TD3 (#338)

2026-02-12 20:05:45 +01:00 · 2019-06-16 11:11:21 +03:00
parent 8df3c46756
commit 7eb884c5b2
107 changed files with 2200 additions and 495 deletions
--- a/docs/genindex.html
+++ b/docs/genindex.html
@@ -221,7 +221,7 @@
        <li><a href="test.html#rl_coach.agents.dqn_agent.DQNAgent.act">(rl_coach.agents.dqn_agent.DQNAgent method)</a>
 </li>
      </ul></li>
-      <li><a href="components/environments/index.html#rl_coach.environments.environment.Environment.action_space">action_space (rl_coach.environments.environment.Environment attribute)</a>
+      <li><a href="components/environments/index.html#rl_coach.environments.environment.Environment.action_space">action_space() (rl_coach.environments.environment.Environment property)</a>
 </li>
      <li><a href="components/core_types.html#rl_coach.core_types.ActionInfo">ActionInfo (class in rl_coach.core_types)</a>
 </li>
@@ -408,6 +408,14 @@

 <h2 id="F">F</h2>
 <table style="width: 100%" class="indextable genindextable"><tr>
+  <td style="width: 33%; vertical-align: top;"><ul>
+      <li><a href="components/agents/index.html#rl_coach.agents.agent.Agent.freeze_memory">freeze_memory() (rl_coach.agents.agent.Agent method)</a>
+
+      <ul>
+        <li><a href="test.html#rl_coach.agents.dqn_agent.DQNAgent.freeze_memory">(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/filters/output_filters.html#rl_coach.filters.action.FullDiscreteActionSpaceMap">FullDiscreteActionSpaceMap (class in rl_coach.filters.action)</a>
 </li>
@@ -461,7 +469,7 @@
 </li>
      <li><a href="components/spaces.html#rl_coach.spaces.GoalsSpace.goal_from_state">goal_from_state() (rl_coach.spaces.GoalsSpace method)</a>
 </li>
-      <li><a href="components/environments/index.html#rl_coach.environments.environment.Environment.goal_space">goal_space (rl_coach.environments.environment.Environment attribute)</a>
+      <li><a href="components/environments/index.html#rl_coach.environments.environment.Environment.goal_space">goal_space() (rl_coach.environments.environment.Environment property)</a>
 </li>
      <li><a href="components/core_types.html#rl_coach.core_types.Batch.goals">goals() (rl_coach.core_types.Batch method)</a>
 </li>
@@ -505,6 +513,12 @@

      <ul>
        <li><a href="test.html#rl_coach.agents.dqn_agent.DQNAgent.init_environment_dependent_modules">(rl_coach.agents.dqn_agent.DQNAgent method)</a>
+</li>
+      </ul></li>
+      <li><a href="components/agents/index.html#rl_coach.agents.agent.Agent.initialize_session_dependent_components">initialize_session_dependent_components() (rl_coach.agents.agent.Agent method)</a>
+
+      <ul>
+        <li><a href="test.html#rl_coach.agents.dqn_agent.DQNAgent.initialize_session_dependent_components">(rl_coach.agents.dqn_agent.DQNAgent method)</a>
 </li>
      </ul></li>
  </ul></td>
@@ -537,7 +551,7 @@
 <h2 id="L">L</h2>
 <table style="width: 100%" class="indextable genindextable"><tr>
  <td style="width: 33%; vertical-align: top;"><ul>
-      <li><a href="components/environments/index.html#rl_coach.environments.environment.Environment.last_env_response">last_env_response (rl_coach.environments.environment.Environment attribute)</a>
+      <li><a href="components/environments/index.html#rl_coach.environments.environment.Environment.last_env_response">last_env_response() (rl_coach.environments.environment.Environment property)</a>
 </li>
      <li><a href="components/agents/index.html#rl_coach.agents.agent.Agent.learn_from_batch">learn_from_batch() (rl_coach.agents.agent.Agent method)</a>

@@ -545,12 +559,18 @@
        <li><a href="test.html#rl_coach.agents.dqn_agent.DQNAgent.learn_from_batch">(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/core_types.html#rl_coach.core_types.Episode.length">length() (rl_coach.core_types.Episode method)</a>
 </li>
+  </ul></td>
+  <td style="width: 33%; vertical-align: top;"><ul>
      <li><a href="components/filters/output_filters.html#rl_coach.filters.action.LinearBoxToBoxMap">LinearBoxToBoxMap (class in rl_coach.filters.action)</a>
 </li>
+      <li><a href="components/agents/index.html#rl_coach.agents.agent.Agent.load_memory_from_file">load_memory_from_file() (rl_coach.agents.agent.Agent method)</a>
+
+      <ul>
+        <li><a href="test.html#rl_coach.agents.dqn_agent.DQNAgent.load_memory_from_file">(rl_coach.agents.dqn_agent.DQNAgent method)</a>
+</li>
+      </ul></li>
      <li><a href="components/agents/index.html#rl_coach.agents.agent.Agent.log_to_screen">log_to_screen() (rl_coach.agents.agent.Agent method)</a>

      <ul>
@@ -647,20 +667,20 @@
 </li>
      <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>
+      <li><a href="components/agents/index.html#rl_coach.agents.agent.Agent.parent">parent() (rl_coach.agents.agent.Agent property)</a>

      <ul>
-        <li><a href="test.html#rl_coach.agents.dqn_agent.DQNAgent.parent">(rl_coach.agents.dqn_agent.DQNAgent attribute)</a>
+        <li><a href="test.html#rl_coach.agents.dqn_agent.DQNAgent.parent">(rl_coach.agents.dqn_agent.DQNAgent property)</a>
 </li>
      </ul></li>
      <li><a href="components/filters/output_filters.html#rl_coach.filters.action.PartialDiscreteActionSpaceMap">PartialDiscreteActionSpaceMap (class in rl_coach.filters.action)</a>
 </li>
-      <li><a href="components/agents/index.html#rl_coach.agents.agent.Agent.phase">phase (rl_coach.agents.agent.Agent attribute)</a>
+      <li><a href="components/agents/index.html#rl_coach.agents.agent.Agent.phase">phase() (rl_coach.agents.agent.Agent property)</a>

      <ul>
-        <li><a href="test.html#rl_coach.agents.dqn_agent.DQNAgent.phase">(rl_coach.agents.dqn_agent.DQNAgent attribute)</a>
+        <li><a href="test.html#rl_coach.agents.dqn_agent.DQNAgent.phase">(rl_coach.agents.dqn_agent.DQNAgent property)</a>
 </li>
-        <li><a href="components/environments/index.html#rl_coach.environments.environment.Environment.phase">(rl_coach.environments.environment.Environment attribute)</a>
+        <li><a href="components/environments/index.html#rl_coach.environments.environment.Environment.phase">(rl_coach.environments.environment.Environment property)</a>
 </li>
      </ul></li>
  </ul></td>
@@ -835,7 +855,7 @@
 </li>
      <li><a href="components/memories/index.html#rl_coach.memories.episodic.SingleEpisodeBuffer">SingleEpisodeBuffer (class in rl_coach.memories.episodic)</a>
 </li>
-      <li><a href="components/core_types.html#rl_coach.core_types.Batch.size">size (rl_coach.core_types.Batch attribute)</a>
+      <li><a href="components/core_types.html#rl_coach.core_types.Batch.size">size() (rl_coach.core_types.Batch property)</a>
 </li>
      <li><a href="components/core_types.html#rl_coach.core_types.Batch.slice">slice() (rl_coach.core_types.Batch method)</a>
 </li>
@@ -845,7 +865,7 @@
 </li>
      <li><a href="components/environments/index.html#rl_coach.environments.starcraft2_environment.StarCraft2Environment">StarCraft2Environment (class in rl_coach.environments.starcraft2_environment)</a>
 </li>
-      <li><a href="components/environments/index.html#rl_coach.environments.environment.Environment.state_space">state_space (rl_coach.environments.environment.Environment attribute)</a>
+      <li><a href="components/environments/index.html#rl_coach.environments.environment.Environment.state_space">state_space() (rl_coach.environments.environment.Environment property)</a>
 </li>
      <li><a href="components/core_types.html#rl_coach.core_types.Batch.states">states() (rl_coach.core_types.Batch method)</a>
 </li>
@@ -866,6 +886,8 @@
 <table style="width: 100%" class="indextable genindextable"><tr>
  <td style="width: 33%; vertical-align: top;"><ul>
      <li><a href="components/additional_parameters.html#rl_coach.base_parameters.TaskParameters">TaskParameters (class in rl_coach.base_parameters)</a>
+</li>
+      <li><a href="components/agents/policy_optimization/td3.html#rl_coach.agents.td3_agent.TD3AlgorithmParameters">TD3AlgorithmParameters (class in rl_coach.agents.td3_agent)</a>
 </li>
      <li><a href="components/agents/index.html#rl_coach.agents.agent.Agent.train">train() (rl_coach.agents.agent.Agent method)</a>

@@ -873,10 +895,10 @@
        <li><a href="test.html#rl_coach.agents.dqn_agent.DQNAgent.train">(rl_coach.agents.dqn_agent.DQNAgent method)</a>
 </li>
      </ul></li>
-      <li><a href="components/architectures/index.html#rl_coach.architectures.network_wrapper.NetworkWrapper.train_and_sync_networks">train_and_sync_networks() (rl_coach.architectures.network_wrapper.NetworkWrapper method)</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.train_and_sync_networks">train_and_sync_networks() (rl_coach.architectures.network_wrapper.NetworkWrapper method)</a>
+</li>
      <li><a href="components/architectures/index.html#rl_coach.architectures.architecture.Architecture.train_on_batch">train_on_batch() (rl_coach.architectures.architecture.Architecture method)</a>
 </li>
      <li><a href="components/core_types.html#rl_coach.core_types.Transition">Transition (class in rl_coach.core_types)</a>