persistent Advantage Learning</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="policy_optimization/pg.html">Policy Gradient</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="policy_optimization/ppo.html">Proximal Policy Optimization</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="value_optimization/rainbow.html">Rainbow</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="value_optimization/qr_dqn.html">Quantile Regression DQN</a></li>
|
||
</ul>
|
||
</div>
|
||
<dl class="class">
|
||
<dt id="rl_coach.base_parameters.AgentParameters">
|
||
<em class="property">class </em><code class="descclassname">rl_coach.base_parameters.</code><code class="descname">AgentParameters</code><span class="sig-paren">(</span><em>algorithm: rl_coach.base_parameters.AlgorithmParameters, exploration: ExplorationParameters, memory: MemoryParameters, networks: Dict[str, rl_coach.base_parameters.NetworkParameters], visualization: rl_coach.base_parameters.VisualizationParameters = <rl_coach.base_parameters.VisualizationParameters object></em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/base_parameters.html#AgentParameters"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.base_parameters.AgentParameters" title="Permalink to this definition">¶</a></dt>
|
||
<dd><table class="docutils field-list" frame="void" rules="none">
|
||
<col class="field-name" />
|
||
<col class="field-body" />
|
||
<tbody valign="top">
|
||
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple">
|
||
<li><strong>algorithm</strong> – A class inheriting AlgorithmParameters.
|
||
The parameters used for the specific algorithm used by the agent.
|
||
These parameters can be later referenced in the agent implementation through self.ap.algorithm.</li>
|
||
<li><strong>exploration</strong> – Either a class inheriting ExplorationParameters or a dictionary mapping between action
|
||
space types and their corresponding ExplorationParameters. If a dictionary was used,
|
||
when the agent will be instantiated, the correct exploration policy parameters will be used
|
||
according to the real type of the environment action space.
|
||
These parameters will be used to instantiate the exporation policy.</li>
|
||
<li><strong>memory</strong> – A class inheriting MemoryParameters. It defines all the parameters used by the memory module.</li>
|
||
<li><strong>networks</strong> – A dictionary mapping between network names and their corresponding network parmeters, defined
|
||
as a class inheriting NetworkParameters. Each element will be used in order to instantiate
|
||
a NetworkWrapper class, and all the network wrappers will be stored in the agent under
|
||
self.network_wrappers. self.network_wrappers is a dict mapping between the network name that
|
||
was given in the networks dict, and the instantiated network wrapper.</li>
|
||
<li><strong>visualization</strong> – A class inheriting VisualizationParameters and defining various parameters that can be
|
||
used for visualization purposes, such as printing to the screen, rendering, and saving videos.</li>
|
||
</ul>
|
||
</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</dd></dl>
|
||
|
||
<dl class="class">
|
||
<dt id="rl_coach.agents.agent.Agent">
|
||
<em class="property">class </em><code class="descclassname">rl_coach.agents.agent.</code><code class="descname">Agent</code><span class="sig-paren">(</span><em>agent_parameters: rl_coach.base_parameters.AgentParameters</em>, <em>parent: Union[LevelManager</em>, <em>CompositeAgent] = None</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent" title="Permalink to this definition">¶</a></dt>
|
||
<dd><table class="docutils field-list" frame="void" rules="none">
|
||
<col class="field-name" />
|
||
<col class="field-body" />
|
||
<tbody valign="top">
|
||
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><strong>agent_parameters</strong> – A AgentParameters class instance with all the agent parameters</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
<dl class="method">
|
||
<dt id="rl_coach.agents.agent.Agent.act">
|
||
<code class="descname">act</code><span class="sig-paren">(</span><em>action: Union[None</em>, <em>int</em>, <em>float</em>, <em>numpy.ndarray</em>, <em>List] = None</em><span class="sig-paren">)</span> → rl_coach.core_types.ActionInfo<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.act"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.act" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>Given the agents current knowledge, decide on the next action to apply to the environment</p>
|
||
<table class="docutils field-list" frame="void" rules="none">
|
||
<col class="field-name" />
|
||
<col class="field-body" />
|
||
<tbody valign="top">
|
||
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><strong>action</strong> – An action to take, overriding whatever the current policy is</td>
|
||
</tr>
|
||
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body">An ActionInfo object, which contains the action and any additional info from the action decision process</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</dd></dl>
|
||
|
||
<dl class="method">
|
||
<dt id="rl_coach.agents.agent.Agent.call_memory">
|
||
<code class="descname">call_memory</code><span class="sig-paren">(</span><em>func</em>, <em>args=()</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.call_memory"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.call_memory" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>This function is a wrapper to allow having the same calls for shared or unshared memories.
|
||
It should be used instead of calling the memory directly in order to allow different algorithms to work
|
||
both with a shared and a local memory.</p>
|
||
<table class="docutils field-list" frame="void" rules="none">
|
||
<col class="field-name" />
|
||
<col class="field-body" />
|
||
<tbody valign="top">
|
||
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple">
|
||
<li><strong>func</strong> – the name of the memory function to call</li>
|
||
<li><strong>args</strong> – the arguments to supply to the function</li>
|
||
</ul>
|
||
</td>
|
||
</tr>
|
||
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body"><p class="first last">the return value of the function</p>
|
||
</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</dd></dl>
|
||
|
||
<dl class="method">
|
||
<dt id="rl_coach.agents.agent.Agent.choose_action">
|
||
<code class="descname">choose_action</code><span class="sig-paren">(</span><em>curr_state</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.choose_action"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.choose_action" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>choose an action to act with in the current episode being played. Different behavior might be exhibited when
|
||
training or testing.</p>
|
||
<table class="docutils field-list" frame="void" rules="none">
|
||
<col class="field-name" />
|
||
<col class="field-body" />
|
||
<tbody valign="top">
|
||
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><strong>curr_state</strong> – the current state to act upon.</td>
|
||
</tr>
|
||
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body">chosen action, some action value describing the action (q-value, probability, etc)</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</dd></dl>
|
||
|
||
<dl class="method">
|
||
<dt id="rl_coach.agents.agent.Agent.collect_savers">
|
||
<code class="descname">collect_savers</code><span class="sig-paren">(</span><em>parent_path_suffix: str</em><span class="sig-paren">)</span> → rl_coach.saver.SaverCollection<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.collect_savers"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.collect_savers" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>Collect all of agent’s network savers
|
||
:param parent_path_suffix: path suffix of the parent of the agent
|
||
(could be name of level manager or composite agent)
|
||
:return: collection of all agent savers</p>
|
||
</dd></dl>
|
||
|
||
<dl class="method">
|
||
<dt id="rl_coach.agents.agent.Agent.create_networks">
|
||
<code class="descname">create_networks</code><span class="sig-paren">(</span><span class="sig-paren">)</span> → Dict[str, rl_coach.architectures.network_wrapper.NetworkWrapper]<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.create_networks"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.create_networks" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>Create all the networks of the agent.
|
||
The network creation will be done after setting the environment parameters for the agent, since they are needed
|
||
for creating the network.</p>
|
||
<table class="docutils field-list" frame="void" rules="none">
|
||
<col class="field-name" />
|
||
<col class="field-body" />
|
||
<tbody valign="top">
|
||
<tr class="field-odd field"><th class="field-name">Returns:</th><td class="field-body">A list containing all the networks</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</dd></dl>
|
||
|
||
<dl class="method">
|
||
<dt id="rl_coach.agents.agent.Agent.get_predictions">
|
||
<code class="descname">get_predictions</code><span class="sig-paren">(</span><em>states: List[Dict[str, numpy.ndarray]], prediction_type: rl_coach.core_types.PredictionType</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.get_predictions"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.get_predictions" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>Get a prediction from the agent with regard to the requested prediction_type.
|
||
If the agent cannot predict this type of prediction_type, or if there is more than possible way to do so,
|
||
raise a ValueException.</p>
|
||
<table class="docutils field-list" frame="void" rules="none">
|
||
<col class="field-name" />
|
||
<col class="field-body" />
|
||
<tbody valign="top">
|
||
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple">
|
||
<li><strong>states</strong> – The states to get a prediction for</li>
|
||
<li><strong>prediction_type</strong> – The type of prediction to get for the states. For example, the state-value prediction.</li>
|
||
</ul>
|
||
</td>
|
||
</tr>
|
||
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body"><p class="first last">the predicted values</p>
|
||
</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</dd></dl>
|
||
|
||
<dl class="method">
|
||
<dt id="rl_coach.agents.agent.Agent.get_state_embedding">
|
||
<code class="descname">get_state_embedding</code><span class="sig-paren">(</span><em>state: dict</em><span class="sig-paren">)</span> → numpy.ndarray<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.get_state_embedding"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.get_state_embedding" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>Given a state, get the corresponding state embedding from the main network</p>
|
||
<table class="docutils field-list" frame="void" rules="none">
|
||
<col class="field-name" />
|
||
<col class="field-body" />
|
||
<tbody valign="top">
|
||
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><strong>state</strong> – a state dict</td>
|
||
</tr>
|
||
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body">a numpy embedding vector</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</dd></dl>
|
||
|
||
<dl class="method">
|
||
<dt id="rl_coach.agents.agent.Agent.handle_episode_ended">
|
||
<code class="descname">handle_episode_ended</code><span class="sig-paren">(</span><span class="sig-paren">)</span> → None<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.handle_episode_ended"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.handle_episode_ended" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>Make any changes needed when each episode is ended.
|
||
This includes incrementing counters, updating full episode dependent values, updating logs, etc.
|
||
This function is called right after each episode is ended.</p>
|
||
<table class="docutils field-list" frame="void" rules="none">
|
||
<col class="field-name" />
|
||
<col class="field-body" />
|
||
<tbody valign="top">
|
||
<tr class="field-odd field"><th class="field-name">Returns:</th><td class="field-body">None</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</dd></dl>
|
||
|
||
<dl class="method">
|
||
<dt id="rl_coach.agents.agent.Agent.init_environment_dependent_modules">
|
||
<code class="descname">init_environment_dependent_modules</code><span class="sig-paren">(</span><span class="sig-paren">)</span> → None<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.init_environment_dependent_modules"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.init_environment_dependent_modules" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>Initialize any modules that depend on knowing information about the environment such as the action space or
|
||
the observation space</p>
|
||
<table class="docutils field-list" frame="void" rules="none">
|
||
<col class="field-name" />
|
||
<col class="field-body" />
|
||
<tbody valign="top">
|
||
<tr class="field-odd field"><th class="field-name">Returns:</th><td class="field-body">None</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</dd></dl>
|
||
|
||
<dl class="method">
|
||
<dt id="rl_coach.agents.agent.Agent.learn_from_batch">
|
||
<code class="descname">learn_from_batch</code><span class="sig-paren">(</span><em>batch</em><span class="sig-paren">)</span> → Tuple[float, List, List]<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.learn_from_batch"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.learn_from_batch" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>Given a batch of transitions, calculates their target values and updates the network.</p>
|
||
<table class="docutils field-list" frame="void" rules="none">
|
||
<col class="field-name" />
|
||
<col class="field-body" />
|
||
<tbody valign="top">
|
||
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><strong>batch</strong> – A list of transitions</td>
|
||
</tr>
|
||
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body">The total loss of the training, the loss per head and the unclipped gradients</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</dd></dl>
|
||
|
||
<dl class="method">
|
||
<dt id="rl_coach.agents.agent.Agent.log_to_screen">
|
||
<code class="descname">log_to_screen</code><span class="sig-paren">(</span><span class="sig-paren">)</span> → None<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.log_to_screen"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.log_to_screen" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>Write an episode summary line to the terminal</p>
|
||
<table class="docutils field-list" frame="void" rules="none">
|
||
<col class="field-name" />
|
||
<col class="field-body" />
|
||
<tbody valign="top">
|
||
<tr class="field-odd field"><th class="field-name">Returns:</th><td class="field-body">None</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</dd></dl>
|
||
|
||
<dl class="method">
|
||
<dt id="rl_coach.agents.agent.Agent.observe">
|
||
<code class="descname">observe</code><span class="sig-paren">(</span><em>env_response: rl_coach.core_types.EnvResponse</em><span class="sig-paren">)</span> → bool<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.observe"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.observe" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>Given a response from the environment, distill the observation from it and store it for later use.
|
||
The response should be a dictionary containing the performed action, the new observation and measurements,
|
||
the reward, a game over flag and any additional information necessary.</p>
|
||
<table class="docutils field-list" frame="void" rules="none">
|
||
<col class="field-name" />
|
||
<col class="field-body" />
|
||
<tbody valign="top">
|
||
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><strong>env_response</strong> – result of call from environment.step(action)</td>
|
||
</tr>
|
||
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body">a boolean value which determines if the agent has decided to terminate the episode after seeing the
|
||
given observation</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</dd></dl>
|
||
|
||
<dl class="attribute">
|
||
<dt id="rl_coach.agents.agent.Agent.parent">
|
||
<code class="descname">parent</code><a class="headerlink" href="#rl_coach.agents.agent.Agent.parent" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>Get the parent class of the agent</p>
|
||
<table class="docutils field-list" frame="void" rules="none">
|
||
<col class="field-name" />
|
||
<col class="field-body" />
|
||
<tbody valign="top">
|
||
<tr class="field-odd field"><th class="field-name">Returns:</th><td class="field-body">the current phase</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</dd></dl>
|
||
|
||
<dl class="attribute">
|
||
<dt id="rl_coach.agents.agent.Agent.phase">
|
||
<code class="descname">phase</code><a class="headerlink" href="#rl_coach.agents.agent.Agent.phase" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>The current running phase of the agent</p>
|
||
<table class="docutils field-list" frame="void" rules="none">
|
||
<col class="field-name" />
|
||
<col class="field-body" />
|
||
<tbody valign="top">
|
||
<tr class="field-odd field"><th class="field-name">Returns:</th><td class="field-body">RunPhase</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</dd></dl>
|
||
|
||
<dl class="method">
|
||
<dt id="rl_coach.agents.agent.Agent.post_training_commands">
|
||
<code class="descname">post_training_commands</code><span class="sig-paren">(</span><span class="sig-paren">)</span> → None<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.post_training_commands"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.post_training_commands" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>A function which allows adding any functionality that is required to run right after the training phase ends.</p>
|
||
<table class="docutils field-list" frame="void" rules="none">
|
||
<col class="field-name" />
|
||
<col class="field-body" />
|
||
<tbody valign="top">
|
||
<tr class="field-odd field"><th class="field-name">Returns:</th><td class="field-body">None</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</dd></dl>
|
||
|
||
<dl class="method">
|
||
<dt id="rl_coach.agents.agent.Agent.prepare_batch_for_inference">
|
||
<code class="descname">prepare_batch_for_inference</code><span class="sig-paren">(</span><em>states: Union[Dict[str, numpy.ndarray], List[Dict[str, numpy.ndarray]]], network_name: str</em><span class="sig-paren">)</span> → Dict[str, numpy.array]<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.prepare_batch_for_inference"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.prepare_batch_for_inference" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>Convert curr_state into input tensors tensorflow is expecting. i.e. if we have several inputs states, stack all
|
||
observations together, measurements together, etc.</p>
|
||
<table class="docutils field-list" frame="void" rules="none">
|
||
<col class="field-name" />
|
||
<col class="field-body" />
|
||
<tbody valign="top">
|
||
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple">
|
||
<li><strong>states</strong> – A list of environment states, where each one is a dict mapping from an observation name to its
|
||
corresponding observation</li>
|
||
<li><strong>network_name</strong> – The agent network name to prepare the batch for. this is needed in order to extract only
|
||
the observation relevant for the network from the states.</li>
|
||
</ul>
|
||
</td>
|
||
</tr>
|
||
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body"><p class="first last">A dictionary containing a list of values from all the given states for each of the observations</p>
|
||
</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</dd></dl>
|
||
|
||
<dl class="method">
|
||
<dt id="rl_coach.agents.agent.Agent.register_signal">
|
||
<code class="descname">register_signal</code><span class="sig-paren">(</span><em>signal_name: str</em>, <em>dump_one_value_per_episode: bool = True</em>, <em>dump_one_value_per_step: bool = False</em><span class="sig-paren">)</span> → rl_coach.utils.Signal<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.register_signal"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.register_signal" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>Register a signal such that its statistics will be dumped and be viewable through dashboard</p>
|
||
<table class="docutils field-list" frame="void" rules="none">
|
||
<col class="field-name" />
|
||
<col class="field-body" />
|
||
<tbody valign="top">
|
||
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple">
|
||
<li><strong>signal_name</strong> – the name of the signal as it will appear in dashboard</li>
|
||
<li><strong>dump_one_value_per_episode</strong> – should the signal value be written for each episode?</li>
|
||
<li><strong>dump_one_value_per_step</strong> – should the signal value be written for each step?</li>
|
||
</ul>
|
||
</td>
|
||
</tr>
|
||
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body"><p class="first last">the created signal</p>
|
||
</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</dd></dl>
|
||
|
||
<dl class="method">
|
||
<dt id="rl_coach.agents.agent.Agent.reset_evaluation_state">
|
||
<code class="descname">reset_evaluation_state</code><span class="sig-paren">(</span><em>val: rl_coach.core_types.RunPhase</em><span class="sig-paren">)</span> → None<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.reset_evaluation_state"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.reset_evaluation_state" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>Perform accumulators initialization when entering an evaluation phase, and signal dumping when exiting an
|
||
evaluation phase. Entering or exiting the evaluation phase is determined according to the new phase given
|
||
by val, and by the current phase set in self.phase.</p>
|
||
<table class="docutils field-list" frame="void" rules="none">
|
||
<col class="field-name" />
|
||
<col class="field-body" />
|
||
<tbody valign="top">
|
||
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><strong>val</strong> – The new phase to change to</td>
|
||
</tr>
|
||
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body">None</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</dd></dl>
|
||
|
||
<dl class="method">
|
||
<dt id="rl_coach.agents.agent.Agent.reset_internal_state">
|
||
<code class="descname">reset_internal_state</code><span class="sig-paren">(</span><span class="sig-paren">)</span> → None<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.reset_internal_state"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.reset_internal_state" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>Reset all the episodic parameters. This function is called right before each episode starts.</p>
|
||
<table class="docutils field-list" frame="void" rules="none">
|
||
<col class="field-name" />
|
||
<col class="field-body" />
|
||
<tbody valign="top">
|
||
<tr class="field-odd field"><th class="field-name">Returns:</th><td class="field-body">None</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</dd></dl>
|
||
|
||
<dl class="method">
|
||
<dt id="rl_coach.agents.agent.Agent.restore_checkpoint">
|
||
<code class="descname">restore_checkpoint</code><span class="sig-paren">(</span><em>checkpoint_dir: str</em><span class="sig-paren">)</span> → None<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.restore_checkpoint"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.restore_checkpoint" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>Allows agents to store additional information when saving checkpoints.</p>
|
||
<table class="docutils field-list" frame="void" rules="none">
|
||
<col class="field-name" />
|
||
<col class="field-body" />
|
||
<tbody valign="top">
|
||
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><strong>checkpoint_dir</strong> – The checkpoint dir to restore from</td>
|
||
</tr>
|
||
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body">None</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</dd></dl>
|
||
|
||
<dl class="method">
|
||
<dt id="rl_coach.agents.agent.Agent.run_off_policy_evaluation">
|
||
<code class="descname">run_off_policy_evaluation</code><span class="sig-paren">(</span><span class="sig-paren">)</span> → None<a class="headerlink" href="#rl_coach.agents.agent.Agent.run_off_policy_evaluation" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>Run off-policy evaluation estimators to evaluate the trained policy performance against a dataset.
|
||
Should only be implemented for off-policy RL algorithms.</p>
|
||
<table class="docutils field-list" frame="void" rules="none">
|
||
<col class="field-name" />
|
||
<col class="field-body" />
|
||
<tbody valign="top">
|
||
<tr class="field-odd field"><th class="field-name">Returns:</th><td class="field-body">None</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</dd></dl>
|
||
|
||
<dl class="method">
|
||
<dt id="rl_coach.agents.agent.Agent.run_pre_network_filter_for_inference">
|
||
<code class="descname">run_pre_network_filter_for_inference</code><span class="sig-paren">(</span><em>state: Dict[str, numpy.ndarray], update_filter_internal_state: bool = True</em><span class="sig-paren">)</span> → Dict[str, numpy.ndarray]<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.run_pre_network_filter_for_inference"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.run_pre_network_filter_for_inference" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>Run filters which where defined for being applied right before using the state for inference.</p>
|
||
<table class="docutils field-list" frame="void" rules="none">
|
||
<col class="field-name" />
|
||
<col class="field-body" />
|
||
<tbody valign="top">
|
||
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple">
|
||
<li><strong>state</strong> – The state to run the filters on</li>
|
||
<li><strong>update_filter_internal_state</strong> – Should update the filter’s internal state - should not update when evaluating</li>
|
||
</ul>
|
||
</td>
|
||
</tr>
|
||
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body"><p class="first last">The filtered state</p>
|
||
</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</dd></dl>
|
||
|
||
<dl class="method">
|
||
<dt id="rl_coach.agents.agent.Agent.save_checkpoint">
|
||
<code class="descname">save_checkpoint</code><span class="sig-paren">(</span><em>checkpoint_prefix: str</em><span class="sig-paren">)</span> → None<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.save_checkpoint"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.save_checkpoint" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>Allows agents to store additional information when saving checkpoints.</p>
|
||
<table class="docutils field-list" frame="void" rules="none">
|
||
<col class="field-name" />
|
||
<col class="field-body" />
|
||
<tbody valign="top">
|
||
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><strong>checkpoint_prefix</strong> – The prefix of the checkpoint file to save</td>
|
||
</tr>
|
||
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body">None</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</dd></dl>
|
||
|
||
<dl class="method">
|
||
<dt id="rl_coach.agents.agent.Agent.set_environment_parameters">
|
||
<code class="descname">set_environment_parameters</code><span class="sig-paren">(</span><em>spaces: rl_coach.spaces.SpacesDefinition</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.set_environment_parameters"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.set_environment_parameters" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>Sets the parameters that are environment dependent. As a side effect, initializes all the components that are
|
||
dependent on those values, by calling init_environment_dependent_modules</p>
|
||
<table class="docutils field-list" frame="void" rules="none">
|
||
<col class="field-name" />
|
||
<col class="field-body" />
|
||
<tbody valign="top">
|
||
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><strong>spaces</strong> – the environment spaces definition</td>
|
||
</tr>
|
||
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body">None</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</dd></dl>
|
||
|
||
<dl class="method">
|
||
<dt id="rl_coach.agents.agent.Agent.set_incoming_directive">
|
||
<code class="descname">set_incoming_directive</code><span class="sig-paren">(</span><em>action: Union[int, float, numpy.ndarray, List]</em><span class="sig-paren">)</span> → None<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.set_incoming_directive"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.set_incoming_directive" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>Allows setting a directive for the agent to follow. This is useful in hierarchy structures, where the agent
|
||
has another master agent that is controlling it. In such cases, the master agent can define the goals for the
|
||
slave agent, define it’s observation, possible actions, etc. The directive type is defined by the agent
|
||
in-action-space.</p>
|
||
<table class="docutils field-list" frame="void" rules="none">
|
||
<col class="field-name" />
|
||
<col class="field-body" />
|
||
<tbody valign="top">
|
||
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><strong>action</strong> – The action that should be set as the directive</td>
|
||
</tr>
|
||
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body"></td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</dd></dl>
|
||
|
||
<dl class="method">
|
||
<dt id="rl_coach.agents.agent.Agent.set_session">
|
||
<code class="descname">set_session</code><span class="sig-paren">(</span><em>sess</em><span class="sig-paren">)</span> → None<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.set_session"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.set_session" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>Set the deep learning framework session for all the agents in the composite agent</p>
|
||
<table class="docutils field-list" frame="void" rules="none">
|
||
<col class="field-name" />
|
||
<col class="field-body" />
|
||
<tbody valign="top">
|
||
<tr class="field-odd field"><th class="field-name">Returns:</th><td class="field-body">None</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</dd></dl>
|
||
|
||
<dl class="method">
|
||
<dt id="rl_coach.agents.agent.Agent.setup_logger">
|
||
<code class="descname">setup_logger</code><span class="sig-paren">(</span><span class="sig-paren">)</span> → None<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.setup_logger"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.setup_logger" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>Setup the logger for the agent</p>
|
||
<table class="docutils field-list" frame="void" rules="none">
|
||
<col class="field-name" />
|
||
<col class="field-body" />
|
||
<tbody valign="top">
|
||
<tr class="field-odd field"><th class="field-name">Returns:</th><td class="field-body">None</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</dd></dl>
|
||
|
||
<dl class="method">
|
||
<dt id="rl_coach.agents.agent.Agent.sync">
|
||
<code class="descname">sync</code><span class="sig-paren">(</span><span class="sig-paren">)</span> → None<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.sync"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.sync" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>Sync the global network parameters to local networks</p>
|
||
<table class="docutils field-list" frame="void" rules="none">
|
||
<col class="field-name" />
|
||
<col class="field-body" />
|
||
<tbody valign="top">
|
||
<tr class="field-odd field"><th class="field-name">Returns:</th><td class="field-body">None</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</dd></dl>
|
||
|
||
<dl class="method">
|
||
<dt id="rl_coach.agents.agent.Agent.train">
|
||
<code class="descname">train</code><span class="sig-paren">(</span><span class="sig-paren">)</span> → float<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.train"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.train" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>Check if a training phase should be done as configured by num_consecutive_playing_steps.
|
||
If it should, then do several training steps as configured by num_consecutive_training_steps.
|
||
A single training iteration: Sample a batch, train on it and update target networks.</p>
|
||
<table class="docutils field-list" frame="void" rules="none">
|
||
<col class="field-name" />
|
||
<col class="field-body" />
|
||
<tbody valign="top">
|
||
<tr class="field-odd field"><th class="field-name">Returns:</th><td class="field-body">The total training loss during the training iterations.</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</dd></dl>
|
||
|
||
<dl class="method">
|
||
<dt id="rl_coach.agents.agent.Agent.update_log">
|
||
<code class="descname">update_log</code><span class="sig-paren">(</span><span class="sig-paren">)</span> → None<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.update_log"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.update_log" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>Updates the episodic log file with all the signal values from the most recent episode.
|
||
Additional signals for logging can be set by the creating a new signal using self.register_signal,
|
||
and then updating it with some internal agent values.</p>
|
||
<table class="docutils field-list" frame="void" rules="none">
|
||
<col class="field-name" />
|
||
<col class="field-body" />
|
||
<tbody valign="top">
|
||
<tr class="field-odd field"><th class="field-name">Returns:</th><td class="field-body">None</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</dd></dl>
|
||
|
||
<dl class="method">
|
||
<dt id="rl_coach.agents.agent.Agent.update_step_in_episode_log">
|
||
<code class="descname">update_step_in_episode_log</code><span class="sig-paren">(</span><span class="sig-paren">)</span> → None<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.update_step_in_episode_log"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.update_step_in_episode_log" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>Updates the in-episode log file with all the signal values from the most recent step.</p>
|
||
<table class="docutils field-list" frame="void" rules="none">
|
||
<col class="field-name" />
|
||
<col class="field-body" />
|
||
<tbody valign="top">
|
||
<tr class="field-odd field"><th class="field-name">Returns:</th><td class="field-body">None</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</dd></dl>
|
||
|
||
<dl class="method">
|
||
<dt id="rl_coach.agents.agent.Agent.update_transition_before_adding_to_replay_buffer">
|
||
<code class="descname">update_transition_before_adding_to_replay_buffer</code><span class="sig-paren">(</span><em>transition: rl_coach.core_types.Transition</em><span class="sig-paren">)</span> → rl_coach.core_types.Transition<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.update_transition_before_adding_to_replay_buffer"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.update_transition_before_adding_to_replay_buffer" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>Allows agents to update the transition just before adding it to the replay buffer.
|
||
Can be useful for agents that want to tweak the reward, termination signal, etc.</p>
|
||
<table class="docutils field-list" frame="void" rules="none">
|
||
<col class="field-name" />
|
||
<col class="field-body" />
|
||
<tbody valign="top">
|
||
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><strong>transition</strong> – the transition to update</td>
|
||
</tr>
|
||
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body">the updated transition</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
</dd></dl>
|
||
|
||
</dd></dl>
|
||
|
||
</div>
|
||
|
||
|
||
</div>
|
||
|
||
</div>
|
||
<footer>
|
||
|
||
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
|
||
|
||
<a href="policy_optimization/ac.html" class="btn btn-neutral float-right" title="Actor-Critic" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a>
|
||
|
||
|
||
<a href="../../contributing/add_env.html" class="btn btn-neutral" title="Adding a New Environment" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left"></span> Previous</a>
|
||
|
||
</div>
|
||
|
||
|
||
<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 type="text/javascript" src="../../_static/language_data.js"></script>
|
||
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
|
||
|
||
|
||
|
||
|
||
<script type="text/javascript" src="../../_static/js/theme.js"></script>
|
||
|
||
<script type="text/javascript">
|
||
jQuery(function () {
|
||
SphinxRtdTheme.Navigation.enable(true);
|
||
});
|
||
</script>
|
||
|
||
</body>
|
||
</html> |