Add documentation on distributed Coach. (#158)

* Added documentation on distributed Coach.
2025-12-18 11:40:18 +01:00 · 2018-11-27 02:26:15 -08:00
parent e3ecf445e2
commit d06197f663
151 changed files with 5302 additions and 643 deletions
--- a/docs/genindex.html
+++ b/docs/genindex.html
@@ -86,6 +86,7 @@
              <p class="caption"><span class="caption-text">Intro</span></p>
 <ul>
 <li class="toctree-l1"><a class="reference internal" href="usage.html">Usage</a></li>
+<li class="toctree-l1"><a class="reference internal" href="dist_usage.html">Usage - Distributed Coach</a></li>
 <li class="toctree-l1"><a class="reference internal" href="features/index.html">Features</a></li>
 <li class="toctree-l1"><a class="reference internal" href="selecting_an_algorithm.html">Selecting an Algorithm</a></li>
 <li class="toctree-l1"><a class="reference internal" href="dashboard.html">Coach Dashboard</a></li>
@@ -94,6 +95,7 @@
 <ul>
 <li class="toctree-l1"><a class="reference internal" href="design/control_flow.html">Control Flow</a></li>
 <li class="toctree-l1"><a class="reference internal" href="design/network.html">Network Design</a></li>
+<li class="toctree-l1"><a class="reference internal" href="design/horizontal_scaling.html">Distributed Coach - Horizontal Scale-Out</a></li>
 </ul>
 <p class="caption"><span class="caption-text">Contributing</span></p>
 <ul>
@@ -104,10 +106,13 @@
 <ul>
 <li class="toctree-l1"><a class="reference internal" href="components/agents/index.html">Agents</a></li>
 <li class="toctree-l1"><a class="reference internal" href="components/architectures/index.html">Architectures</a></li>
+<li class="toctree-l1"><a class="reference internal" href="components/data_stores/index.html">Data Stores</a></li>
 <li class="toctree-l1"><a class="reference internal" href="components/environments/index.html">Environments</a></li>
 <li class="toctree-l1"><a class="reference internal" href="components/exploration_policies/index.html">Exploration Policies</a></li>
 <li class="toctree-l1"><a class="reference internal" href="components/filters/index.html">Filters</a></li>
 <li class="toctree-l1"><a class="reference internal" href="components/memories/index.html">Memories</a></li>
+<li class="toctree-l1"><a class="reference internal" href="components/memory_backends/index.html">Memory Backends</a></li>
+<li class="toctree-l1"><a class="reference internal" href="components/orchestrators/index.html">Orchestrators</a></li>
 <li class="toctree-l1"><a class="reference internal" href="components/core_types.html">Core Types</a></li>
 <li class="toctree-l1"><a class="reference internal" href="components/spaces.html">Spaces</a></li>
 <li class="toctree-l1"><a class="reference internal" href="components/additional_parameters.html">Additional Parameters</a></li>
@@ -186,6 +191,7 @@
 | <a href="#G"><strong>G</strong></a>
 | <a href="#H"><strong>H</strong></a>
 | <a href="#I"><strong>I</strong></a>
+ | <a href="#K"><strong>K</strong></a>
 | <a href="#L"><strong>L</strong></a>
 | <a href="#M"><strong>M</strong></a>
 | <a href="#N"><strong>N</strong></a>
@@ -294,8 +300,6 @@
        <li><a href="test.html#rl_coach.agents.dqn_agent.DQNAgent.choose_action">(rl_coach.agents.dqn_agent.DQNAgent method)</a>
 </li>
      </ul></li>
-  </ul></td>
-  <td style="width: 33%; vertical-align: top;"><ul>
      <li><a href="components/agents/imitation/cil.html#rl_coach.agents.cil_agent.CILAlgorithmParameters">CILAlgorithmParameters (class in rl_coach.agents.cil_agent)</a>
 </li>
      <li><a href="components/spaces.html#rl_coach.spaces.ActionSpace.clip_action_to_space">clip_action_to_space() (rl_coach.spaces.ActionSpace method)</a>
@@ -304,9 +308,25 @@
        <li><a href="components/spaces.html#rl_coach.spaces.GoalsSpace.clip_action_to_space">(rl_coach.spaces.GoalsSpace method)</a>
 </li>
      </ul></li>
+  </ul></td>
+  <td style="width: 33%; vertical-align: top;"><ul>
      <li><a href="components/agents/policy_optimization/cppo.html#rl_coach.agents.clipped_ppo_agent.ClippedPPOAlgorithmParameters">ClippedPPOAlgorithmParameters (class in rl_coach.agents.clipped_ppo_agent)</a>
 </li>
+      <li><a href="components/environments/index.html#rl_coach.environments.environment.Environment.close">close() (rl_coach.environments.environment.Environment method)</a>
+</li>
+      <li><a href="components/agents/index.html#rl_coach.agents.agent.Agent.collect_savers">collect_savers() (rl_coach.agents.agent.Agent method)</a>
+
+      <ul>
+        <li><a href="test.html#rl_coach.agents.dqn_agent.DQNAgent.collect_savers">(rl_coach.agents.dqn_agent.DQNAgent method)</a>
+</li>
+        <li><a href="components/architectures/index.html#rl_coach.architectures.architecture.Architecture.collect_savers">(rl_coach.architectures.architecture.Architecture method)</a>
+</li>
+        <li><a href="components/architectures/index.html#rl_coach.architectures.network_wrapper.NetworkWrapper.collect_savers">(rl_coach.architectures.network_wrapper.NetworkWrapper method)</a>
+</li>
+      </ul></li>
      <li><a href="components/spaces.html#rl_coach.spaces.CompoundActionSpace">CompoundActionSpace (class in rl_coach.spaces)</a>
+</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>
@@ -350,14 +370,26 @@
  <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>
+      <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>
+
+      <ul>
+        <li><a href="test.html#rl_coach.agents.dqn_agent.DQNAgent.emulate_act_on_trainer">(rl_coach.agents.dqn_agent.DQNAgent method)</a>
+</li>
+      </ul></li>
+      <li><a href="components/agents/index.html#rl_coach.agents.agent.Agent.emulate_observe_on_trainer">emulate_observe_on_trainer() (rl_coach.agents.agent.Agent method)</a>
+
+      <ul>
+        <li><a href="test.html#rl_coach.agents.dqn_agent.DQNAgent.emulate_observe_on_trainer">(rl_coach.agents.dqn_agent.DQNAgent method)</a>
+</li>
+      </ul></li>
      <li><a href="components/environments/index.html#rl_coach.environments.environment.Environment">Environment (class in rl_coach.environments.environment)</a>
 </li>
+  </ul></td>
+  <td style="width: 33%; vertical-align: top;"><ul>
      <li><a href="components/core_types.html#rl_coach.core_types.EnvResponse">EnvResponse (class in rl_coach.core_types)</a>
 </li>
      <li><a href="components/core_types.html#rl_coach.core_types.Episode">Episode (class in rl_coach.core_types)</a>
 </li>
-  </ul></td>
-  <td style="width: 33%; vertical-align: top;"><ul>
      <li><a href="components/memories/index.html#rl_coach.memories.episodic.EpisodicExperienceReplay">EpisodicExperienceReplay (class in rl_coach.memories.episodic)</a>
 </li>
      <li><a href="components/memories/index.html#rl_coach.memories.episodic.EpisodicHindsightExperienceReplay">EpisodicHindsightExperienceReplay (class in rl_coach.memories.episodic)</a>
@@ -391,14 +423,10 @@
      <li><a href="components/environments/index.html#rl_coach.environments.environment.Environment.get_available_keys">get_available_keys() (rl_coach.environments.environment.Environment method)</a>
 </li>
      <li><a href="components/core_types.html#rl_coach.core_types.Episode.get_first_transition">get_first_transition() (rl_coach.core_types.Episode method)</a>
-</li>
-      <li><a href="components/architectures/index.html#rl_coach.architectures.network_wrapper.NetworkWrapper.get_global_variables">get_global_variables() (rl_coach.architectures.network_wrapper.NetworkWrapper method)</a>
 </li>
      <li><a href="components/environments/index.html#rl_coach.environments.environment.Environment.get_goal">get_goal() (rl_coach.environments.environment.Environment method)</a>
 </li>
      <li><a href="components/core_types.html#rl_coach.core_types.Episode.get_last_transition">get_last_transition() (rl_coach.core_types.Episode method)</a>
-</li>
-      <li><a href="components/architectures/index.html#rl_coach.architectures.network_wrapper.NetworkWrapper.get_local_variables">get_local_variables() (rl_coach.architectures.network_wrapper.NetworkWrapper method)</a>
 </li>
      <li><a href="components/agents/index.html#rl_coach.agents.agent.Agent.get_predictions">get_predictions() (rl_coach.agents.agent.Agent method)</a>

@@ -410,10 +438,10 @@
 </li>
      <li><a href="components/environments/index.html#rl_coach.environments.environment.Environment.get_rendered_image">get_rendered_image() (rl_coach.environments.environment.Environment method)</a>
 </li>
-  </ul></td>
-  <td style="width: 33%; vertical-align: top;"><ul>
      <li><a href="components/spaces.html#rl_coach.spaces.GoalsSpace.get_reward_for_goal_and_state">get_reward_for_goal_and_state() (rl_coach.spaces.GoalsSpace method)</a>
 </li>
+  </ul></td>
+  <td style="width: 33%; vertical-align: top;"><ul>
      <li><a href="components/agents/index.html#rl_coach.agents.agent.Agent.get_state_embedding">get_state_embedding() (rl_coach.agents.agent.Agent method)</a>

      <ul>
@@ -493,6 +521,14 @@
  </ul></td>
 </tr></table>

+<h2 id="K">K</h2>
+<table style="width: 100%" class="indextable genindextable"><tr>
+  <td style="width: 33%; vertical-align: top;"><ul>
+      <li><a href="components/orchestrators/index.html#rl_coach.orchestrators.kubernetes_orchestrator.Kubernetes">Kubernetes (class in rl_coach.orchestrators.kubernetes_orchestrator)</a>
+</li>
+  </ul></td>
+</tr></table>
+
 <h2 id="L">L</h2>
 <table style="width: 100%" class="indextable genindextable"><tr>
  <td style="width: 33%; vertical-align: top;"><ul>
@@ -540,13 +576,15 @@
 </li>
      <li><a href="components/agents/value_optimization/nec.html#rl_coach.agents.nec_agent.NECAlgorithmParameters">NECAlgorithmParameters (class in rl_coach.agents.nec_agent)</a>
 </li>
-  </ul></td>
-  <td style="width: 33%; vertical-align: top;"><ul>
      <li><a href="components/architectures/index.html#rl_coach.base_parameters.NetworkParameters">NetworkParameters (class in rl_coach.base_parameters)</a>
 </li>
+  </ul></td>
+  <td style="width: 33%; vertical-align: top;"><ul>
      <li><a href="components/architectures/index.html#rl_coach.architectures.network_wrapper.NetworkWrapper">NetworkWrapper (class in rl_coach.architectures.network_wrapper)</a>
 </li>
      <li><a href="components/core_types.html#rl_coach.core_types.Batch.next_states">next_states() (rl_coach.core_types.Batch method)</a>
+</li>
+      <li><a href="components/data_stores/index.html#rl_coach.data_stores.nfs_data_store.NFSDataStore">NFSDataStore (class in rl_coach.data_stores.nfs_data_store)</a>
 </li>
      <li><a href="components/agents/value_optimization/n_step.html#rl_coach.agents.n_step_q_agent.NStepQAlgorithmParameters">NStepQAlgorithmParameters (class in rl_coach.agents.n_step_q_agent)</a>
 </li>
@@ -665,6 +703,8 @@
 <table style="width: 100%" class="indextable genindextable"><tr>
  <td style="width: 33%; vertical-align: top;"><ul>
      <li><a href="components/agents/value_optimization/rainbow.html#rl_coach.agents.rainbow_dqn_agent.RainbowDQNAlgorithmParameters">RainbowDQNAlgorithmParameters (class in rl_coach.agents.rainbow_dqn_agent)</a>
+</li>
+      <li><a href="components/memory_backends/index.html#rl_coach.memories.backend.redis.RedisPubSubBackend">RedisPubSubBackend (class in rl_coach.memories.backend.redis)</a>
 </li>
      <li><a href="components/agents/index.html#rl_coach.agents.agent.Agent.register_signal">register_signal() (rl_coach.agents.agent.Agent method)</a>

@@ -694,6 +734,12 @@
        <li><a href="test.html#rl_coach.agents.dqn_agent.DQNAgent.reset_internal_state">(rl_coach.agents.dqn_agent.DQNAgent method)</a>
 </li>
        <li><a href="components/environments/index.html#rl_coach.environments.environment.Environment.reset_internal_state">(rl_coach.environments.environment.Environment method)</a>
+</li>
+      </ul></li>
+      <li><a href="components/agents/index.html#rl_coach.agents.agent.Agent.restore_checkpoint">restore_checkpoint() (rl_coach.agents.agent.Agent method)</a>
+
+      <ul>
+        <li><a href="test.html#rl_coach.agents.dqn_agent.DQNAgent.restore_checkpoint">(rl_coach.agents.dqn_agent.DQNAgent method)</a>
 </li>
      </ul></li>
      <li><a href="components/filters/input_filters.html#rl_coach.filters.reward.RewardClippingFilter">RewardClippingFilter (class in rl_coach.filters.reward)</a>
@@ -716,6 +762,8 @@
 <h2 id="S">S</h2>
 <table style="width: 100%" class="indextable genindextable"><tr>
  <td style="width: 33%; vertical-align: top;"><ul>
+      <li><a href="components/data_stores/index.html#rl_coach.data_stores.s3_data_store.S3DataStore">S3DataStore (class in rl_coach.data_stores.s3_data_store)</a>
+</li>
      <li><a href="components/spaces.html#rl_coach.spaces.ActionSpace.sample">sample() (rl_coach.spaces.ActionSpace method)</a>

      <ul>