mirror of
https://github.com/gryf/coach.git
synced 2025-12-18 11:40:18 +01:00
Enabling Coach Documentation to be run even when environments are not installed (#326)
This commit is contained in:
anabwan
@@ -8,7 +8,7 @@
|
||||
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
|
||||
<title>Exploration Policies — Reinforcement Learning Coach 0.11.0 documentation</title>
|
||||
<title>Exploration Policies — Reinforcement Learning Coach 0.12.1 documentation</title>
|
||||
|
||||
|
||||
|
||||
@@ -17,13 +17,21 @@
|
||||
|
||||
|
||||
|
||||
<script type="text/javascript" src="../../_static/js/modernizr.min.js"></script>
|
||||
|
||||
|
||||
<script type="text/javascript" id="documentation_options" data-url_root="../../" src="../../_static/documentation_options.js"></script>
|
||||
<script type="text/javascript" src="../../_static/jquery.js"></script>
|
||||
<script type="text/javascript" src="../../_static/underscore.js"></script>
|
||||
<script type="text/javascript" src="../../_static/doctools.js"></script>
|
||||
<script type="text/javascript" src="../../_static/language_data.js"></script>
|
||||
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
|
||||
|
||||
<script type="text/javascript" src="../../_static/js/theme.js"></script>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../../_static/css/theme.css" type="text/css" />
|
||||
<link rel="stylesheet" href="../../_static/pygments.css" type="text/css" />
|
||||
<link rel="stylesheet" href="../../_static/css/custom.css" type="text/css" />
|
||||
@@ -33,21 +41,16 @@
|
||||
<link rel="prev" title="Environments" href="../environments/index.html" />
|
||||
<link href="../../_static/css/custom.css" rel="stylesheet" type="text/css">
|
||||
|
||||
|
||||
|
||||
<script src="../../_static/js/modernizr.min.js"></script>
|
||||
|
||||
</head>
|
||||
|
||||
<body class="wy-body-for-nav">
|
||||
|
||||
|
||||
<div class="wy-grid-for-nav">
|
||||
|
||||
|
||||
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
|
||||
<div class="wy-side-scroll">
|
||||
<div class="wy-side-nav-search">
|
||||
<div class="wy-side-nav-search" >
|
||||
|
||||
|
||||
|
||||
@@ -202,62 +205,62 @@ predefined policy. This is one of the most important aspects of reinforcement le
|
||||
tuning to get it right. Coach supports several pre-defined exploration policies, and it can be easily extended with
|
||||
custom policies. Note that not all exploration policies are expected to work for both discrete and continuous action
|
||||
spaces.</p>
|
||||
<table border="1" class="docutils">
|
||||
<table class="docutils align-center">
|
||||
<colgroup>
|
||||
<col width="35%" />
|
||||
<col width="37%" />
|
||||
<col width="29%" />
|
||||
<col style="width: 35%" />
|
||||
<col style="width: 37%" />
|
||||
<col style="width: 29%" />
|
||||
</colgroup>
|
||||
<thead valign="bottom">
|
||||
<tr class="row-odd"><th class="head">Exploration Policy</th>
|
||||
<th class="head">Discrete Action Space</th>
|
||||
<th class="head">Box Action Space</th>
|
||||
<thead>
|
||||
<tr class="row-odd"><th class="head"><p>Exploration Policy</p></th>
|
||||
<th class="head"><p>Discrete Action Space</p></th>
|
||||
<th class="head"><p>Box Action Space</p></th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody valign="top">
|
||||
<tr class="row-even"><td>AdditiveNoise</td>
|
||||
<td><span class="red">X</span></td>
|
||||
<td><span class="green">V</span></td>
|
||||
<tbody>
|
||||
<tr class="row-even"><td><p>AdditiveNoise</p></td>
|
||||
<td><p><span class="red">X</span></p></td>
|
||||
<td><p><span class="green">V</span></p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td>Boltzmann</td>
|
||||
<td><span class="green">V</span></td>
|
||||
<td><span class="red">X</span></td>
|
||||
<tr class="row-odd"><td><p>Boltzmann</p></td>
|
||||
<td><p><span class="green">V</span></p></td>
|
||||
<td><p><span class="red">X</span></p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td>Bootstrapped</td>
|
||||
<td><span class="green">V</span></td>
|
||||
<td><span class="red">X</span></td>
|
||||
<tr class="row-even"><td><p>Bootstrapped</p></td>
|
||||
<td><p><span class="green">V</span></p></td>
|
||||
<td><p><span class="red">X</span></p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td>Categorical</td>
|
||||
<td><span class="green">V</span></td>
|
||||
<td><span class="red">X</span></td>
|
||||
<tr class="row-odd"><td><p>Categorical</p></td>
|
||||
<td><p><span class="green">V</span></p></td>
|
||||
<td><p><span class="red">X</span></p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td>ContinuousEntropy</td>
|
||||
<td><span class="red">X</span></td>
|
||||
<td><span class="green">V</span></td>
|
||||
<tr class="row-even"><td><p>ContinuousEntropy</p></td>
|
||||
<td><p><span class="red">X</span></p></td>
|
||||
<td><p><span class="green">V</span></p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td>EGreedy</td>
|
||||
<td><span class="green">V</span></td>
|
||||
<td><span class="green">V</span></td>
|
||||
<tr class="row-odd"><td><p>EGreedy</p></td>
|
||||
<td><p><span class="green">V</span></p></td>
|
||||
<td><p><span class="green">V</span></p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td>Greedy</td>
|
||||
<td><span class="green">V</span></td>
|
||||
<td><span class="green">V</span></td>
|
||||
<tr class="row-even"><td><p>Greedy</p></td>
|
||||
<td><p><span class="green">V</span></p></td>
|
||||
<td><p><span class="green">V</span></p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td>OUProcess</td>
|
||||
<td><span class="red">X</span></td>
|
||||
<td><span class="green">V</span></td>
|
||||
<tr class="row-odd"><td><p>OUProcess</p></td>
|
||||
<td><p><span class="red">X</span></p></td>
|
||||
<td><p><span class="green">V</span></p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td>ParameterNoise</td>
|
||||
<td><span class="green">V</span></td>
|
||||
<td><span class="green">V</span></td>
|
||||
<tr class="row-even"><td><p>ParameterNoise</p></td>
|
||||
<td><p><span class="green">V</span></p></td>
|
||||
<td><p><span class="green">V</span></p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td>TruncatedNormal</td>
|
||||
<td><span class="red">X</span></td>
|
||||
<td><span class="green">V</span></td>
|
||||
<tr class="row-odd"><td><p>TruncatedNormal</p></td>
|
||||
<td><p><span class="red">X</span></p></td>
|
||||
<td><p><span class="green">V</span></p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td>UCB</td>
|
||||
<td><span class="green">V</span></td>
|
||||
<td><span class="red">X</span></td>
|
||||
<tr class="row-even"><td><p>UCB</p></td>
|
||||
<td><p><span class="green">V</span></p></td>
|
||||
<td><p><span class="red">X</span></p></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
@@ -268,14 +271,11 @@ spaces.</p>
|
||||
<em class="property">class </em><code class="descclassname">rl_coach.exploration_policies.exploration_policy.</code><code class="descname">ExplorationPolicy</code><span class="sig-paren">(</span><em>action_space: rl_coach.spaces.ActionSpace</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/exploration_policies/exploration_policy.html#ExplorationPolicy"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.exploration_policies.exploration_policy.ExplorationPolicy" title="Permalink to this definition">¶</a></dt>
|
||||
<dd><p>An exploration policy takes the predicted actions or action values from the agent, and selects the action to
|
||||
actually apply to the environment using some predefined algorithm.</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_space</strong> – the action space used by the environment</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters</dt>
|
||||
<dd class="field-odd"><p><strong>action_space</strong> – the action space used by the environment</p>
|
||||
</dd>
|
||||
</dl>
|
||||
<dl class="method">
|
||||
<dt id="rl_coach.exploration_policies.exploration_policy.ExplorationPolicy.change_phase">
|
||||
<code class="descname">change_phase</code><span class="sig-paren">(</span><em>phase</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/exploration_policies/exploration_policy.html#ExplorationPolicy.change_phase"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.exploration_policies.exploration_policy.ExplorationPolicy.change_phase" title="Permalink to this definition">¶</a></dt>
|
||||
@@ -323,20 +323,16 @@ can be given in two different ways:
|
||||
1. Specified by the user as a noise schedule which is taken in percentiles out of the action space size
|
||||
2. Specified by the agents action. In case the agents action is a list with 2 values, the 1st one is assumed to
|
||||
be the mean of the action, and 2nd is assumed to be its standard deviation.</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 last simple">
|
||||
<li><strong>action_space</strong> – the action space used by the environment</li>
|
||||
<li><strong>noise_percentage_schedule</strong> – the schedule for the noise variance percentage relative to the absolute range
|
||||
of the action space</li>
|
||||
<li><strong>evaluation_noise_percentage</strong> – the noise variance percentage that will be used during evaluation phases</li>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters</dt>
|
||||
<dd class="field-odd"><ul class="simple">
|
||||
<li><p><strong>action_space</strong> – the action space used by the environment</p></li>
|
||||
<li><p><strong>noise_percentage_schedule</strong> – the schedule for the noise variance percentage relative to the absolute range
|
||||
of the action space</p></li>
|
||||
<li><p><strong>evaluation_noise_percentage</strong> – the noise variance percentage that will be used during evaluation phases</p></li>
|
||||
</ul>
|
||||
</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
</div>
|
||||
@@ -349,18 +345,14 @@ of the action space</li>
|
||||
actions has some value assigned to it (such as the Q value), and uses a softmax function to convert these values
|
||||
into a distribution over the actions. It then samples the action for playing out of the calculated distribution.
|
||||
An additional temperature schedule can be given by the user, and will control the steepness of the softmax function.</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 last simple">
|
||||
<li><strong>action_space</strong> – the action space used by the environment</li>
|
||||
<li><strong>temperature_schedule</strong> – the schedule for the temperature parameter of the softmax</li>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters</dt>
|
||||
<dd class="field-odd"><ul class="simple">
|
||||
<li><p><strong>action_space</strong> – the action space used by the environment</p></li>
|
||||
<li><p><strong>temperature_schedule</strong> – the schedule for the temperature parameter of the softmax</p></li>
|
||||
</ul>
|
||||
</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
</div>
|
||||
@@ -375,26 +367,22 @@ values for all the possible actions. For each episode, a single head is selected
|
||||
to its value predictions. In evaluation, the action is selected using a majority vote over all the heads
|
||||
predictions.</p>
|
||||
<div class="admonition note">
|
||||
<p class="first admonition-title">Note</p>
|
||||
<p class="last">This exploration policy will only work for Discrete action spaces with Bootstrapped DQN style agents,
|
||||
<p class="admonition-title">Note</p>
|
||||
<p>This exploration policy will only work for Discrete action spaces with Bootstrapped DQN style agents,
|
||||
since it requires the agent to have a network with multiple heads.</p>
|
||||
</div>
|
||||
<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>action_space</strong> – the action space used by the environment</li>
|
||||
<li><strong>epsilon_schedule</strong> – a schedule for the epsilon values</li>
|
||||
<li><strong>evaluation_epsilon</strong> – the epsilon value to use for evaluation phases</li>
|
||||
<li><strong>continuous_exploration_policy_parameters</strong> – the parameters of the continuous exploration policy to use
|
||||
if the e-greedy is used for a continuous policy</li>
|
||||
<li><strong>architecture_num_q_heads</strong> – the number of q heads to select from</li>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters</dt>
|
||||
<dd class="field-odd"><ul class="simple">
|
||||
<li><p><strong>action_space</strong> – the action space used by the environment</p></li>
|
||||
<li><p><strong>epsilon_schedule</strong> – a schedule for the epsilon values</p></li>
|
||||
<li><p><strong>evaluation_epsilon</strong> – the epsilon value to use for evaluation phases</p></li>
|
||||
<li><p><strong>continuous_exploration_policy_parameters</strong> – the parameters of the continuous exploration policy to use
|
||||
if the e-greedy is used for a continuous policy</p></li>
|
||||
<li><p><strong>architecture_num_q_heads</strong> – the number of q heads to select from</p></li>
|
||||
</ul>
|
||||
</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
</div>
|
||||
@@ -407,14 +395,11 @@ if the e-greedy is used for a continuous policy</li>
|
||||
represent a probability distribution over the action, from which a single action will be sampled.
|
||||
In evaluation, the action that has the highest probability will be selected. This is particularly useful for
|
||||
actor-critic schemes, where the actors output is a probability distribution over the actions.</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_space</strong> – the action space used by the environment</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters</dt>
|
||||
<dd class="field-odd"><p><strong>action_space</strong> – the action space used by the environment</p>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
</div>
|
||||
@@ -429,24 +414,20 @@ implemented by adding a regularization factor to the network loss, which regular
|
||||
This exploration policy is only intended for continuous action spaces, and assumes that the entire calculation
|
||||
is implemented as part of the head.</p>
|
||||
<div class="admonition warning">
|
||||
<p class="first admonition-title">Warning</p>
|
||||
<p class="last">This exploration policy expects the agent or the network to implement the exploration functionality.
|
||||
<p class="admonition-title">Warning</p>
|
||||
<p>This exploration policy expects the agent or the network to implement the exploration functionality.
|
||||
There are only a few heads that actually are relevant and implement the entropy regularization factor.</p>
|
||||
</div>
|
||||
<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>action_space</strong> – the action space used by the environment</li>
|
||||
<li><strong>noise_percentage_schedule</strong> – the schedule for the noise variance percentage relative to the absolute range
|
||||
of the action space</li>
|
||||
<li><strong>evaluation_noise_percentage</strong> – the noise variance percentage that will be used during evaluation phases</li>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters</dt>
|
||||
<dd class="field-odd"><ul class="simple">
|
||||
<li><p><strong>action_space</strong> – the action space used by the environment</p></li>
|
||||
<li><p><strong>noise_percentage_schedule</strong> – the schedule for the noise variance percentage relative to the absolute range
|
||||
of the action space</p></li>
|
||||
<li><p><strong>evaluation_noise_percentage</strong> – the noise variance percentage that will be used during evaluation phases</p></li>
|
||||
</ul>
|
||||
</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
</div>
|
||||
@@ -464,21 +445,17 @@ In evaluation, a different epsilon value can be specified.</p>
|
||||
it samples a random action out of the action space bounds. Otherwise, it selects the action according to a
|
||||
given continuous exploration policy, which is set to AdditiveNoise by default. In evaluation, the action is
|
||||
always selected according to the given continuous exploration policy (where its phase is set to evaluation as well).</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 last simple">
|
||||
<li><strong>action_space</strong> – the action space used by the environment</li>
|
||||
<li><strong>epsilon_schedule</strong> – a schedule for the epsilon values</li>
|
||||
<li><strong>evaluation_epsilon</strong> – the epsilon value to use for evaluation phases</li>
|
||||
<li><strong>continuous_exploration_policy_parameters</strong> – the parameters of the continuous exploration policy to use
|
||||
if the e-greedy is used for a continuous policy</li>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters</dt>
|
||||
<dd class="field-odd"><ul class="simple">
|
||||
<li><p><strong>action_space</strong> – the action space used by the environment</p></li>
|
||||
<li><p><strong>epsilon_schedule</strong> – a schedule for the epsilon values</p></li>
|
||||
<li><p><strong>evaluation_epsilon</strong> – the epsilon value to use for evaluation phases</p></li>
|
||||
<li><p><strong>continuous_exploration_policy_parameters</strong> – the parameters of the continuous exploration policy to use
|
||||
if the e-greedy is used for a continuous policy</p></li>
|
||||
</ul>
|
||||
</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
</div>
|
||||
@@ -490,14 +467,11 @@ if the e-greedy is used for a continuous policy</li>
|
||||
<dd><p>The Greedy exploration policy is intended for both discrete and continuous action spaces.
|
||||
For discrete action spaces, it always selects the action with the maximum value, as given by the agent.
|
||||
For continuous action spaces, it always return the exact action, as it was given by 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">Parameters:</th><td class="field-body"><strong>action_space</strong> – the action space used by the environment</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters</dt>
|
||||
<dd class="field-odd"><p><strong>action_space</strong> – the action space used by the environment</p>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
</div>
|
||||
@@ -509,14 +483,11 @@ For continuous action spaces, it always return the exact action, as it was given
|
||||
<dd><p>OUProcess exploration policy is intended for continuous action spaces, and selects the action according to
|
||||
an Ornstein-Uhlenbeck process. The Ornstein-Uhlenbeck process implements the action as a Gaussian process, where
|
||||
the samples are correlated between consequent time steps.</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_space</strong> – the action space used by the environment</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters</dt>
|
||||
<dd class="field-odd"><p><strong>action_space</strong> – the action space used by the environment</p>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
</div>
|
||||
@@ -531,14 +502,11 @@ The noisy layers have both weight means and weight standard deviations, and for
|
||||
the weights are sampled from a normal distribution that follows the learned weights mean and standard deviation
|
||||
values.</p>
|
||||
<p>Warning: currently supported only by DQN variants</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_space</strong> – the action space used by the environment</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters</dt>
|
||||
<dd class="field-odd"><p><strong>action_space</strong> – the action space used by the environment</p>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
</div>
|
||||
@@ -555,20 +523,16 @@ wo different ways:
|
||||
be the mean of the action, and 2nd is assumed to be its standard deviation.
|
||||
When the sampled action is outside of the action bounds given by the user, it is sampled again and again, until it
|
||||
is within the bounds.</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 last simple">
|
||||
<li><strong>action_space</strong> – the action space used by the environment</li>
|
||||
<li><strong>noise_percentage_schedule</strong> – the schedule for the noise variance percentage relative to the absolute range
|
||||
of the action space</li>
|
||||
<li><strong>evaluation_noise_percentage</strong> – the noise variance percentage that will be used during evaluation phases</li>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters</dt>
|
||||
<dd class="field-odd"><ul class="simple">
|
||||
<li><p><strong>action_space</strong> – the action space used by the environment</p></li>
|
||||
<li><p><strong>noise_percentage_schedule</strong> – the schedule for the noise variance percentage relative to the absolute range
|
||||
of the action space</p></li>
|
||||
<li><p><strong>evaluation_noise_percentage</strong> – the noise variance percentage that will be used during evaluation phases</p></li>
|
||||
</ul>
|
||||
</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
</div>
|
||||
@@ -584,23 +548,19 @@ It then updates the action value estimates to by mean(actions)+lambda*stdev(acti
|
||||
given by the user. This exploration policy aims to take advantage of the uncertainty of the agent in its predictions,
|
||||
and select the action according to the tradeoff between how uncertain the agent is, and how large it predicts
|
||||
the outcome from those actions to be.</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 last simple">
|
||||
<li><strong>action_space</strong> – the action space used by the environment</li>
|
||||
<li><strong>epsilon_schedule</strong> – a schedule for the epsilon values</li>
|
||||
<li><strong>evaluation_epsilon</strong> – the epsilon value to use for evaluation phases</li>
|
||||
<li><strong>architecture_num_q_heads</strong> – the number of q heads to select from</li>
|
||||
<li><strong>lamb</strong> – lambda coefficient for taking the standard deviation into account</li>
|
||||
<li><strong>continuous_exploration_policy_parameters</strong> – the parameters of the continuous exploration policy to use
|
||||
if the e-greedy is used for a continuous policy</li>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">Parameters</dt>
|
||||
<dd class="field-odd"><ul class="simple">
|
||||
<li><p><strong>action_space</strong> – the action space used by the environment</p></li>
|
||||
<li><p><strong>epsilon_schedule</strong> – a schedule for the epsilon values</p></li>
|
||||
<li><p><strong>evaluation_epsilon</strong> – the epsilon value to use for evaluation phases</p></li>
|
||||
<li><p><strong>architecture_num_q_heads</strong> – the number of q heads to select from</p></li>
|
||||
<li><p><strong>lamb</strong> – lambda coefficient for taking the standard deviation into account</p></li>
|
||||
<li><p><strong>continuous_exploration_policy_parameters</strong> – the parameters of the continuous exploration policy to use
|
||||
if the e-greedy is used for a continuous policy</p></li>
|
||||
</ul>
|
||||
</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
</div>
|
||||
@@ -617,7 +577,7 @@ if the e-greedy is used for a continuous policy</li>
|
||||
<a href="../filters/index.html" class="btn btn-neutral float-right" title="Filters" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a>
|
||||
|
||||
|
||||
<a href="../environments/index.html" class="btn btn-neutral" title="Environments" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left"></span> Previous</a>
|
||||
<a href="../environments/index.html" class="btn btn-neutral float-left" title="Environments" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left"></span> Previous</a>
|
||||
|
||||
</div>
|
||||
|
||||
@@ -626,7 +586,7 @@ if the e-greedy is used for a continuous policy</li>
|
||||
|
||||
<div role="contentinfo">
|
||||
<p>
|
||||
© Copyright 2018, Intel AI Lab
|
||||
© Copyright 2018-2019, Intel AI Lab
|
||||
|
||||
</p>
|
||||
</div>
|
||||
@@ -643,27 +603,16 @@ if the e-greedy is used for a continuous policy</li>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<script type="text/javascript" id="documentation_options" data-url_root="../../" src="../../_static/documentation_options.js"></script>
|
||||
<script type="text/javascript" src="../../_static/jquery.js"></script>
|
||||
<script type="text/javascript" src="../../_static/underscore.js"></script>
|
||||
<script type="text/javascript" src="../../_static/doctools.js"></script>
|
||||
<script type="text/javascript" src="../../_static/language_data.js"></script>
|
||||
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
|
||||
|
||||
|
||||
|
||||
|
||||
<script type="text/javascript" src="../../_static/js/theme.js"></script>
|
||||
|
||||
<script type="text/javascript">
|
||||
jQuery(function () {
|
||||
SphinxRtdTheme.Navigation.enable(true);
|
||||
});
|
||||
</script>
|
||||
</script>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
Reference in New Issue
Block a user