gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2025-12-17 19:20:19 +01:00
Code Issues Projects Releases Wiki Activity

Docs changes - fixing blogpost links, removing importing all exploration policies (#139)

Browse Source 
* updated docs

* removing imports for all exploration policies in __init__ + setting the right blog-post link

* small cleanups
This commit is contained in:
Gal Leibovich
2018-12-05 23:16:16 +02:00
committed by Scott Leishman
parent 155b78b995
commit f12857a8c7
33 changed files with 191 additions and 160 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@@ -28,7 +28,7 @@ Blog posts from the Intel® AI website:
* [Release 0.8.0](https://ai.intel.com/reinforcement-learning-coach-intel/) (initial release)
* [Release 0.9.0](https://ai.intel.com/reinforcement-learning-coach-carla-qr-dqn/)
* [Release 0.10.0](https://ai.intel.com/introducing-reinforcement-learning-coach-0-10-0/)
* Release 0.11 (current release)
* [Release 0.11.0](https://ai.intel.com/rl-coach-data-science-at-scale) (current release)
Contacting the Coach development team is also possible through the email [coach@intel.com](coach@intel.com)

2
docs/_modules/rl_coach/agents/agent.html
View File

@@ -195,13 +195,11 @@
<span class="c1">#</span>
<span class="kn">import</span> <span class="nn">copy</span>
<span class="kn">import</span> <span class="nn">os</span>
<span class="kn">import</span> <span class="nn">random</span>
<span class="kn">from</span> <span class="nn">collections</span> <span class="k">import</span> <span class="n">OrderedDict</span>
<span class="kn">from</span> <span class="nn">typing</span> <span class="k">import</span> <span class="n">Dict</span><span class="p">,</span> <span class="n">List</span><span class="p">,</span> <span class="n">Union</span><span class="p">,</span> <span class="n">Tuple</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">pandas</span> <span class="k">import</span> <span class="n">read_pickle</span>
<span class="kn">from</span> <span class="nn">six.moves</span> <span class="k">import</span> <span class="nb">range</span>
<span class="kn">from</span> <span class="nn">rl_coach.agents.agent_interface</span> <span class="k">import</span> <span class="n">AgentInterface</span>

3
docs/_modules/rl_coach/agents/dqn_agent.html
View File

@@ -215,7 +215,8 @@
<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">num_steps_between_copying_online_weights_to_target</span> <span class="o">=</span> <span class="n">EnvironmentSteps</span><span class="p">(</span><span class="mi">10000</span><span class="p">)</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">discount</span> <span class="o">=</span> <span class="mf">0.99</span></div>
<span class="bp">self</span><span class="o">.</span><span class="n">discount</span> <span class="o">=</span> <span class="mf">0.99</span>
<span class="bp">self</span><span class="o">.</span><span class="n">supports_parameter_noise</span> <span class="o">=</span> <span class="kc">True</span></div>
<span class="k">class</span> <span class="nc">DQNNetworkParameters</span><span class="p">(</span><span class="n">NetworkParameters</span><span class="p">):</span>

3
docs/_modules/rl_coach/base_parameters.html
View File

@@ -391,6 +391,9 @@
<span class="c1"># Should the workers wait for full episode</span>
<span class="bp">self</span><span class="o">.</span><span class="n">act_for_full_episodes</span> <span class="o">=</span> <span class="kc">False</span>
<span class="c1"># Support for parameter noise</span>
<span class="bp">self</span><span class="o">.</span><span class="n">supports_parameter_noise</span> <span class="o">=</span> <span class="kc">False</span>
<div class="viewcode-block" id="PresetValidationParameters"><a class="viewcode-back" href="../../components/additional_parameters.html#rl_coach.base_parameters.PresetValidationParameters">[docs]</a><span class="k">class</span> <span class="nc">PresetValidationParameters</span><span class="p">(</span><span class="n">Parameters</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>

19
docs/_modules/rl_coach/data_stores/nfs_data_store.html
View File

@@ -178,7 +178,24 @@
<div itemprop="articleBody">
<h1>Source code for rl_coach.data_stores.nfs_data_store</h1><div class="highlight"><pre>
<span></span><span class="kn">import</span> <span class="nn">uuid</span>
<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 &quot;License&quot;);</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 &quot;AS IS&quot; 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">uuid</span>
<span class="kn">from</span> <span class="nn">rl_coach.data_stores.data_store</span> <span class="k">import</span> <span class="n">DataStore</span><span class="p">,</span> <span class="n">DataStoreParameters</span>

19
docs/_modules/rl_coach/data_stores/s3_data_store.html
View File

@@ -178,7 +178,24 @@
<div itemprop="articleBody">
<h1>Source code for rl_coach.data_stores.s3_data_store</h1><div class="highlight"><pre>
<span></span><span class="kn">from</span> <span class="nn">rl_coach.data_stores.data_store</span> <span class="k">import</span> <span class="n">DataStore</span><span class="p">,</span> <span class="n">DataStoreParameters</span>
<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 &quot;License&quot;);</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 &quot;AS IS&quot; BASIS,</span>
<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
<span class="c1"># See the License for the specific language governing permissions and</span>
<span class="c1"># limitations under the License.</span>
<span class="c1">#</span>
<span class="kn">from</span> <span class="nn">rl_coach.data_stores.data_store</span> <span class="k">import</span> <span class="n">DataStore</span><span class="p">,</span> <span class="n">DataStoreParameters</span>
<span class="kn">from</span> <span class="nn">minio</span> <span class="k">import</span> <span class="n">Minio</span>
<span class="kn">from</span> <span class="nn">minio.error</span> <span class="k">import</span> <span class="n">ResponseError</span>
<span class="kn">from</span> <span class="nn">configparser</span> <span class="k">import</span> <span class="n">ConfigParser</span><span class="p">,</span> <span class="n">Error</span>

2
docs/_modules/rl_coach/exploration_policies/additive_noise.html
View File

@@ -216,7 +216,7 @@
<span class="k">return</span> <span class="s1">&#39;rl_coach.exploration_policies.additive_noise:AdditiveNoise&#39;</span>
<div class="viewcode-block" id="AdditiveNoise"><a class="viewcode-back" href="../../../components/exploration_policies/index.html#rl_coach.exploration_policies.AdditiveNoise">[docs]</a><span class="k">class</span> <span class="nc">AdditiveNoise</span><span class="p">(</span><span class="n">ExplorationPolicy</span><span class="p">):</span>
<div class="viewcode-block" id="AdditiveNoise"><a class="viewcode-back" href="../../../components/exploration_policies/index.html#rl_coach.exploration_policies.additive_noise.AdditiveNoise">[docs]</a><span class="k">class</span> <span class="nc">AdditiveNoise</span><span class="p">(</span><span class="n">ExplorationPolicy</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> AdditiveNoise is an exploration policy intended for continuous action spaces. It takes the action from the agent</span>
<span class="sd"> and adds a Gaussian distributed noise to it. The amount of noise added to the action follows the noise amount that</span>

2
docs/_modules/rl_coach/exploration_policies/boltzmann.html
View File

@@ -215,7 +215,7 @@
<div class="viewcode-block" id="Boltzmann"><a class="viewcode-back" href="../../../components/exploration_policies/index.html#rl_coach.exploration_policies.Boltzmann">[docs]</a><span class="k">class</span> <span class="nc">Boltzmann</span><span class="p">(</span><span class="n">ExplorationPolicy</span><span class="p">):</span>
<div class="viewcode-block" id="Boltzmann"><a class="viewcode-back" href="../../../components/exploration_policies/index.html#rl_coach.exploration_policies.boltzmann.Boltzmann">[docs]</a><span class="k">class</span> <span class="nc">Boltzmann</span><span class="p">(</span><span class="n">ExplorationPolicy</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> The Boltzmann exploration policy is intended for discrete action spaces. It assumes that each of the possible</span>
<span class="sd"> actions has some value assigned to it (such as the Q value), and uses a softmax function to convert these values</span>

2
docs/_modules/rl_coach/exploration_policies/bootstrapped.html
View File

@@ -218,7 +218,7 @@
<span class="k">return</span> <span class="s1">&#39;rl_coach.exploration_policies.bootstrapped:Bootstrapped&#39;</span>
<div class="viewcode-block" id="Bootstrapped"><a class="viewcode-back" href="../../../components/exploration_policies/index.html#rl_coach.exploration_policies.Bootstrapped">[docs]</a><span class="k">class</span> <span class="nc">Bootstrapped</span><span class="p">(</span><span class="n">EGreedy</span><span class="p">):</span>
<div class="viewcode-block" id="Bootstrapped"><a class="viewcode-back" href="../../../components/exploration_policies/index.html#rl_coach.exploration_policies.bootstrapped.Bootstrapped">[docs]</a><span class="k">class</span> <span class="nc">Bootstrapped</span><span class="p">(</span><span class="n">EGreedy</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Bootstrapped exploration policy is currently only used for discrete action spaces along with the</span>
<span class="sd"> Bootstrapped DQN agent. It assumes that there is an ensemble of network heads, where each one predicts the</span>

2
docs/_modules/rl_coach/exploration_policies/categorical.html
View File

@@ -209,7 +209,7 @@
<span class="k">return</span> <span class="s1">&#39;rl_coach.exploration_policies.categorical:Categorical&#39;</span>
<div class="viewcode-block" id="Categorical"><a class="viewcode-back" href="../../../components/exploration_policies/index.html#rl_coach.exploration_policies.Categorical">[docs]</a><span class="k">class</span> <span class="nc">Categorical</span><span class="p">(</span><span class="n">ExplorationPolicy</span><span class="p">):</span>
<div class="viewcode-block" id="Categorical"><a class="viewcode-back" href="../../../components/exploration_policies/index.html#rl_coach.exploration_policies.categorical.Categorical">[docs]</a><span class="k">class</span> <span class="nc">Categorical</span><span class="p">(</span><span class="n">ExplorationPolicy</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Categorical exploration policy is intended for discrete action spaces. It expects the action values to</span>
<span class="sd"> represent a probability distribution over the action, from which a single action will be sampled.</span>

2
docs/_modules/rl_coach/exploration_policies/continuous_entropy.html
View File

@@ -203,7 +203,7 @@
<span class="k">return</span> <span class="s1">&#39;rl_coach.exploration_policies.continuous_entropy:ContinuousEntropy&#39;</span>
<div class="viewcode-block" id="ContinuousEntropy"><a class="viewcode-back" href="../../../components/exploration_policies/index.html#rl_coach.exploration_policies.ContinuousEntropy">[docs]</a><span class="k">class</span> <span class="nc">ContinuousEntropy</span><span class="p">(</span><span class="n">AdditiveNoise</span><span class="p">):</span>
<div class="viewcode-block" id="ContinuousEntropy"><a class="viewcode-back" href="../../../components/exploration_policies/index.html#rl_coach.exploration_policies.continuous_entropy.ContinuousEntropy">[docs]</a><span class="k">class</span> <span class="nc">ContinuousEntropy</span><span class="p">(</span><span class="n">AdditiveNoise</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Continuous entropy is an exploration policy that is actually implemented as part of the network.</span>
<span class="sd"> The exploration policy class is only a placeholder for choosing this policy. The exploration policy is</span>

2
docs/_modules/rl_coach/exploration_policies/e_greedy.html
View File

@@ -222,7 +222,7 @@
<span class="k">return</span> <span class="s1">&#39;rl_coach.exploration_policies.e_greedy:EGreedy&#39;</span>
<div class="viewcode-block" id="EGreedy"><a class="viewcode-back" href="../../../components/exploration_policies/index.html#rl_coach.exploration_policies.EGreedy">[docs]</a><span class="k">class</span> <span class="nc">EGreedy</span><span class="p">(</span><span class="n">ExplorationPolicy</span><span class="p">):</span>
<div class="viewcode-block" id="EGreedy"><a class="viewcode-back" href="../../../components/exploration_policies/index.html#rl_coach.exploration_policies.e_greedy.EGreedy">[docs]</a><span class="k">class</span> <span class="nc">EGreedy</span><span class="p">(</span><span class="n">ExplorationPolicy</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> e-greedy is an exploration policy that is intended for both discrete and continuous action spaces.</span>

10
docs/_modules/rl_coach/exploration_policies/exploration_policy.html
View File

@@ -210,7 +210,7 @@
<span class="k">return</span> <span class="s1">&#39;rl_coach.exploration_policies.exploration_policy:ExplorationPolicy&#39;</span>
<div class="viewcode-block" id="ExplorationPolicy"><a class="viewcode-back" href="../../../components/exploration_policies/index.html#rl_coach.exploration_policies.ExplorationPolicy">[docs]</a><span class="k">class</span> <span class="nc">ExplorationPolicy</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<div class="viewcode-block" id="ExplorationPolicy"><a class="viewcode-back" href="../../../components/exploration_policies/index.html#rl_coach.exploration_policies.exploration_policy.ExplorationPolicy">[docs]</a><span class="k">class</span> <span class="nc">ExplorationPolicy</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> An exploration policy takes the predicted actions or action values from the agent, and selects the action to</span>
<span class="sd"> actually apply to the environment using some predefined algorithm.</span>
@@ -222,14 +222,14 @@
<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="bp">self</span><span class="o">.</span><span class="n">action_space</span> <span class="o">=</span> <span class="n">action_space</span>
<div class="viewcode-block" id="ExplorationPolicy.reset"><a class="viewcode-back" href="../../../components/exploration_policies/index.html#rl_coach.exploration_policies.ExplorationPolicy.reset">[docs]</a> <span class="k">def</span> <span class="nf">reset</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<div class="viewcode-block" id="ExplorationPolicy.reset"><a class="viewcode-back" href="../../../components/exploration_policies/index.html#rl_coach.exploration_policies.exploration_policy.ExplorationPolicy.reset">[docs]</a> <span class="k">def</span> <span class="nf">reset</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Used for resetting the exploration policy parameters when needed</span>
<span class="sd"> :return: None</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">pass</span></div>
<div class="viewcode-block" id="ExplorationPolicy.get_action"><a class="viewcode-back" href="../../../components/exploration_policies/index.html#rl_coach.exploration_policies.ExplorationPolicy.get_action">[docs]</a> <span class="k">def</span> <span class="nf">get_action</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">action_values</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="n">ActionType</span><span class="p">])</span> <span class="o">-&gt;</span> <span class="n">ActionType</span><span class="p">:</span>
<div class="viewcode-block" id="ExplorationPolicy.get_action"><a class="viewcode-back" href="../../../components/exploration_policies/index.html#rl_coach.exploration_policies.exploration_policy.ExplorationPolicy.get_action">[docs]</a> <span class="k">def</span> <span class="nf">get_action</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">action_values</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="n">ActionType</span><span class="p">])</span> <span class="o">-&gt;</span> <span class="n">ActionType</span><span class="p">:</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Given a list of values corresponding to each action, </span>
<span class="sd"> choose one actions according to the exploration policy</span>
@@ -243,7 +243,7 @@
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">&quot;The get_action function should be overridden in the inheriting exploration class&quot;</span><span class="p">)</span></div>
<div class="viewcode-block" id="ExplorationPolicy.change_phase"><a class="viewcode-back" href="../../../components/exploration_policies/index.html#rl_coach.exploration_policies.ExplorationPolicy.change_phase">[docs]</a> <span class="k">def</span> <span class="nf">change_phase</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">phase</span><span class="p">):</span>
<div class="viewcode-block" id="ExplorationPolicy.change_phase"><a class="viewcode-back" href="../../../components/exploration_policies/index.html#rl_coach.exploration_policies.exploration_policy.ExplorationPolicy.change_phase">[docs]</a> <span class="k">def</span> <span class="nf">change_phase</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">phase</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Change between running phases of the algorithm</span>
<span class="sd"> :param phase: Either Heatup or Train</span>
@@ -251,7 +251,7 @@
<span class="sd"> &quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">phase</span> <span class="o">=</span> <span class="n">phase</span></div>
<div class="viewcode-block" id="ExplorationPolicy.requires_action_values"><a class="viewcode-back" href="../../../components/exploration_policies/index.html#rl_coach.exploration_policies.ExplorationPolicy.requires_action_values">[docs]</a> <span class="k">def</span> <span class="nf">requires_action_values</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">bool</span><span class="p">:</span>
<div class="viewcode-block" id="ExplorationPolicy.requires_action_values"><a class="viewcode-back" href="../../../components/exploration_policies/index.html#rl_coach.exploration_policies.exploration_policy.ExplorationPolicy.requires_action_values">[docs]</a> <span class="k">def</span> <span class="nf">requires_action_values</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">bool</span><span class="p">:</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Allows exploration policies to define if they require the action values for the current step.</span>
<span class="sd"> This can save up a lot of computation. For example in e-greedy, if the random value generated is smaller</span>

2
docs/_modules/rl_coach/exploration_policies/greedy.html
View File

@@ -209,7 +209,7 @@
<span class="k">return</span> <span class="s1">&#39;rl_coach.exploration_policies.greedy:Greedy&#39;</span>
<div class="viewcode-block" id="Greedy"><a class="viewcode-back" href="../../../components/exploration_policies/index.html#rl_coach.exploration_policies.Greedy">[docs]</a><span class="k">class</span> <span class="nc">Greedy</span><span class="p">(</span><span class="n">ExplorationPolicy</span><span class="p">):</span>
<div class="viewcode-block" id="Greedy"><a class="viewcode-back" href="../../../components/exploration_policies/index.html#rl_coach.exploration_policies.greedy.Greedy">[docs]</a><span class="k">class</span> <span class="nc">Greedy</span><span class="p">(</span><span class="n">ExplorationPolicy</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> The Greedy exploration policy is intended for both discrete and continuous action spaces.</span>
<span class="sd"> For discrete action spaces, it always selects the action with the maximum value, as given by the agent.</span>

2
docs/_modules/rl_coach/exploration_policies/ou_process.html
View File

@@ -219,7 +219,7 @@
<span class="c1"># Ornstein-Uhlenbeck process</span>
<div class="viewcode-block" id="OUProcess"><a class="viewcode-back" href="../../../components/exploration_policies/index.html#rl_coach.exploration_policies.OUProcess">[docs]</a><span class="k">class</span> <span class="nc">OUProcess</span><span class="p">(</span><span class="n">ExplorationPolicy</span><span class="p">):</span>
<div class="viewcode-block" id="OUProcess"><a class="viewcode-back" href="../../../components/exploration_policies/index.html#rl_coach.exploration_policies.ou_process.OUProcess">[docs]</a><span class="k">class</span> <span class="nc">OUProcess</span><span class="p">(</span><span class="n">ExplorationPolicy</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> OUProcess exploration policy is intended for continuous action spaces, and selects the action according to</span>
<span class="sd"> an Ornstein-Uhlenbeck process. The Ornstein-Uhlenbeck process implements the action as a Gaussian process, where</span>

5
docs/_modules/rl_coach/exploration_policies/parameter_noise.html
View File

@@ -210,7 +210,8 @@
<span class="k">class</span> <span class="nc">ParameterNoiseParameters</span><span class="p">(</span><span class="n">ExplorationParameters</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_params</span><span class="p">:</span> <span class="n">AgentParameters</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="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">agent_params</span><span class="p">,</span> <span class="n">DQNAgentParameters</span><span class="p">):</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">agent_params</span><span class="o">.</span><span class="n">algorithm</span><span class="o">.</span><span class="n">supports_parameter_noise</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">&quot;Currently only DQN variants are supported for using an exploration type of &quot;</span>
<span class="s2">&quot;ParameterNoise.&quot;</span><span class="p">)</span>
@@ -221,7 +222,7 @@
<span class="k">return</span> <span class="s1">&#39;rl_coach.exploration_policies.parameter_noise:ParameterNoise&#39;</span>
<div class="viewcode-block" id="ParameterNoise"><a class="viewcode-back" href="../../../components/exploration_policies/index.html#rl_coach.exploration_policies.ParameterNoise">[docs]</a><span class="k">class</span> <span class="nc">ParameterNoise</span><span class="p">(</span><span class="n">ExplorationPolicy</span><span class="p">):</span>
<div class="viewcode-block" id="ParameterNoise"><a class="viewcode-back" href="../../../components/exploration_policies/index.html#rl_coach.exploration_policies.parameter_noise.ParameterNoise">[docs]</a><span class="k">class</span> <span class="nc">ParameterNoise</span><span class="p">(</span><span class="n">ExplorationPolicy</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> The ParameterNoise exploration policy is intended for both discrete and continuous action spaces.</span>
<span class="sd"> It applies the exploration policy by replacing all the dense network layers with noisy layers.</span>

2
docs/_modules/rl_coach/exploration_policies/truncated_normal.html
View File

@@ -218,7 +218,7 @@
<span class="k">return</span> <span class="s1">&#39;rl_coach.exploration_policies.truncated_normal:TruncatedNormal&#39;</span>
<div class="viewcode-block" id="TruncatedNormal"><a class="viewcode-back" href="../../../components/exploration_policies/index.html#rl_coach.exploration_policies.TruncatedNormal">[docs]</a><span class="k">class</span> <span class="nc">TruncatedNormal</span><span class="p">(</span><span class="n">ExplorationPolicy</span><span class="p">):</span>
<div class="viewcode-block" id="TruncatedNormal"><a class="viewcode-back" href="../../../components/exploration_policies/index.html#rl_coach.exploration_policies.truncated_normal.TruncatedNormal">[docs]</a><span class="k">class</span> <span class="nc">TruncatedNormal</span><span class="p">(</span><span class="n">ExplorationPolicy</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> The TruncatedNormal exploration policy is intended for continuous action spaces. It samples the action from a</span>
<span class="sd"> normal distribution, where the mean action is given by the agent, and the standard deviation can be given in t</span>

2
docs/_modules/rl_coach/exploration_policies/ucb.html
View File

@@ -222,7 +222,7 @@
<span class="k">return</span> <span class="s1">&#39;rl_coach.exploration_policies.ucb:UCB&#39;</span>
<div class="viewcode-block" id="UCB"><a class="viewcode-back" href="../../../components/exploration_policies/index.html#rl_coach.exploration_policies.UCB">[docs]</a><span class="k">class</span> <span class="nc">UCB</span><span class="p">(</span><span class="n">EGreedy</span><span class="p">):</span>
<div class="viewcode-block" id="UCB"><a class="viewcode-back" href="../../../components/exploration_policies/index.html#rl_coach.exploration_policies.ucb.UCB">[docs]</a><span class="k">class</span> <span class="nc">UCB</span><span class="p">(</span><span class="n">EGreedy</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> UCB exploration policy is following the upper confidence bound heuristic to sample actions in discrete action spaces.</span>
<span class="sd"> It assumes that there are multiple network heads that are predicting action values, and that the standard deviation</span>

18
docs/_modules/rl_coach/memories/backend/redis.html
View File

@@ -178,7 +178,23 @@
<div itemprop="articleBody">
<h1>Source code for rl_coach.memories.backend.redis</h1><div class="highlight"><pre>
<span></span>
<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 &quot;License&quot;);</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 &quot;AS IS&quot; 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">redis</span>
<span class="kn">import</span> <span class="nn">pickle</span>
<span class="kn">import</span> <span class="nn">uuid</span>

19
docs/_modules/rl_coach/memories/non_episodic/transition_collection.html
View File

@@ -178,7 +178,24 @@
<div itemprop="articleBody">
<h1>Source code for rl_coach.memories.non_episodic.transition_collection</h1><div class="highlight"><pre>
<span></span><span class="kn">from</span> <span class="nn">rl_coach.core_types</span> <span class="k">import</span> <span class="n">Transition</span>
<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 &quot;License&quot;);</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 &quot;AS IS&quot; BASIS,</span>
<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
<span class="c1"># See the License for the specific language governing permissions and</span>
<span class="c1"># limitations under the License.</span>
<span class="c1">#</span>
<span class="kn">from</span> <span class="nn">rl_coach.core_types</span> <span class="k">import</span> <span class="n">Transition</span>
<div class="viewcode-block" id="TransitionCollection"><a class="viewcode-back" href="../../../../components/memories/index.html#rl_coach.memories.non_episodic.TransitionCollection">[docs]</a><span class="k">class</span> <span class="nc">TransitionCollection</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>

19
docs/_modules/rl_coach/orchestrators/kubernetes_orchestrator.html
View File

@@ -178,7 +178,24 @@
<div itemprop="articleBody">
<h1>Source code for rl_coach.orchestrators.kubernetes_orchestrator</h1><div class="highlight"><pre>
<span></span><span class="kn">import</span> <span class="nn">os</span>
<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 &quot;License&quot;);</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 &quot;AS IS&quot; 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">uuid</span>
<span class="kn">import</span> <span class="nn">json</span>
<span class="kn">import</span> <span class="nn">time</span>

24
docs/_sources/components/exploration_policies/index.rst.txt
View File

@@ -38,50 +38,50 @@ spaces.
ExplorationPolicy
-----------------
.. autoclass:: rl_coach.exploration_policies.ExplorationPolicy
.. autoclass:: rl_coach.exploration_policies.exploration_policy.ExplorationPolicy
:members:
:inherited-members:
AdditiveNoise
-------------
.. autoclass:: rl_coach.exploration_policies.AdditiveNoise
.. autoclass:: rl_coach.exploration_policies.additive_noise.AdditiveNoise
Boltzmann
---------
.. autoclass:: rl_coach.exploration_policies.Boltzmann
.. autoclass:: rl_coach.exploration_policies.boltzmann.Boltzmann
Bootstrapped
------------
.. autoclass:: rl_coach.exploration_policies.Bootstrapped
.. autoclass:: rl_coach.exploration_policies.bootstrapped.Bootstrapped
Categorical
-----------
.. autoclass:: rl_coach.exploration_policies.Categorical
.. autoclass:: rl_coach.exploration_policies.categorical.Categorical
ContinuousEntropy
-----------------
.. autoclass:: rl_coach.exploration_policies.ContinuousEntropy
.. autoclass:: rl_coach.exploration_policies.continuous_entropy.ContinuousEntropy
EGreedy
-------
.. autoclass:: rl_coach.exploration_policies.EGreedy
.. autoclass:: rl_coach.exploration_policies.e_greedy.EGreedy
Greedy
------
.. autoclass:: rl_coach.exploration_policies.Greedy
.. autoclass:: rl_coach.exploration_policies.greedy.Greedy
OUProcess
---------
.. autoclass:: rl_coach.exploration_policies.OUProcess
.. autoclass:: rl_coach.exploration_policies.ou_process.OUProcess
ParameterNoise
--------------
.. autoclass:: rl_coach.exploration_policies.ParameterNoise
.. autoclass:: rl_coach.exploration_policies.parameter_noise.ParameterNoise
TruncatedNormal
---------------
.. autoclass:: rl_coach.exploration_policies.TruncatedNormal
.. autoclass:: rl_coach.exploration_policies.truncated_normal.TruncatedNormal
UCB
---
.. autoclass:: rl_coach.exploration_policies.UCB
.. autoclass:: rl_coach.exploration_policies.ucb.UCB

2
docs/_sources/index.rst.txt
View File

@@ -25,7 +25,7 @@ Blog posts from the Intel® AI website:
* `Release 0.10.0 <https://ai.intel.com/introducing-reinforcement-learning-coach-0-10-0/)>`_
* `Release 0.11.0 <https://ai.intel.com/>`_ (current release)
* `Release 0.11.0 <https://ai.intel.com/rl-coach-data-science-at-scale/>`_ (current release)
You can find more details in the `GitHub repository <https://github.com/NervanaSystems/coach>`_.

64
docs/components/exploration_policies/index.html
View File

@@ -264,8 +264,8 @@ spaces.</p>
<div class="section" id="explorationpolicy">
<h2>ExplorationPolicy<a class="headerlink" href="#explorationpolicy" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt id="rl_coach.exploration_policies.ExplorationPolicy">
<em class="property">class </em><code class="descclassname">rl_coach.exploration_policies.</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.ExplorationPolicy" title="Permalink to this definition"></a></dt>
<dt id="rl_coach.exploration_policies.exploration_policy.ExplorationPolicy">
<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">
@@ -277,16 +277,16 @@ actually apply to the environment using some predefined algorithm.</p>
</tbody>
</table>
<dl class="method">
<dt id="rl_coach.exploration_policies.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.ExplorationPolicy.change_phase" title="Permalink to this definition"></a></dt>
<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>
<dd><p>Change between running phases of the algorithm
:param phase: Either Heatup or Train
:return: none</p>
</dd></dl>
<dl class="method">
<dt id="rl_coach.exploration_policies.ExplorationPolicy.get_action">
<code class="descname">get_action</code><span class="sig-paren">(</span><em>action_values: List[Union[int, float, numpy.ndarray, List]]</em><span class="sig-paren">)</span> &#x2192; Union[int, float, numpy.ndarray, List]<a class="reference internal" href="../../_modules/rl_coach/exploration_policies/exploration_policy.html#ExplorationPolicy.get_action"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.exploration_policies.ExplorationPolicy.get_action" title="Permalink to this definition"></a></dt>
<dt id="rl_coach.exploration_policies.exploration_policy.ExplorationPolicy.get_action">
<code class="descname">get_action</code><span class="sig-paren">(</span><em>action_values: List[Union[int, float, numpy.ndarray, List]]</em><span class="sig-paren">)</span> &#x2192; Union[int, float, numpy.ndarray, List]<a class="reference internal" href="../../_modules/rl_coach/exploration_policies/exploration_policy.html#ExplorationPolicy.get_action"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.exploration_policies.exploration_policy.ExplorationPolicy.get_action" title="Permalink to this definition"></a></dt>
<dd><p>Given a list of values corresponding to each action,
choose one actions according to the exploration policy
:param action_values: A list of action values
@@ -294,8 +294,8 @@ choose one actions according to the exploration policy
</dd></dl>
<dl class="method">
<dt id="rl_coach.exploration_policies.ExplorationPolicy.requires_action_values">
<code class="descname">requires_action_values</code><span class="sig-paren">(</span><span class="sig-paren">)</span> &#x2192; bool<a class="reference internal" href="../../_modules/rl_coach/exploration_policies/exploration_policy.html#ExplorationPolicy.requires_action_values"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.exploration_policies.ExplorationPolicy.requires_action_values" title="Permalink to this definition"></a></dt>
<dt id="rl_coach.exploration_policies.exploration_policy.ExplorationPolicy.requires_action_values">
<code class="descname">requires_action_values</code><span class="sig-paren">(</span><span class="sig-paren">)</span> &#x2192; bool<a class="reference internal" href="../../_modules/rl_coach/exploration_policies/exploration_policy.html#ExplorationPolicy.requires_action_values"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.exploration_policies.exploration_policy.ExplorationPolicy.requires_action_values" title="Permalink to this definition"></a></dt>
<dd><p>Allows exploration policies to define if they require the action values for the current step.
This can save up a lot of computation. For example in e-greedy, if the random value generated is smaller
than epsilon, the action is completely random, and the action values don’t need to be calculated
@@ -303,8 +303,8 @@ than epsilon, the action is completely random, and the action values don’t nee
</dd></dl>
<dl class="method">
<dt id="rl_coach.exploration_policies.ExplorationPolicy.reset">
<code class="descname">reset</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/exploration_policies/exploration_policy.html#ExplorationPolicy.reset"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.exploration_policies.ExplorationPolicy.reset" title="Permalink to this definition"></a></dt>
<dt id="rl_coach.exploration_policies.exploration_policy.ExplorationPolicy.reset">
<code class="descname">reset</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/exploration_policies/exploration_policy.html#ExplorationPolicy.reset"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.exploration_policies.exploration_policy.ExplorationPolicy.reset" title="Permalink to this definition"></a></dt>
<dd><p>Used for resetting the exploration policy parameters when needed
:return: None</p>
</dd></dl>
@@ -315,8 +315,8 @@ than epsilon, the action is completely random, and the action values don’t nee
<div class="section" id="additivenoise">
<h2>AdditiveNoise<a class="headerlink" href="#additivenoise" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt id="rl_coach.exploration_policies.AdditiveNoise">
<em class="property">class </em><code class="descclassname">rl_coach.exploration_policies.</code><code class="descname">AdditiveNoise</code><span class="sig-paren">(</span><em>action_space: rl_coach.spaces.ActionSpace</em>, <em>noise_percentage_schedule: rl_coach.schedules.Schedule</em>, <em>evaluation_noise_percentage: float</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/exploration_policies/additive_noise.html#AdditiveNoise"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.exploration_policies.AdditiveNoise" title="Permalink to this definition"></a></dt>
<dt id="rl_coach.exploration_policies.additive_noise.AdditiveNoise">
<em class="property">class </em><code class="descclassname">rl_coach.exploration_policies.additive_noise.</code><code class="descname">AdditiveNoise</code><span class="sig-paren">(</span><em>action_space: rl_coach.spaces.ActionSpace</em>, <em>noise_percentage_schedule: rl_coach.schedules.Schedule</em>, <em>evaluation_noise_percentage: float</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/exploration_policies/additive_noise.html#AdditiveNoise"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.exploration_policies.additive_noise.AdditiveNoise" title="Permalink to this definition"></a></dt>
<dd><p>AdditiveNoise is an exploration policy intended for continuous action spaces. It takes the action from the agent
and adds a Gaussian distributed noise to it. The amount of noise added to the action follows the noise amount that
can be given in two different ways:
@@ -343,8 +343,8 @@ of the action space</li>
<div class="section" id="boltzmann">
<h2>Boltzmann<a class="headerlink" href="#boltzmann" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt id="rl_coach.exploration_policies.Boltzmann">
<em class="property">class </em><code class="descclassname">rl_coach.exploration_policies.</code><code class="descname">Boltzmann</code><span class="sig-paren">(</span><em>action_space: rl_coach.spaces.ActionSpace</em>, <em>temperature_schedule: rl_coach.schedules.Schedule</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/exploration_policies/boltzmann.html#Boltzmann"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.exploration_policies.Boltzmann" title="Permalink to this definition"></a></dt>
<dt id="rl_coach.exploration_policies.boltzmann.Boltzmann">
<em class="property">class </em><code class="descclassname">rl_coach.exploration_policies.boltzmann.</code><code class="descname">Boltzmann</code><span class="sig-paren">(</span><em>action_space: rl_coach.spaces.ActionSpace</em>, <em>temperature_schedule: rl_coach.schedules.Schedule</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/exploration_policies/boltzmann.html#Boltzmann"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.exploration_policies.boltzmann.Boltzmann" title="Permalink to this definition"></a></dt>
<dd><p>The Boltzmann exploration policy is intended for discrete action spaces. It assumes that each of the possible
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.
@@ -367,8 +367,8 @@ An additional temperature schedule can be given by the user, and will control th
<div class="section" id="bootstrapped">
<h2>Bootstrapped<a class="headerlink" href="#bootstrapped" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt id="rl_coach.exploration_policies.Bootstrapped">
<em class="property">class </em><code class="descclassname">rl_coach.exploration_policies.</code><code class="descname">Bootstrapped</code><span class="sig-paren">(</span><em>action_space: rl_coach.spaces.ActionSpace</em>, <em>epsilon_schedule: rl_coach.schedules.Schedule</em>, <em>evaluation_epsilon: float</em>, <em>architecture_num_q_heads: int</em>, <em>continuous_exploration_policy_parameters: rl_coach.exploration_policies.exploration_policy.ExplorationParameters = &lt;rl_coach.exploration_policies.additive_noise.AdditiveNoiseParameters object&gt;</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/exploration_policies/bootstrapped.html#Bootstrapped"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.exploration_policies.Bootstrapped" title="Permalink to this definition"></a></dt>
<dt id="rl_coach.exploration_policies.bootstrapped.Bootstrapped">
<em class="property">class </em><code class="descclassname">rl_coach.exploration_policies.bootstrapped.</code><code class="descname">Bootstrapped</code><span class="sig-paren">(</span><em>action_space: rl_coach.spaces.ActionSpace</em>, <em>epsilon_schedule: rl_coach.schedules.Schedule</em>, <em>evaluation_epsilon: float</em>, <em>architecture_num_q_heads: int</em>, <em>continuous_exploration_policy_parameters: rl_coach.exploration_policies.exploration_policy.ExplorationParameters = &lt;rl_coach.exploration_policies.additive_noise.AdditiveNoiseParameters object&gt;</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/exploration_policies/bootstrapped.html#Bootstrapped"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.exploration_policies.bootstrapped.Bootstrapped" title="Permalink to this definition"></a></dt>
<dd><p>Bootstrapped exploration policy is currently only used for discrete action spaces along with the
Bootstrapped DQN agent. It assumes that there is an ensemble of network heads, where each one predicts the
values for all the possible actions. For each episode, a single head is selected to lead the agent, according
@@ -401,8 +401,8 @@ if the e-greedy is used for a continuous policy</li>
<div class="section" id="categorical">
<h2>Categorical<a class="headerlink" href="#categorical" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt id="rl_coach.exploration_policies.Categorical">
<em class="property">class </em><code class="descclassname">rl_coach.exploration_policies.</code><code class="descname">Categorical</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/categorical.html#Categorical"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.exploration_policies.Categorical" title="Permalink to this definition"></a></dt>
<dt id="rl_coach.exploration_policies.categorical.Categorical">
<em class="property">class </em><code class="descclassname">rl_coach.exploration_policies.categorical.</code><code class="descname">Categorical</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/categorical.html#Categorical"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.exploration_policies.categorical.Categorical" title="Permalink to this definition"></a></dt>
<dd><p>Categorical exploration policy is intended for discrete action spaces. It expects the action values to
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
@@ -421,8 +421,8 @@ actor-critic schemes, where the actors output is a probability distribution over
<div class="section" id="continuousentropy">
<h2>ContinuousEntropy<a class="headerlink" href="#continuousentropy" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt id="rl_coach.exploration_policies.ContinuousEntropy">
<em class="property">class </em><code class="descclassname">rl_coach.exploration_policies.</code><code class="descname">ContinuousEntropy</code><span class="sig-paren">(</span><em>action_space: rl_coach.spaces.ActionSpace</em>, <em>noise_percentage_schedule: rl_coach.schedules.Schedule</em>, <em>evaluation_noise_percentage: float</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/exploration_policies/continuous_entropy.html#ContinuousEntropy"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.exploration_policies.ContinuousEntropy" title="Permalink to this definition"></a></dt>
<dt id="rl_coach.exploration_policies.continuous_entropy.ContinuousEntropy">
<em class="property">class </em><code class="descclassname">rl_coach.exploration_policies.continuous_entropy.</code><code class="descname">ContinuousEntropy</code><span class="sig-paren">(</span><em>action_space: rl_coach.spaces.ActionSpace</em>, <em>noise_percentage_schedule: rl_coach.schedules.Schedule</em>, <em>evaluation_noise_percentage: float</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/exploration_policies/continuous_entropy.html#ContinuousEntropy"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.exploration_policies.continuous_entropy.ContinuousEntropy" title="Permalink to this definition"></a></dt>
<dd><p>Continuous entropy is an exploration policy that is actually implemented as part of the network.
The exploration policy class is only a placeholder for choosing this policy. The exploration policy is
implemented by adding a regularization factor to the network loss, which regularizes the entropy of the action.
@@ -453,8 +453,8 @@ of the action space</li>
<div class="section" id="egreedy">
<h2>EGreedy<a class="headerlink" href="#egreedy" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt id="rl_coach.exploration_policies.EGreedy">
<em class="property">class </em><code class="descclassname">rl_coach.exploration_policies.</code><code class="descname">EGreedy</code><span class="sig-paren">(</span><em>action_space: rl_coach.spaces.ActionSpace</em>, <em>epsilon_schedule: rl_coach.schedules.Schedule</em>, <em>evaluation_epsilon: float</em>, <em>continuous_exploration_policy_parameters: rl_coach.exploration_policies.exploration_policy.ExplorationParameters = &lt;rl_coach.exploration_policies.additive_noise.AdditiveNoiseParameters object&gt;</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/exploration_policies/e_greedy.html#EGreedy"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.exploration_policies.EGreedy" title="Permalink to this definition"></a></dt>
<dt id="rl_coach.exploration_policies.e_greedy.EGreedy">
<em class="property">class </em><code class="descclassname">rl_coach.exploration_policies.e_greedy.</code><code class="descname">EGreedy</code><span class="sig-paren">(</span><em>action_space: rl_coach.spaces.ActionSpace</em>, <em>epsilon_schedule: rl_coach.schedules.Schedule</em>, <em>evaluation_epsilon: float</em>, <em>continuous_exploration_policy_parameters: rl_coach.exploration_policies.exploration_policy.ExplorationParameters = &lt;rl_coach.exploration_policies.additive_noise.AdditiveNoiseParameters object&gt;</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/exploration_policies/e_greedy.html#EGreedy"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.exploration_policies.e_greedy.EGreedy" title="Permalink to this definition"></a></dt>
<dd><p>e-greedy is an exploration policy that is intended for both discrete and continuous action spaces.</p>
<p>For discrete action spaces, it assumes that each action is assigned a value, and it selects the action with the
highest value with probability 1 - epsilon. Otherwise, it selects a action sampled uniformly out of all the
@@ -485,8 +485,8 @@ if the e-greedy is used for a continuous policy</li>
<div class="section" id="greedy">
<h2>Greedy<a class="headerlink" href="#greedy" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt id="rl_coach.exploration_policies.Greedy">
<em class="property">class </em><code class="descclassname">rl_coach.exploration_policies.</code><code class="descname">Greedy</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/greedy.html#Greedy"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.exploration_policies.Greedy" title="Permalink to this definition"></a></dt>
<dt id="rl_coach.exploration_policies.greedy.Greedy">
<em class="property">class </em><code class="descclassname">rl_coach.exploration_policies.greedy.</code><code class="descname">Greedy</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/greedy.html#Greedy"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.exploration_policies.greedy.Greedy" title="Permalink to this definition"></a></dt>
<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>
@@ -504,8 +504,8 @@ For continuous action spaces, it always return the exact action, as it was given
<div class="section" id="ouprocess">
<h2>OUProcess<a class="headerlink" href="#ouprocess" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt id="rl_coach.exploration_policies.OUProcess">
<em class="property">class </em><code class="descclassname">rl_coach.exploration_policies.</code><code class="descname">OUProcess</code><span class="sig-paren">(</span><em>action_space: rl_coach.spaces.ActionSpace</em>, <em>mu: float = 0</em>, <em>theta: float = 0.15</em>, <em>sigma: float = 0.2</em>, <em>dt: float = 0.01</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/exploration_policies/ou_process.html#OUProcess"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.exploration_policies.OUProcess" title="Permalink to this definition"></a></dt>
<dt id="rl_coach.exploration_policies.ou_process.OUProcess">
<em class="property">class </em><code class="descclassname">rl_coach.exploration_policies.ou_process.</code><code class="descname">OUProcess</code><span class="sig-paren">(</span><em>action_space: rl_coach.spaces.ActionSpace</em>, <em>mu: float = 0</em>, <em>theta: float = 0.15</em>, <em>sigma: float = 0.2</em>, <em>dt: float = 0.01</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/exploration_policies/ou_process.html#OUProcess"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.exploration_policies.ou_process.OUProcess" title="Permalink to this definition"></a></dt>
<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>
@@ -523,8 +523,8 @@ the samples are correlated between consequent time steps.</p>
<div class="section" id="parameternoise">
<h2>ParameterNoise<a class="headerlink" href="#parameternoise" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt id="rl_coach.exploration_policies.ParameterNoise">
<em class="property">class </em><code class="descclassname">rl_coach.exploration_policies.</code><code class="descname">ParameterNoise</code><span class="sig-paren">(</span><em>network_params: Dict[str, rl_coach.base_parameters.NetworkParameters], action_space: rl_coach.spaces.ActionSpace</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/exploration_policies/parameter_noise.html#ParameterNoise"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.exploration_policies.ParameterNoise" title="Permalink to this definition"></a></dt>
<dt id="rl_coach.exploration_policies.parameter_noise.ParameterNoise">
<em class="property">class </em><code class="descclassname">rl_coach.exploration_policies.parameter_noise.</code><code class="descname">ParameterNoise</code><span class="sig-paren">(</span><em>network_params: Dict[str, rl_coach.base_parameters.NetworkParameters], action_space: rl_coach.spaces.ActionSpace</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/exploration_policies/parameter_noise.html#ParameterNoise"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.exploration_policies.parameter_noise.ParameterNoise" title="Permalink to this definition"></a></dt>
<dd><p>The ParameterNoise exploration policy is intended for both discrete and continuous action spaces.
It applies the exploration policy by replacing all the dense network layers with noisy layers.
The noisy layers have both weight means and weight standard deviations, and for each forward pass of the network
@@ -545,8 +545,8 @@ values.</p>
<div class="section" id="truncatednormal">
<h2>TruncatedNormal<a class="headerlink" href="#truncatednormal" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt id="rl_coach.exploration_policies.TruncatedNormal">
<em class="property">class </em><code class="descclassname">rl_coach.exploration_policies.</code><code class="descname">TruncatedNormal</code><span class="sig-paren">(</span><em>action_space: rl_coach.spaces.ActionSpace</em>, <em>noise_percentage_schedule: rl_coach.schedules.Schedule</em>, <em>evaluation_noise_percentage: float</em>, <em>clip_low: float</em>, <em>clip_high: float</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/exploration_policies/truncated_normal.html#TruncatedNormal"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.exploration_policies.TruncatedNormal" title="Permalink to this definition"></a></dt>
<dt id="rl_coach.exploration_policies.truncated_normal.TruncatedNormal">
<em class="property">class </em><code class="descclassname">rl_coach.exploration_policies.truncated_normal.</code><code class="descname">TruncatedNormal</code><span class="sig-paren">(</span><em>action_space: rl_coach.spaces.ActionSpace</em>, <em>noise_percentage_schedule: rl_coach.schedules.Schedule</em>, <em>evaluation_noise_percentage: float</em>, <em>clip_low: float</em>, <em>clip_high: float</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/exploration_policies/truncated_normal.html#TruncatedNormal"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.exploration_policies.truncated_normal.TruncatedNormal" title="Permalink to this definition"></a></dt>
<dd><p>The TruncatedNormal exploration policy is intended for continuous action spaces. It samples the action from a
normal distribution, where the mean action is given by the agent, and the standard deviation can be given in t
wo different ways:
@@ -575,8 +575,8 @@ of the action space</li>
<div class="section" id="ucb">
<h2>UCB<a class="headerlink" href="#ucb" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt id="rl_coach.exploration_policies.UCB">
<em class="property">class </em><code class="descclassname">rl_coach.exploration_policies.</code><code class="descname">UCB</code><span class="sig-paren">(</span><em>action_space: rl_coach.spaces.ActionSpace</em>, <em>epsilon_schedule: rl_coach.schedules.Schedule</em>, <em>evaluation_epsilon: float</em>, <em>architecture_num_q_heads: int</em>, <em>lamb: int</em>, <em>continuous_exploration_policy_parameters: rl_coach.exploration_policies.exploration_policy.ExplorationParameters = &lt;rl_coach.exploration_policies.additive_noise.AdditiveNoiseParameters object&gt;</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/exploration_policies/ucb.html#UCB"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.exploration_policies.UCB" title="Permalink to this definition"></a></dt>
<dt id="rl_coach.exploration_policies.ucb.UCB">
<em class="property">class </em><code class="descclassname">rl_coach.exploration_policies.ucb.</code><code class="descname">UCB</code><span class="sig-paren">(</span><em>action_space: rl_coach.spaces.ActionSpace</em>, <em>epsilon_schedule: rl_coach.schedules.Schedule</em>, <em>evaluation_epsilon: float</em>, <em>architecture_num_q_heads: int</em>, <em>lamb: int</em>, <em>continuous_exploration_policy_parameters: rl_coach.exploration_policies.exploration_policy.ExplorationParameters = &lt;rl_coach.exploration_policies.additive_noise.AdditiveNoiseParameters object&gt;</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/exploration_policies/ucb.html#UCB"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.exploration_policies.ucb.UCB" title="Permalink to this definition"></a></dt>
<dd><p>UCB exploration policy is following the upper confidence bound heuristic to sample actions in discrete action spaces.
It assumes that there are multiple network heads that are predicting action values, and that the standard deviation
between the heads predictions represents the uncertainty of the agent in each of the actions.

32
docs/genindex.html
View File

@@ -226,7 +226,7 @@
</li>
<li><a href="components/agents/policy_optimization/ac.html#rl_coach.agents.actor_critic_agent.ActorCriticAlgorithmParameters">ActorCriticAlgorithmParameters (class in rl_coach.agents.actor_critic_agent)</a>
</li>
<li><a href="components/exploration_policies/index.html#rl_coach.exploration_policies.AdditiveNoise">AdditiveNoise (class in rl_coach.exploration_policies)</a>
<li><a href="components/exploration_policies/index.html#rl_coach.exploration_policies.additive_noise.AdditiveNoise">AdditiveNoise (class in rl_coach.exploration_policies.additive_noise)</a>
</li>
</ul></td>
<td style="width: 33%; vertical-align: top;"><ul>
@@ -262,11 +262,11 @@
</li>
<li><a href="components/agents/imitation/bc.html#rl_coach.agents.bc_agent.BCAlgorithmParameters">BCAlgorithmParameters (class in rl_coach.agents.bc_agent)</a>
</li>
<li><a href="components/exploration_policies/index.html#rl_coach.exploration_policies.Boltzmann">Boltzmann (class in rl_coach.exploration_policies)</a>
<li><a href="components/exploration_policies/index.html#rl_coach.exploration_policies.boltzmann.Boltzmann">Boltzmann (class in rl_coach.exploration_policies.boltzmann)</a>
</li>
</ul></td>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="components/exploration_policies/index.html#rl_coach.exploration_policies.Bootstrapped">Bootstrapped (class in rl_coach.exploration_policies)</a>
<li><a href="components/exploration_policies/index.html#rl_coach.exploration_policies.bootstrapped.Bootstrapped">Bootstrapped (class in rl_coach.exploration_policies.bootstrapped)</a>
</li>
<li><a href="components/spaces.html#rl_coach.spaces.BoxActionSpace">BoxActionSpace (class in rl_coach.spaces)</a>
</li>
@@ -288,11 +288,11 @@
</ul></li>
<li><a href="components/environments/index.html#rl_coach.environments.carla_environment.CarlaEnvironment">CarlaEnvironment (class in rl_coach.environments.carla_environment)</a>
</li>
<li><a href="components/exploration_policies/index.html#rl_coach.exploration_policies.Categorical">Categorical (class in rl_coach.exploration_policies)</a>
<li><a href="components/exploration_policies/index.html#rl_coach.exploration_policies.categorical.Categorical">Categorical (class in rl_coach.exploration_policies.categorical)</a>
</li>
<li><a href="components/agents/value_optimization/categorical_dqn.html#rl_coach.agents.categorical_dqn_agent.CategoricalDQNAlgorithmParameters">CategoricalDQNAlgorithmParameters (class in rl_coach.agents.categorical_dqn_agent)</a>
</li>
<li><a href="components/exploration_policies/index.html#rl_coach.exploration_policies.ExplorationPolicy.change_phase">change_phase() (rl_coach.exploration_policies.ExplorationPolicy method)</a>
<li><a href="components/exploration_policies/index.html#rl_coach.exploration_policies.exploration_policy.ExplorationPolicy.change_phase">change_phase() (rl_coach.exploration_policies.exploration_policy.ExplorationPolicy method)</a>
</li>
<li><a href="components/agents/index.html#rl_coach.agents.agent.Agent.choose_action">choose_action() (rl_coach.agents.agent.Agent method)</a>
@@ -328,7 +328,7 @@
</li>
<li><a href="components/architectures/index.html#rl_coach.architectures.architecture.Architecture.construct">construct() (rl_coach.architectures.architecture.Architecture static method)</a>
</li>
<li><a href="components/exploration_policies/index.html#rl_coach.exploration_policies.ContinuousEntropy">ContinuousEntropy (class in rl_coach.exploration_policies)</a>
<li><a href="components/exploration_policies/index.html#rl_coach.exploration_policies.continuous_entropy.ContinuousEntropy">ContinuousEntropy (class in rl_coach.exploration_policies.continuous_entropy)</a>
</li>
<li><a href="components/environments/index.html#rl_coach.environments.control_suite_environment.ControlSuiteEnvironment">ControlSuiteEnvironment (class in rl_coach.environments.control_suite_environment)</a>
</li>
@@ -368,7 +368,7 @@
<h2 id="E">E</h2>
<table style="width: 100%" class="indextable genindextable"><tr>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="components/exploration_policies/index.html#rl_coach.exploration_policies.EGreedy">EGreedy (class in rl_coach.exploration_policies)</a>
<li><a href="components/exploration_policies/index.html#rl_coach.exploration_policies.e_greedy.EGreedy">EGreedy (class in rl_coach.exploration_policies.e_greedy)</a>
</li>
<li><a href="components/agents/index.html#rl_coach.agents.agent.Agent.emulate_act_on_trainer">emulate_act_on_trainer() (rl_coach.agents.agent.Agent method)</a>
@@ -398,7 +398,7 @@
</li>
<li><a href="components/memories/index.html#rl_coach.memories.non_episodic.ExperienceReplay">ExperienceReplay (class in rl_coach.memories.non_episodic)</a>
</li>
<li><a href="components/exploration_policies/index.html#rl_coach.exploration_policies.ExplorationPolicy">ExplorationPolicy (class in rl_coach.exploration_policies)</a>
<li><a href="components/exploration_policies/index.html#rl_coach.exploration_policies.exploration_policy.ExplorationPolicy">ExplorationPolicy (class in rl_coach.exploration_policies.exploration_policy)</a>
</li>
</ul></td>
</tr></table>
@@ -416,7 +416,7 @@
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="components/core_types.html#rl_coach.core_types.Batch.game_overs">game_overs() (rl_coach.core_types.Batch method)</a>
</li>
<li><a href="components/exploration_policies/index.html#rl_coach.exploration_policies.ExplorationPolicy.get_action">get_action() (rl_coach.exploration_policies.ExplorationPolicy method)</a>
<li><a href="components/exploration_policies/index.html#rl_coach.exploration_policies.exploration_policy.ExplorationPolicy.get_action">get_action() (rl_coach.exploration_policies.exploration_policy.ExplorationPolicy method)</a>
</li>
<li><a href="components/environments/index.html#rl_coach.environments.environment.Environment.get_action_from_user">get_action_from_user() (rl_coach.environments.environment.Environment method)</a>
</li>
@@ -466,7 +466,7 @@
</li>
<li><a href="components/spaces.html#rl_coach.spaces.GoalsSpace.DistanceMetric">GoalsSpace.DistanceMetric (class in rl_coach.spaces)</a>
</li>
<li><a href="components/exploration_policies/index.html#rl_coach.exploration_policies.Greedy">Greedy (class in rl_coach.exploration_policies)</a>
<li><a href="components/exploration_policies/index.html#rl_coach.exploration_policies.greedy.Greedy">Greedy (class in rl_coach.exploration_policies.greedy)</a>
</li>
<li><a href="components/environments/index.html#rl_coach.environments.gym_environment.GymEnvironment">GymEnvironment (class in rl_coach.environments.gym_environment)</a>
</li>
@@ -626,7 +626,7 @@
<li><a href="test.html#rl_coach.agents.dqn_agent.DQNAgent.observe">(rl_coach.agents.dqn_agent.DQNAgent method)</a>
</li>
</ul></li>
<li><a href="components/exploration_policies/index.html#rl_coach.exploration_policies.OUProcess">OUProcess (class in rl_coach.exploration_policies)</a>
<li><a href="components/exploration_policies/index.html#rl_coach.exploration_policies.ou_process.OUProcess">OUProcess (class in rl_coach.exploration_policies.ou_process)</a>
</li>
</ul></td>
</tr></table>
@@ -640,7 +640,7 @@
</li>
<li><a href="components/architectures/index.html#rl_coach.architectures.network_wrapper.NetworkWrapper.parallel_prediction">parallel_prediction() (rl_coach.architectures.network_wrapper.NetworkWrapper method)</a>
</li>
<li><a href="components/exploration_policies/index.html#rl_coach.exploration_policies.ParameterNoise">ParameterNoise (class in rl_coach.exploration_policies)</a>
<li><a href="components/exploration_policies/index.html#rl_coach.exploration_policies.parameter_noise.ParameterNoise">ParameterNoise (class in rl_coach.exploration_policies.parameter_noise)</a>
</li>
<li><a href="components/agents/index.html#rl_coach.agents.agent.Agent.parent">parent (rl_coach.agents.agent.Agent attribute)</a>
@@ -714,9 +714,9 @@
</ul></li>
<li><a href="components/environments/index.html#rl_coach.environments.environment.Environment.render">render() (rl_coach.environments.environment.Environment method)</a>
</li>
<li><a href="components/exploration_policies/index.html#rl_coach.exploration_policies.ExplorationPolicy.requires_action_values">requires_action_values() (rl_coach.exploration_policies.ExplorationPolicy method)</a>
<li><a href="components/exploration_policies/index.html#rl_coach.exploration_policies.exploration_policy.ExplorationPolicy.requires_action_values">requires_action_values() (rl_coach.exploration_policies.exploration_policy.ExplorationPolicy method)</a>
</li>
<li><a href="components/exploration_policies/index.html#rl_coach.exploration_policies.ExplorationPolicy.reset">reset() (rl_coach.exploration_policies.ExplorationPolicy method)</a>
<li><a href="components/exploration_policies/index.html#rl_coach.exploration_policies.exploration_policy.ExplorationPolicy.reset">reset() (rl_coach.exploration_policies.exploration_policy.ExplorationPolicy method)</a>
</li>
<li><a href="components/architectures/index.html#rl_coach.architectures.architecture.Architecture.reset_accumulated_gradients">reset_accumulated_gradients() (rl_coach.architectures.architecture.Architecture method)</a>
</li>
@@ -870,7 +870,7 @@
</li>
<li><a href="components/memories/index.html#rl_coach.memories.non_episodic.TransitionCollection">TransitionCollection (class in rl_coach.memories.non_episodic)</a>
</li>
<li><a href="components/exploration_policies/index.html#rl_coach.exploration_policies.TruncatedNormal">TruncatedNormal (class in rl_coach.exploration_policies)</a>
<li><a href="components/exploration_policies/index.html#rl_coach.exploration_policies.truncated_normal.TruncatedNormal">TruncatedNormal (class in rl_coach.exploration_policies.truncated_normal)</a>
</li>
</ul></td>
</tr></table>
@@ -878,7 +878,7 @@
<h2 id="U">U</h2>
<table style="width: 100%" class="indextable genindextable"><tr>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="components/exploration_policies/index.html#rl_coach.exploration_policies.UCB">UCB (class in rl_coach.exploration_policies)</a>
<li><a href="components/exploration_policies/index.html#rl_coach.exploration_policies.ucb.UCB">UCB (class in rl_coach.exploration_policies.ucb)</a>
</li>
<li><a href="components/core_types.html#rl_coach.core_types.Episode.update_discounted_rewards">update_discounted_rewards() (rl_coach.core_types.Episode method)</a>
</li>

2
docs/index.html
View File

@@ -194,7 +194,7 @@ Coach collects statistics from the training process and supports advanced visual
<li><a class="reference external" href="https://ai.intel.com/reinforcement-learning-coach-intel/">Release 0.8.0</a> (initial release)</li>
<li><a class="reference external" href="https://ai.intel.com/reinforcement-learning-coach-carla-qr-dqn/">Release 0.9.0</a></li>
<li><a class="reference external" href="https://ai.intel.com/introducing-reinforcement-learning-coach-0-10-0/)">Release 0.10.0</a></li>
<li><a class="reference external" href="https://ai.intel.com/">Release 0.11.0</a> (current release)</li>
<li><a class="reference external" href="https://ai.intel.com/rl-coach-data-science-at-scale/">Release 0.11.0</a> (current release)</li>
</ul>
<p>You can find more details in the <a class="reference external" href="https://github.com/NervanaSystems/coach">GitHub repository</a>.</p>
<div class="toctree-wrapper compound">

BIN
docs/objects.inv
View File

Binary file not shown.

2
docs/searchindex.js
View File

File diff suppressed because one or more lines are too long

24
docs_raw/source/components/exploration_policies/index.rst
View File

@@ -38,50 +38,50 @@ spaces.
ExplorationPolicy
-----------------
.. autoclass:: rl_coach.exploration_policies.ExplorationPolicy
.. autoclass:: rl_coach.exploration_policies.exploration_policy.ExplorationPolicy
:members:
:inherited-members:
AdditiveNoise
-------------
.. autoclass:: rl_coach.exploration_policies.AdditiveNoise
.. autoclass:: rl_coach.exploration_policies.additive_noise.AdditiveNoise
Boltzmann
---------
.. autoclass:: rl_coach.exploration_policies.Boltzmann
.. autoclass:: rl_coach.exploration_policies.boltzmann.Boltzmann
Bootstrapped
------------
.. autoclass:: rl_coach.exploration_policies.Bootstrapped
.. autoclass:: rl_coach.exploration_policies.bootstrapped.Bootstrapped
Categorical
-----------
.. autoclass:: rl_coach.exploration_policies.Categorical
.. autoclass:: rl_coach.exploration_policies.categorical.Categorical
ContinuousEntropy
-----------------
.. autoclass:: rl_coach.exploration_policies.ContinuousEntropy
.. autoclass:: rl_coach.exploration_policies.continuous_entropy.ContinuousEntropy
EGreedy
-------
.. autoclass:: rl_coach.exploration_policies.EGreedy
.. autoclass:: rl_coach.exploration_policies.e_greedy.EGreedy
Greedy
------
.. autoclass:: rl_coach.exploration_policies.Greedy
.. autoclass:: rl_coach.exploration_policies.greedy.Greedy
OUProcess
---------
.. autoclass:: rl_coach.exploration_policies.OUProcess
.. autoclass:: rl_coach.exploration_policies.ou_process.OUProcess
ParameterNoise
--------------
.. autoclass:: rl_coach.exploration_policies.ParameterNoise
.. autoclass:: rl_coach.exploration_policies.parameter_noise.ParameterNoise
TruncatedNormal
---------------
.. autoclass:: rl_coach.exploration_policies.TruncatedNormal
.. autoclass:: rl_coach.exploration_policies.truncated_normal.TruncatedNormal
UCB
---
.. autoclass:: rl_coach.exploration_policies.UCB
.. autoclass:: rl_coach.exploration_policies.ucb.UCB

2
docs_raw/source/index.rst
View File

@@ -25,7 +25,7 @@ Blog posts from the Intel® AI website:
* `Release 0.10.0 <https://ai.intel.com/introducing-reinforcement-learning-coach-0-10-0/)>`_
* `Release 0.11.0 <https://ai.intel.com/>`_ (current release)
* `Release 0.11.0 <https://ai.intel.com/rl-coach-data-science-at-scale/>`_ (current release)
You can find more details in the `GitHub repository <https://github.com/NervanaSystems/coach>`_.

2
rl_coach/agents/agent.py
View File

@@ -15,13 +15,11 @@
#
import copy
import os
import random
from collections import OrderedDict
from typing import Dict, List, Union, Tuple
import numpy as np
from pandas import read_pickle
from six.moves import range
from rl_coach.agents.agent_interface import AgentInterface

3
rl_coach/coach.py
View File

@@ -35,7 +35,6 @@ from multiprocessing.managers import BaseManager
import subprocess
from rl_coach.graph_managers.graph_manager import HumanPlayScheduleParameters, GraphManager
from rl_coach.utils import list_all_presets, short_dynamic_import, get_open_port, SharedMemoryScratchPad, get_base_dir
from rl_coach.agents.human_agent import HumanAgentParameters
from rl_coach.graph_managers.basic_rl_graph_manager import BasicRLGraphManager
from rl_coach.environments.environment import SingleLevelSelection
from rl_coach.memories.backend.redis import RedisPubSubMemoryBackendParameters
@@ -229,6 +228,8 @@ class CoachLauncher(object):
# for human play we need to create a custom graph manager
if args.play:
from rl_coach.agents.human_agent import HumanAgentParameters
env_params = short_dynamic_import(args.environment_type, ignore_module_case=True)()
env_params.human_control = True
schedule_params = HumanPlayScheduleParameters()

55
rl_coach/exploration_policies/__init__.py
View File

@@ -1,55 +0,0 @@
#
# Copyright (c) 2017 Intel Corporation
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
from .additive_noise import AdditiveNoiseParameters, AdditiveNoise
from .boltzmann import BoltzmannParameters, Boltzmann
from .bootstrapped import BootstrappedParameters, Bootstrapped
from .categorical import CategoricalParameters, Categorical
from .continuous_entropy import ContinuousEntropyParameters, ContinuousEntropy
from .e_greedy import EGreedyParameters, EGreedy
from .exploration_policy import ExplorationParameters, ExplorationPolicy
from .greedy import GreedyParameters, Greedy
from .ou_process import OUProcessParameters, OUProcess
from .parameter_noise import ParameterNoiseParameters, ParameterNoise
from .truncated_normal import TruncatedNormalParameters, TruncatedNormal
from .ucb import UCBParameters, UCB
__all__ = [
'AdditiveNoiseParameters',
'AdditiveNoise',
'BoltzmannParameters',
'Boltzmann',
'BootstrappedParameters',
'Bootstrapped',
'CategoricalParameters',
'Categorical',
'ContinuousEntropyParameters',
'ContinuousEntropy',
'EGreedyParameters',
'EGreedy',
'ExplorationParameters',
'ExplorationPolicy',
'GreedyParameters',
'Greedy',
'OUProcessParameters',
'OUProcess',
'ParameterNoiseParameters',
'ParameterNoise',
'TruncatedNormalParameters',
'TruncatedNormal',
'UCBParameters',
'UCB'
]