mirror of
https://github.com/gryf/coach.git
synced 2025-12-17 19:20:19 +01:00
SAC algorithm (#282)
* SAC algorithm * SAC - updates to agent (learn_from_batch), sac_head and sac_q_head to fix problem in gradient calculation. Now SAC agents is able to train. gym_environment - fixing an error in access to gym.spaces * Soft Actor Critic - code cleanup * code cleanup * V-head initialization fix * SAC benchmarks * SAC Documentation * typo fix * documentation fixes * documentation and version update * README typo
This commit is contained in:
guyk1971
@@ -276,19 +276,22 @@ of the trace tests suite.</li>
|
||||
<h2>TaskParameters<a class="headerlink" href="#taskparameters" title="Permalink to this headline">¶</a></h2>
|
||||
<dl class="class">
|
||||
<dt id="rl_coach.base_parameters.TaskParameters">
|
||||
<em class="property">class </em><code class="descclassname">rl_coach.base_parameters.</code><code class="descname">TaskParameters</code><span class="sig-paren">(</span><em>framework_type: rl_coach.base_parameters.Frameworks = <Frameworks.tensorflow: 'TensorFlow'></em>, <em>evaluate_only: bool = False</em>, <em>use_cpu: bool = False</em>, <em>experiment_path='/tmp'</em>, <em>seed=None</em>, <em>checkpoint_save_secs=None</em>, <em>checkpoint_restore_dir=None</em>, <em>checkpoint_save_dir=None</em>, <em>export_onnx_graph: bool = False</em>, <em>apply_stop_condition: bool = False</em>, <em>num_gpu: int = 1</em><span class="sig-paren">)</span><a class="reference internal" href="../_modules/rl_coach/base_parameters.html#TaskParameters"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.base_parameters.TaskParameters" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property">class </em><code class="descclassname">rl_coach.base_parameters.</code><code class="descname">TaskParameters</code><span class="sig-paren">(</span><em>framework_type: rl_coach.base_parameters.Frameworks = <Frameworks.tensorflow: 'TensorFlow'></em>, <em>evaluate_only: int = None</em>, <em>use_cpu: bool = False</em>, <em>experiment_path='/tmp'</em>, <em>seed=None</em>, <em>checkpoint_save_secs=None</em>, <em>checkpoint_restore_dir=None</em>, <em>checkpoint_restore_path=None</em>, <em>checkpoint_save_dir=None</em>, <em>export_onnx_graph: bool = False</em>, <em>apply_stop_condition: bool = False</em>, <em>num_gpu: int = 1</em><span class="sig-paren">)</span><a class="reference internal" href="../_modules/rl_coach/base_parameters.html#TaskParameters"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.base_parameters.TaskParameters" title="Permalink to this definition">¶</a></dt>
|
||||
<dd><table class="docutils field-list" frame="void" rules="none">
|
||||
<col class="field-name" />
|
||||
<col class="field-body" />
|
||||
<tbody valign="top">
|
||||
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple">
|
||||
<li><strong>framework_type</strong> – deep learning framework type. currently only tensorflow is supported</li>
|
||||
<li><strong>evaluate_only</strong> – the task will be used only for evaluating the model</li>
|
||||
<li><strong>evaluate_only</strong> – if not None, the task will be used only for evaluating the model for the given number of steps.
|
||||
A value of 0 means that task will be evaluated for an infinite number of steps.</li>
|
||||
<li><strong>use_cpu</strong> – use the cpu for this task</li>
|
||||
<li><strong>experiment_path</strong> – the path to the directory which will store all the experiment outputs</li>
|
||||
<li><strong>seed</strong> – a seed to use for the random numbers generator</li>
|
||||
<li><strong>checkpoint_save_secs</strong> – the number of seconds between each checkpoint saving</li>
|
||||
<li><strong>checkpoint_restore_dir</strong> – the directory to restore the checkpoints from</li>
|
||||
<li><strong>checkpoint_restore_dir</strong> – [DEPECRATED - will be removed in one of the next releases - switch to checkpoint_restore_path]
|
||||
the dir to restore the checkpoints from</li>
|
||||
<li><strong>checkpoint_restore_path</strong> – the path to restore the checkpoints from</li>
|
||||
<li><strong>checkpoint_save_dir</strong> – the directory to store the checkpoints in</li>
|
||||
<li><strong>export_onnx_graph</strong> – If set to True, this will export an onnx graph each time a checkpoint is saved</li>
|
||||
<li><strong>apply_stop_condition</strong> – If set to True, this will apply the stop condition defined by reaching a target success rate</li>
|
||||
@@ -305,14 +308,15 @@ of the trace tests suite.</li>
|
||||
<h2>DistributedTaskParameters<a class="headerlink" href="#distributedtaskparameters" title="Permalink to this headline">¶</a></h2>
|
||||
<dl class="class">
|
||||
<dt id="rl_coach.base_parameters.DistributedTaskParameters">
|
||||
<em class="property">class </em><code class="descclassname">rl_coach.base_parameters.</code><code class="descname">DistributedTaskParameters</code><span class="sig-paren">(</span><em>framework_type: rl_coach.base_parameters.Frameworks</em>, <em>parameters_server_hosts: str</em>, <em>worker_hosts: str</em>, <em>job_type: str</em>, <em>task_index: int</em>, <em>evaluate_only: bool = False</em>, <em>num_tasks: int = None</em>, <em>num_training_tasks: int = None</em>, <em>use_cpu: bool = False</em>, <em>experiment_path=None</em>, <em>dnd=None</em>, <em>shared_memory_scratchpad=None</em>, <em>seed=None</em>, <em>checkpoint_save_secs=None</em>, <em>checkpoint_restore_dir=None</em>, <em>checkpoint_save_dir=None</em>, <em>export_onnx_graph: bool = False</em>, <em>apply_stop_condition: bool = False</em><span class="sig-paren">)</span><a class="reference internal" href="../_modules/rl_coach/base_parameters.html#DistributedTaskParameters"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.base_parameters.DistributedTaskParameters" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property">class </em><code class="descclassname">rl_coach.base_parameters.</code><code class="descname">DistributedTaskParameters</code><span class="sig-paren">(</span><em>framework_type: rl_coach.base_parameters.Frameworks</em>, <em>parameters_server_hosts: str</em>, <em>worker_hosts: str</em>, <em>job_type: str</em>, <em>task_index: int</em>, <em>evaluate_only: int = None</em>, <em>num_tasks: int = None</em>, <em>num_training_tasks: int = None</em>, <em>use_cpu: bool = False</em>, <em>experiment_path=None</em>, <em>dnd=None</em>, <em>shared_memory_scratchpad=None</em>, <em>seed=None</em>, <em>checkpoint_save_secs=None</em>, <em>checkpoint_restore_path=None</em>, <em>checkpoint_save_dir=None</em>, <em>export_onnx_graph: bool = False</em>, <em>apply_stop_condition: bool = False</em><span class="sig-paren">)</span><a class="reference internal" href="../_modules/rl_coach/base_parameters.html#DistributedTaskParameters"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.base_parameters.DistributedTaskParameters" title="Permalink to this definition">¶</a></dt>
|
||||
<dd><table class="docutils field-list" frame="void" rules="none">
|
||||
<col class="field-name" />
|
||||
<col class="field-body" />
|
||||
<tbody valign="top">
|
||||
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple">
|
||||
<li><strong>framework_type</strong> – deep learning framework type. currently only tensorflow is supported</li>
|
||||
<li><strong>evaluate_only</strong> – the task will be used only for evaluating the model</li>
|
||||
<li><strong>evaluate_only</strong> – if not None, the task will be used only for evaluating the model for the given number of steps.
|
||||
A value of 0 means that task will be evaluated for an infinite number of steps.</li>
|
||||
<li><strong>parameters_server_hosts</strong> – comma-separated list of hostname:port pairs to which the parameter servers are
|
||||
assigned</li>
|
||||
<li><strong>worker_hosts</strong> – comma-separated list of hostname:port pairs to which the workers are assigned</li>
|
||||
@@ -325,7 +329,7 @@ assigned</li>
|
||||
<li><strong>dnd</strong> – an external DND to use for NEC. This is a workaround needed for a shared DND not using the scratchpad.</li>
|
||||
<li><strong>seed</strong> – a seed to use for the random numbers generator</li>
|
||||
<li><strong>checkpoint_save_secs</strong> – the number of seconds between each checkpoint saving</li>
|
||||
<li><strong>checkpoint_restore_dir</strong> – the directory to restore the checkpoints from</li>
|
||||
<li><strong>checkpoint_restore_path</strong> – the path to restore the checkpoints from</li>
|
||||
<li><strong>checkpoint_save_dir</strong> – the directory to store the checkpoints in</li>
|
||||
<li><strong>export_onnx_graph</strong> – If set to True, this will export an onnx graph each time a checkpoint is saved</li>
|
||||
<li><strong>apply_stop_condition</strong> – If set to True, this will apply the stop condition defined by reaching a target success rate</li>
|
||||
|
||||
@@ -121,6 +121,7 @@
|
||||
<li class="toctree-l2"><a class="reference internal" href="cil.html">Conditional Imitation Learning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/cppo.html">Clipped Proximal Policy Optimization</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/ddpg.html">Deep Deterministic Policy Gradient</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/sac.html">Soft Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../other/dfp.html">Direct Future Prediction</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/double_dqn.html">Double DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/dqn.html">Deep Q Networks</a></li>
|
||||
|
||||
@@ -121,6 +121,7 @@
|
||||
</li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/cppo.html">Clipped Proximal Policy Optimization</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/ddpg.html">Deep Deterministic Policy Gradient</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/sac.html">Soft Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../other/dfp.html">Direct Future Prediction</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/double_dqn.html">Double DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/dqn.html">Deep Q Networks</a></li>
|
||||
|
||||
@@ -114,6 +114,7 @@
|
||||
<li class="toctree-l2"><a class="reference internal" href="imitation/cil.html">Conditional Imitation Learning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="policy_optimization/cppo.html">Clipped Proximal Policy Optimization</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="policy_optimization/ddpg.html">Deep Deterministic Policy Gradient</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="policy_optimization/sac.html">Soft Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="other/dfp.html">Direct Future Prediction</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="value_optimization/double_dqn.html">Double DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="value_optimization/dqn.html">Deep Q Networks</a></li>
|
||||
@@ -221,6 +222,7 @@ A detailed description of those algorithms can be found by navigating to each of
|
||||
<li class="toctree-l1"><a class="reference internal" href="imitation/cil.html">Conditional Imitation Learning</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="policy_optimization/cppo.html">Clipped Proximal Policy Optimization</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="policy_optimization/ddpg.html">Deep Deterministic Policy Gradient</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="policy_optimization/sac.html">Soft Actor-Critic</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="other/dfp.html">Direct Future Prediction</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="value_optimization/double_dqn.html">Double DQN</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="value_optimization/dqn.html">Deep Q Networks</a></li>
|
||||
@@ -280,13 +282,15 @@ used for visualization purposes, such as printing to the screen, rendering, and
|
||||
</table>
|
||||
<dl class="method">
|
||||
<dt id="rl_coach.agents.agent.Agent.act">
|
||||
<code class="descname">act</code><span class="sig-paren">(</span><span class="sig-paren">)</span> → rl_coach.core_types.ActionInfo<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.act"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.act" title="Permalink to this definition">¶</a></dt>
|
||||
<code class="descname">act</code><span class="sig-paren">(</span><em>action: Union[None</em>, <em>int</em>, <em>float</em>, <em>numpy.ndarray</em>, <em>List] = None</em><span class="sig-paren">)</span> → rl_coach.core_types.ActionInfo<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.act"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.act" title="Permalink to this definition">¶</a></dt>
|
||||
<dd><p>Given the agents current knowledge, decide on the next action to apply to the environment</p>
|
||||
<table class="docutils field-list" frame="void" rules="none">
|
||||
<col class="field-name" />
|
||||
<col class="field-body" />
|
||||
<tbody valign="top">
|
||||
<tr class="field-odd field"><th class="field-name">Returns:</th><td class="field-body">An ActionInfo object, which contains the action and any additional info from the action decision process</td>
|
||||
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><strong>action</strong> – An action to take, overriding whatever the current policy is</td>
|
||||
</tr>
|
||||
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body">An ActionInfo object, which contains the action and any additional info from the action decision process</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
@@ -357,26 +361,6 @@ for creating the network.</p>
|
||||
</table>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="method">
|
||||
<dt id="rl_coach.agents.agent.Agent.emulate_act_on_trainer">
|
||||
<code class="descname">emulate_act_on_trainer</code><span class="sig-paren">(</span><em>transition: rl_coach.core_types.Transition</em><span class="sig-paren">)</span> → rl_coach.core_types.ActionInfo<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.emulate_act_on_trainer"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.emulate_act_on_trainer" title="Permalink to this definition">¶</a></dt>
|
||||
<dd><p>This emulates the act using the transition obtained from the rollout worker on the training worker
|
||||
in case of distributed training.
|
||||
Given the agents current knowledge, decide on the next action to apply to the environment
|
||||
:return: an action and a dictionary containing any additional info from the action decision process</p>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="method">
|
||||
<dt id="rl_coach.agents.agent.Agent.emulate_observe_on_trainer">
|
||||
<code class="descname">emulate_observe_on_trainer</code><span class="sig-paren">(</span><em>transition: rl_coach.core_types.Transition</em><span class="sig-paren">)</span> → bool<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.emulate_observe_on_trainer"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.emulate_observe_on_trainer" title="Permalink to this definition">¶</a></dt>
|
||||
<dd><p>This emulates the observe using the transition obtained from the rollout worker on the training worker
|
||||
in case of distributed training.
|
||||
Given a response from the environment, distill the observation from it and store it for later use.
|
||||
The response should be a dictionary containing the performed action, the new observation and measurements,
|
||||
the reward, a game over flag and any additional information necessary.
|
||||
:return:</p>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="method">
|
||||
<dt id="rl_coach.agents.agent.Agent.get_predictions">
|
||||
<code class="descname">get_predictions</code><span class="sig-paren">(</span><em>states: List[Dict[str, numpy.ndarray]], prediction_type: rl_coach.core_types.PredictionType</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.get_predictions"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.get_predictions" title="Permalink to this definition">¶</a></dt>
|
||||
@@ -540,7 +524,7 @@ given observation</td>
|
||||
|
||||
<dl class="method">
|
||||
<dt id="rl_coach.agents.agent.Agent.prepare_batch_for_inference">
|
||||
<code class="descname">prepare_batch_for_inference</code><span class="sig-paren">(</span><em>states: Union[Dict[str, numpy.ndarray], List[Dict[str, numpy.ndarray]]], network_name: str</em><span class="sig-paren">)</span> → Dict[str, numpy.core.multiarray.array]<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.prepare_batch_for_inference"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.prepare_batch_for_inference" title="Permalink to this definition">¶</a></dt>
|
||||
<code class="descname">prepare_batch_for_inference</code><span class="sig-paren">(</span><em>states: Union[Dict[str, numpy.ndarray], List[Dict[str, numpy.ndarray]]], network_name: str</em><span class="sig-paren">)</span> → Dict[str, numpy.array]<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.prepare_batch_for_inference"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.prepare_batch_for_inference" title="Permalink to this definition">¶</a></dt>
|
||||
<dd><p>Convert curr_state into input tensors tensorflow is expecting. i.e. if we have several inputs states, stack all
|
||||
observations together, measurements together, etc.</p>
|
||||
<table class="docutils field-list" frame="void" rules="none">
|
||||
@@ -632,6 +616,21 @@ by val, and by the current phase set in self.phase.</p>
|
||||
</table>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="method">
|
||||
<dt id="rl_coach.agents.agent.Agent.run_off_policy_evaluation">
|
||||
<code class="descname">run_off_policy_evaluation</code><span class="sig-paren">(</span><span class="sig-paren">)</span> → None<a class="headerlink" href="#rl_coach.agents.agent.Agent.run_off_policy_evaluation" title="Permalink to this definition">¶</a></dt>
|
||||
<dd><p>Run off-policy evaluation estimators to evaluate the trained policy performance against a dataset.
|
||||
Should only be implemented for off-policy RL algorithms.</p>
|
||||
<table class="docutils field-list" frame="void" rules="none">
|
||||
<col class="field-name" />
|
||||
<col class="field-body" />
|
||||
<tbody valign="top">
|
||||
<tr class="field-odd field"><th class="field-name">Returns:</th><td class="field-body">None</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="method">
|
||||
<dt id="rl_coach.agents.agent.Agent.run_pre_network_filter_for_inference">
|
||||
<code class="descname">run_pre_network_filter_for_inference</code><span class="sig-paren">(</span><em>state: Dict[str, numpy.ndarray], update_filter_internal_state: bool = True</em><span class="sig-paren">)</span> → Dict[str, numpy.ndarray]<a class="reference internal" href="../../_modules/rl_coach/agents/agent.html#Agent.run_pre_network_filter_for_inference"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.agent.Agent.run_pre_network_filter_for_inference" title="Permalink to this definition">¶</a></dt>
|
||||
|
||||
@@ -30,7 +30,7 @@
|
||||
<link rel="index" title="Index" href="../../../genindex.html" />
|
||||
<link rel="search" title="Search" href="../../../search.html" />
|
||||
<link rel="next" title="Double DQN" href="../value_optimization/double_dqn.html" />
|
||||
<link rel="prev" title="Deep Deterministic Policy Gradient" href="../policy_optimization/ddpg.html" />
|
||||
<link rel="prev" title="Soft Actor-Critic" href="../policy_optimization/sac.html" />
|
||||
<link href="../../../_static/css/custom.css" rel="stylesheet" type="text/css">
|
||||
|
||||
|
||||
@@ -114,6 +114,7 @@
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/cil.html">Conditional Imitation Learning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/cppo.html">Clipped Proximal Policy Optimization</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/ddpg.html">Deep Deterministic Policy Gradient</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/sac.html">Soft Actor-Critic</a></li>
|
||||
<li class="toctree-l2 current"><a class="current reference internal" href="#">Direct Future Prediction</a><ul>
|
||||
<li class="toctree-l3"><a class="reference internal" href="#network-structure">Network Structure</a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="#algorithm-description">Algorithm Description</a><ul>
|
||||
@@ -296,7 +297,7 @@ have a different scale and you want to normalize them to the same scale.</li>
|
||||
<a href="../value_optimization/double_dqn.html" class="btn btn-neutral float-right" title="Double DQN" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a>
|
||||
|
||||
|
||||
<a href="../policy_optimization/ddpg.html" class="btn btn-neutral" title="Deep Deterministic Policy Gradient" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left"></span> Previous</a>
|
||||
<a href="../policy_optimization/sac.html" class="btn btn-neutral" title="Soft Actor-Critic" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left"></span> Previous</a>
|
||||
|
||||
</div>
|
||||
|
||||
|
||||
@@ -122,6 +122,7 @@
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/cil.html">Conditional Imitation Learning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="cppo.html">Clipped Proximal Policy Optimization</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="ddpg.html">Deep Deterministic Policy Gradient</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="sac.html">Soft Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../other/dfp.html">Direct Future Prediction</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/double_dqn.html">Double DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/dqn.html">Deep Q Networks</a></li>
|
||||
|
||||
@@ -122,6 +122,7 @@
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/cil.html">Conditional Imitation Learning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="cppo.html">Clipped Proximal Policy Optimization</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="ddpg.html">Deep Deterministic Policy Gradient</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="sac.html">Soft Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../other/dfp.html">Direct Future Prediction</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/double_dqn.html">Double DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/dqn.html">Deep Q Networks</a></li>
|
||||
@@ -247,21 +248,20 @@ and <span class="math notranslate nohighlight">\(n\)</span> (replay ratio) off-p
|
||||
\[\text{where} \quad \bar{\rho}_{t} = \min{\left\{c,\rho_t\right\}},\quad \rho_t=\frac{\pi (a_t \mid s_t)}{\mu (a_t \mid s_t)}\]</div>
|
||||
</div></blockquote>
|
||||
</li>
|
||||
<li><dl class="first docutils">
|
||||
<dt><strong>Accumulate gradients:</strong></dt>
|
||||
<dd><p class="first"><span class="math notranslate nohighlight">\(\bullet\)</span> <strong>Policy gradients (with bias correction):</strong></p>
|
||||
<li><p class="first"><strong>Accumulate gradients:</strong></p>
|
||||
<blockquote>
|
||||
<div><p><span class="math notranslate nohighlight">\(\bullet\)</span> <strong>Policy gradients (with bias correction):</strong></p>
|
||||
<blockquote>
|
||||
<div><div class="math notranslate nohighlight">
|
||||
\[\begin{split}\hat{g}_t^{policy} & = & \bar{\rho}_{t} \nabla \log \pi (a_t \mid s_t) [Q^{ret}(s_t,a_t) - V(s_t)] \\
|
||||
& & + \mathbb{E}_{a \sim \pi} \left(\left[\frac{\rho_t(a)-c}{\rho_t(a)}\right] \nabla \log \pi (a \mid s_t) [Q(s_t,a) - V(s_t)] \right)\end{split}\]</div>
|
||||
</div></blockquote>
|
||||
<p><span class="math notranslate nohighlight">\(\bullet\)</span> <strong>Q-Head gradients (MSE):</strong></p>
|
||||
<blockquote class="last">
|
||||
<blockquote>
|
||||
<div><div class="math notranslate nohighlight">
|
||||
\[\begin{split}\hat{g}_t^{Q} = (Q^{ret}(s_t,a_t) - Q(s_t,a_t)) \nabla Q(s_t,a_t)\\\end{split}\]</div>
|
||||
</div></blockquote>
|
||||
</dd>
|
||||
</dl>
|
||||
</div></blockquote>
|
||||
</li>
|
||||
<li><p class="first"><strong>(Optional) Trust region update:</strong> change the policy loss gradient w.r.t network output:</p>
|
||||
<blockquote>
|
||||
|
||||
@@ -122,6 +122,7 @@
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="ddpg.html">Deep Deterministic Policy Gradient</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="sac.html">Soft Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../other/dfp.html">Direct Future Prediction</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/double_dqn.html">Double DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/dqn.html">Deep Q Networks</a></li>
|
||||
|
||||
@@ -29,7 +29,7 @@
|
||||
<link rel="stylesheet" href="../../../_static/css/custom.css" type="text/css" />
|
||||
<link rel="index" title="Index" href="../../../genindex.html" />
|
||||
<link rel="search" title="Search" href="../../../search.html" />
|
||||
<link rel="next" title="Direct Future Prediction" href="../other/dfp.html" />
|
||||
<link rel="next" title="Soft Actor-Critic" href="sac.html" />
|
||||
<link rel="prev" title="Clipped Proximal Policy Optimization" href="cppo.html" />
|
||||
<link href="../../../_static/css/custom.css" rel="stylesheet" type="text/css">
|
||||
|
||||
@@ -122,6 +122,7 @@
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="sac.html">Soft Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../other/dfp.html">Direct Future Prediction</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/double_dqn.html">Double DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/dqn.html">Deep Q Networks</a></li>
|
||||
@@ -297,7 +298,7 @@ values. If set to False, the terminal states reward will be taken as the target
|
||||
|
||||
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
|
||||
|
||||
<a href="../other/dfp.html" class="btn btn-neutral float-right" title="Direct Future Prediction" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a>
|
||||
<a href="sac.html" class="btn btn-neutral float-right" title="Soft Actor-Critic" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a>
|
||||
|
||||
|
||||
<a href="cppo.html" class="btn btn-neutral" title="Clipped Proximal Policy Optimization" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left"></span> Previous</a>
|
||||
|
||||
@@ -114,6 +114,7 @@
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/cil.html">Conditional Imitation Learning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="cppo.html">Clipped Proximal Policy Optimization</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="ddpg.html">Deep Deterministic Policy Gradient</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="sac.html">Soft Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../other/dfp.html">Direct Future Prediction</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/double_dqn.html">Double DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/dqn.html">Deep Q Networks</a></li>
|
||||
|
||||
@@ -114,6 +114,7 @@
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/cil.html">Conditional Imitation Learning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="cppo.html">Clipped Proximal Policy Optimization</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="ddpg.html">Deep Deterministic Policy Gradient</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="sac.html">Soft Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../other/dfp.html">Direct Future Prediction</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/double_dqn.html">Double DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/dqn.html">Deep Q Networks</a></li>
|
||||
|
||||
343
docs/components/agents/policy_optimization/sac.html
Normal file
343
docs/components/agents/policy_optimization/sac.html
Normal file
@@ -0,0 +1,343 @@
|
||||
|
||||
|
||||
<!DOCTYPE html>
|
||||
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
|
||||
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
|
||||
<head>
|
||||
<meta charset="utf-8">
|
||||
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
|
||||
<title>Soft Actor-Critic — Reinforcement Learning Coach 0.11.0 documentation</title>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
|
||||
<link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
|
||||
<link rel="stylesheet" href="../../../_static/css/custom.css" type="text/css" />
|
||||
<link rel="index" title="Index" href="../../../genindex.html" />
|
||||
<link rel="search" title="Search" href="../../../search.html" />
|
||||
<link rel="next" title="Direct Future Prediction" href="../other/dfp.html" />
|
||||
<link rel="prev" title="Deep Deterministic Policy Gradient" href="ddpg.html" />
|
||||
<link href="../../../_static/css/custom.css" rel="stylesheet" type="text/css">
|
||||
|
||||
|
||||
|
||||
<script src="../../../_static/js/modernizr.min.js"></script>
|
||||
|
||||
</head>
|
||||
|
||||
<body class="wy-body-for-nav">
|
||||
|
||||
|
||||
<div class="wy-grid-for-nav">
|
||||
|
||||
|
||||
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
|
||||
<div class="wy-side-scroll">
|
||||
<div class="wy-side-nav-search">
|
||||
|
||||
|
||||
|
||||
<a href="../../../index.html" class="icon icon-home"> Reinforcement Learning Coach
|
||||
|
||||
|
||||
|
||||
|
||||
<img src="../../../_static/dark_logo.png" class="logo" alt="Logo"/>
|
||||
|
||||
</a>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<div role="search">
|
||||
<form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get">
|
||||
<input type="text" name="q" placeholder="Search docs" />
|
||||
<input type="hidden" name="check_keywords" value="yes" />
|
||||
<input type="hidden" name="area" value="default" />
|
||||
</form>
|
||||
</div>
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<p class="caption"><span class="caption-text">Intro</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../usage.html">Usage</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../dist_usage.html">Usage - Distributed Coach</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../features/index.html">Features</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../selecting_an_algorithm.html">Selecting an Algorithm</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../dashboard.html">Coach Dashboard</a></li>
|
||||
</ul>
|
||||
<p class="caption"><span class="caption-text">Design</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../design/control_flow.html">Control Flow</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../design/network.html">Network Design</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../design/horizontal_scaling.html">Distributed Coach - Horizontal Scale-Out</a></li>
|
||||
</ul>
|
||||
<p class="caption"><span class="caption-text">Contributing</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../contributing/add_agent.html">Adding a New Agent</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../../contributing/add_env.html">Adding a New Environment</a></li>
|
||||
</ul>
|
||||
<p class="caption"><span class="caption-text">Components</span></p>
|
||||
<ul class="current">
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="../index.html">Agents</a><ul class="current">
|
||||
<li class="toctree-l2"><a class="reference internal" href="ac.html">Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="acer.html">ACER</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/bc.html">Behavioral Cloning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/bs_dqn.html">Bootstrapped DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/categorical_dqn.html">Categorical DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/cil.html">Conditional Imitation Learning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="cppo.html">Clipped Proximal Policy Optimization</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="ddpg.html">Deep Deterministic Policy Gradient</a></li>
|
||||
<li class="toctree-l2 current"><a class="current reference internal" href="#">Soft Actor-Critic</a><ul>
|
||||
<li class="toctree-l3"><a class="reference internal" href="#network-structure">Network Structure</a></li>
|
||||
<li class="toctree-l3"><a class="reference internal" href="#algorithm-description">Algorithm Description</a><ul>
|
||||
<li class="toctree-l4"><a class="reference internal" href="#choosing-an-action-continuous-actions">Choosing an action - Continuous actions</a></li>
|
||||
<li class="toctree-l4"><a class="reference internal" href="#training-the-network">Training the network</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../other/dfp.html">Direct Future Prediction</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/double_dqn.html">Double DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/dqn.html">Deep Q Networks</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/dueling_dqn.html">Dueling DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/mmc.html">Mixed Monte Carlo</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/n_step.html">N-Step Q Learning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/naf.html">Normalized Advantage Functions</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/nec.html">Neural Episodic Control</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/pal.html">Persistent Advantage Learning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="pg.html">Policy Gradient</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="ppo.html">Proximal Policy Optimization</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/rainbow.html">Rainbow</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../value_optimization/qr_dqn.html">Quantile Regression DQN</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../architectures/index.html">Architectures</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../data_stores/index.html">Data Stores</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../environments/index.html">Environments</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../exploration_policies/index.html">Exploration Policies</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../filters/index.html">Filters</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../memories/index.html">Memories</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../memory_backends/index.html">Memory Backends</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../orchestrators/index.html">Orchestrators</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../core_types.html">Core Types</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../spaces.html">Spaces</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../additional_parameters.html">Additional Parameters</a></li>
|
||||
</ul>
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
</nav>
|
||||
|
||||
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
|
||||
|
||||
|
||||
<nav class="wy-nav-top" aria-label="top navigation">
|
||||
|
||||
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
|
||||
<a href="../../../index.html">Reinforcement Learning Coach</a>
|
||||
|
||||
</nav>
|
||||
|
||||
|
||||
<div class="wy-nav-content">
|
||||
|
||||
<div class="rst-content">
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<div role="navigation" aria-label="breadcrumbs navigation">
|
||||
|
||||
<ul class="wy-breadcrumbs">
|
||||
|
||||
<li><a href="../../../index.html">Docs</a> »</li>
|
||||
|
||||
<li><a href="../index.html">Agents</a> »</li>
|
||||
|
||||
<li>Soft Actor-Critic</li>
|
||||
|
||||
|
||||
<li class="wy-breadcrumbs-aside">
|
||||
|
||||
|
||||
<a href="../../../_sources/components/agents/policy_optimization/sac.rst.txt" rel="nofollow"> View page source</a>
|
||||
|
||||
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
|
||||
|
||||
<hr/>
|
||||
</div>
|
||||
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
|
||||
<div itemprop="articleBody">
|
||||
|
||||
<div class="section" id="soft-actor-critic">
|
||||
<h1>Soft Actor-Critic<a class="headerlink" href="#soft-actor-critic" title="Permalink to this headline">¶</a></h1>
|
||||
<p><strong>Actions space:</strong> Continuous</p>
|
||||
<p><strong>References:</strong> <a class="reference external" href="https://arxiv.org/abs/1801.01290">Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor</a></p>
|
||||
<div class="section" id="network-structure">
|
||||
<h2>Network Structure<a class="headerlink" href="#network-structure" title="Permalink to this headline">¶</a></h2>
|
||||
<img alt="../../../_images/sac.png" class="align-center" src="../../../_images/sac.png" />
|
||||
</div>
|
||||
<div class="section" id="algorithm-description">
|
||||
<h2>Algorithm Description<a class="headerlink" href="#algorithm-description" title="Permalink to this headline">¶</a></h2>
|
||||
<div class="section" id="choosing-an-action-continuous-actions">
|
||||
<h3>Choosing an action - Continuous actions<a class="headerlink" href="#choosing-an-action-continuous-actions" title="Permalink to this headline">¶</a></h3>
|
||||
<p>The policy network is used in order to predict mean and log std for each action. While training, a sample is taken
|
||||
from a Gaussian distribution with these mean and std values. When testing, the agent can choose deterministically
|
||||
by picking the mean value or sample from a gaussian distribution like in training.</p>
|
||||
</div>
|
||||
<div class="section" id="training-the-network">
|
||||
<h3>Training the network<a class="headerlink" href="#training-the-network" title="Permalink to this headline">¶</a></h3>
|
||||
<p>Start by sampling a batch <span class="math notranslate nohighlight">\(B\)</span> of transitions from the experience replay.</p>
|
||||
<ul>
|
||||
<li><p class="first">To train the <strong>Q network</strong>, use the following targets:</p>
|
||||
<div class="math notranslate nohighlight">
|
||||
\[y_t^Q=r(s_t,a_t)+\gamma \cdot V(s_{t+1})\]</div>
|
||||
<p>The state value used in the above target is acquired by running the target state value network.</p>
|
||||
</li>
|
||||
<li><p class="first">To train the <strong>State Value network</strong>, use the following targets:</p>
|
||||
<div class="math notranslate nohighlight">
|
||||
\[y_t^V = \min_{i=1,2}Q_i(s_t,\tilde{a}) - log\pi (\tilde{a} \vert s),\,\,\,\, \tilde{a} \sim \pi(\cdot \vert s_t)\]</div>
|
||||
<p>The state value network is trained using a sample-based approximation of the connection between and state value and state
|
||||
action values, The actions used for constructing the target are <strong>not</strong> sampled from the replay buffer, but rather sampled
|
||||
from the current policy.</p>
|
||||
</li>
|
||||
<li><p class="first">To train the <strong>actor network</strong>, use the following equation:</p>
|
||||
<div class="math notranslate nohighlight">
|
||||
\[\nabla_{\theta} J \approx \nabla_{\theta} \frac{1}{\vert B \vert} \sum_{s_t\in B} \left( Q \left(s_t, \tilde{a}_\theta(s_t)\right) - log\pi_{\theta}(\tilde{a}_{\theta}(s_t)\vert s_t) \right),\,\,\,\, \tilde{a} \sim \pi(\cdot \vert s_t)\]</div>
|
||||
</li>
|
||||
</ul>
|
||||
<p>After every training step, do a soft update of the V target network’s weights from the online networks.</p>
|
||||
<dl class="class">
|
||||
<dt id="rl_coach.agents.soft_actor_critic_agent.SoftActorCriticAlgorithmParameters">
|
||||
<em class="property">class </em><code class="descclassname">rl_coach.agents.soft_actor_critic_agent.</code><code class="descname">SoftActorCriticAlgorithmParameters</code><a class="reference internal" href="../../../_modules/rl_coach/agents/soft_actor_critic_agent.html#SoftActorCriticAlgorithmParameters"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.agents.soft_actor_critic_agent.SoftActorCriticAlgorithmParameters" title="Permalink to this definition">¶</a></dt>
|
||||
<dd><table class="docutils field-list" frame="void" rules="none">
|
||||
<col class="field-name" />
|
||||
<col class="field-body" />
|
||||
<tbody valign="top">
|
||||
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple">
|
||||
<li><strong>num_steps_between_copying_online_weights_to_target</strong> – (StepMethod)
|
||||
The number of steps between copying the online network weights to the target network weights.</li>
|
||||
<li><strong>rate_for_copying_weights_to_target</strong> – (float)
|
||||
When copying the online network weights to the target network weights, a soft update will be used, which
|
||||
weight the new online network weights by rate_for_copying_weights_to_target. (Tau as defined in the paper)</li>
|
||||
<li><strong>use_deterministic_for_evaluation</strong> – (bool)
|
||||
If True, during the evaluation phase, action are chosen deterministically according to the policy mean
|
||||
and not sampled from the policy distribution.</li>
|
||||
</ul>
|
||||
</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
</dd></dl>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
<footer>
|
||||
|
||||
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
|
||||
|
||||
<a href="../other/dfp.html" class="btn btn-neutral float-right" title="Direct Future Prediction" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a>
|
||||
|
||||
|
||||
<a href="ddpg.html" class="btn btn-neutral" title="Deep Deterministic Policy Gradient" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left"></span> Previous</a>
|
||||
|
||||
</div>
|
||||
|
||||
|
||||
<hr/>
|
||||
|
||||
<div role="contentinfo">
|
||||
<p>
|
||||
© Copyright 2018, Intel AI Lab
|
||||
|
||||
</p>
|
||||
</div>
|
||||
Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
|
||||
|
||||
</footer>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
|
||||
</section>
|
||||
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<script type="text/javascript" id="documentation_options" data-url_root="../../../" src="../../../_static/documentation_options.js"></script>
|
||||
<script type="text/javascript" src="../../../_static/jquery.js"></script>
|
||||
<script type="text/javascript" src="../../../_static/underscore.js"></script>
|
||||
<script type="text/javascript" src="../../../_static/doctools.js"></script>
|
||||
<script type="text/javascript" src="../../../_static/language_data.js"></script>
|
||||
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
|
||||
|
||||
|
||||
|
||||
|
||||
<script type="text/javascript" src="../../../_static/js/theme.js"></script>
|
||||
|
||||
<script type="text/javascript">
|
||||
jQuery(function () {
|
||||
SphinxRtdTheme.Navigation.enable(true);
|
||||
});
|
||||
</script>
|
||||
|
||||
</body>
|
||||
</html>
|
||||
@@ -123,6 +123,7 @@
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/cil.html">Conditional Imitation Learning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/cppo.html">Clipped Proximal Policy Optimization</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/ddpg.html">Deep Deterministic Policy Gradient</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/sac.html">Soft Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../other/dfp.html">Direct Future Prediction</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="double_dqn.html">Double DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="dqn.html">Deep Q Networks</a></li>
|
||||
|
||||
@@ -121,6 +121,7 @@
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/cil.html">Conditional Imitation Learning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/cppo.html">Clipped Proximal Policy Optimization</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/ddpg.html">Deep Deterministic Policy Gradient</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/sac.html">Soft Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../other/dfp.html">Direct Future Prediction</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="double_dqn.html">Double DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="dqn.html">Deep Q Networks</a></li>
|
||||
|
||||
@@ -114,6 +114,7 @@
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/cil.html">Conditional Imitation Learning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/cppo.html">Clipped Proximal Policy Optimization</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/ddpg.html">Deep Deterministic Policy Gradient</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/sac.html">Soft Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../other/dfp.html">Direct Future Prediction</a></li>
|
||||
<li class="toctree-l2 current"><a class="current reference internal" href="#">Double DQN</a><ul>
|
||||
<li class="toctree-l3"><a class="reference internal" href="#network-structure">Network Structure</a></li>
|
||||
|
||||
@@ -114,6 +114,7 @@
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/cil.html">Conditional Imitation Learning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/cppo.html">Clipped Proximal Policy Optimization</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/ddpg.html">Deep Deterministic Policy Gradient</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/sac.html">Soft Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../other/dfp.html">Direct Future Prediction</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="double_dqn.html">Double DQN</a></li>
|
||||
<li class="toctree-l2 current"><a class="current reference internal" href="#">Deep Q Networks</a><ul>
|
||||
|
||||
@@ -114,6 +114,7 @@
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/cil.html">Conditional Imitation Learning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/cppo.html">Clipped Proximal Policy Optimization</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/ddpg.html">Deep Deterministic Policy Gradient</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/sac.html">Soft Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../other/dfp.html">Direct Future Prediction</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="double_dqn.html">Double DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="dqn.html">Deep Q Networks</a></li>
|
||||
|
||||
@@ -114,6 +114,7 @@
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/cil.html">Conditional Imitation Learning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/cppo.html">Clipped Proximal Policy Optimization</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/ddpg.html">Deep Deterministic Policy Gradient</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/sac.html">Soft Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../other/dfp.html">Direct Future Prediction</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="double_dqn.html">Double DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="dqn.html">Deep Q Networks</a></li>
|
||||
|
||||
@@ -114,6 +114,7 @@
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/cil.html">Conditional Imitation Learning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/cppo.html">Clipped Proximal Policy Optimization</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/ddpg.html">Deep Deterministic Policy Gradient</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/sac.html">Soft Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../other/dfp.html">Direct Future Prediction</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="double_dqn.html">Double DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="dqn.html">Deep Q Networks</a></li>
|
||||
|
||||
@@ -114,6 +114,7 @@
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/cil.html">Conditional Imitation Learning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/cppo.html">Clipped Proximal Policy Optimization</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/ddpg.html">Deep Deterministic Policy Gradient</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/sac.html">Soft Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../other/dfp.html">Direct Future Prediction</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="double_dqn.html">Double DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="dqn.html">Deep Q Networks</a></li>
|
||||
|
||||
@@ -114,6 +114,7 @@
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/cil.html">Conditional Imitation Learning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/cppo.html">Clipped Proximal Policy Optimization</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/ddpg.html">Deep Deterministic Policy Gradient</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/sac.html">Soft Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../other/dfp.html">Direct Future Prediction</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="double_dqn.html">Double DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="dqn.html">Deep Q Networks</a></li>
|
||||
|
||||
@@ -114,6 +114,7 @@
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/cil.html">Conditional Imitation Learning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/cppo.html">Clipped Proximal Policy Optimization</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/ddpg.html">Deep Deterministic Policy Gradient</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/sac.html">Soft Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../other/dfp.html">Direct Future Prediction</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="double_dqn.html">Double DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="dqn.html">Deep Q Networks</a></li>
|
||||
|
||||
@@ -114,6 +114,7 @@
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/cil.html">Conditional Imitation Learning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/cppo.html">Clipped Proximal Policy Optimization</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/ddpg.html">Deep Deterministic Policy Gradient</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/sac.html">Soft Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../other/dfp.html">Direct Future Prediction</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="double_dqn.html">Double DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="dqn.html">Deep Q Networks</a></li>
|
||||
|
||||
@@ -114,6 +114,7 @@
|
||||
<li class="toctree-l2"><a class="reference internal" href="../imitation/cil.html">Conditional Imitation Learning</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/cppo.html">Clipped Proximal Policy Optimization</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/ddpg.html">Deep Deterministic Policy Gradient</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../policy_optimization/sac.html">Soft Actor-Critic</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../other/dfp.html">Direct Future Prediction</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="double_dqn.html">Double DQN</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="dqn.html">Deep Q Networks</a></li>
|
||||
|
||||
@@ -193,7 +193,7 @@ own components under a dedicated directory. For example, tensorflow components w
|
||||
parts that are implemented using TensorFlow.</p>
|
||||
<dl class="class">
|
||||
<dt id="rl_coach.base_parameters.NetworkParameters">
|
||||
<em class="property">class </em><code class="descclassname">rl_coach.base_parameters.</code><code class="descname">NetworkParameters</code><span class="sig-paren">(</span><em>force_cpu=False</em>, <em>async_training=False</em>, <em>shared_optimizer=True</em>, <em>scale_down_gradients_by_number_of_workers_for_sync_training=True</em>, <em>clip_gradients=None</em>, <em>gradients_clipping_method=<GradientClippingMethod.ClipByGlobalNorm: 0></em>, <em>l2_regularization=0</em>, <em>learning_rate=0.00025</em>, <em>learning_rate_decay_rate=0</em>, <em>learning_rate_decay_steps=0</em>, <em>input_embedders_parameters={}</em>, <em>embedding_merger_type=<EmbeddingMergerType.Concat: 0></em>, <em>middleware_parameters=None</em>, <em>heads_parameters=[]</em>, <em>use_separate_networks_per_head=False</em>, <em>optimizer_type='Adam'</em>, <em>optimizer_epsilon=0.0001</em>, <em>adam_optimizer_beta1=0.9</em>, <em>adam_optimizer_beta2=0.99</em>, <em>rms_prop_optimizer_decay=0.9</em>, <em>batch_size=32</em>, <em>replace_mse_with_huber_loss=False</em>, <em>create_target_network=False</em>, <em>tensorflow_support=True</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/base_parameters.html#NetworkParameters"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.base_parameters.NetworkParameters" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property">class </em><code class="descclassname">rl_coach.base_parameters.</code><code class="descname">NetworkParameters</code><span class="sig-paren">(</span><em>force_cpu=False</em>, <em>async_training=False</em>, <em>shared_optimizer=True</em>, <em>scale_down_gradients_by_number_of_workers_for_sync_training=True</em>, <em>clip_gradients=None</em>, <em>gradients_clipping_method=<GradientClippingMethod.ClipByGlobalNorm: 0></em>, <em>l2_regularization=0</em>, <em>learning_rate=0.00025</em>, <em>learning_rate_decay_rate=0</em>, <em>learning_rate_decay_steps=0</em>, <em>input_embedders_parameters={}</em>, <em>embedding_merger_type=<EmbeddingMergerType.Concat: 0></em>, <em>middleware_parameters=None</em>, <em>heads_parameters=[]</em>, <em>use_separate_networks_per_head=False</em>, <em>optimizer_type='Adam'</em>, <em>optimizer_epsilon=0.0001</em>, <em>adam_optimizer_beta1=0.9</em>, <em>adam_optimizer_beta2=0.99</em>, <em>rms_prop_optimizer_decay=0.9</em>, <em>batch_size=32</em>, <em>replace_mse_with_huber_loss=False</em>, <em>create_target_network=False</em>, <em>tensorflow_support=True</em>, <em>softmax_temperature=1</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/base_parameters.html#NetworkParameters"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.base_parameters.NetworkParameters" title="Permalink to this definition">¶</a></dt>
|
||||
<dd><table class="docutils field-list" frame="void" rules="none">
|
||||
<col class="field-name" />
|
||||
<col class="field-body" />
|
||||
@@ -257,6 +257,7 @@ selected for this network.</li>
|
||||
same weights as the online network. It can then be queried, and its weights can be synced from the
|
||||
online network at will.</li>
|
||||
<li><strong>tensorflow_support</strong> – A flag which specifies if the network is supported by the TensorFlow framework.</li>
|
||||
<li><strong>softmax_temperature</strong> – If a softmax is present in the network head output, use this temperature</li>
|
||||
</ul>
|
||||
</td>
|
||||
</tr>
|
||||
|
||||
@@ -194,7 +194,7 @@
|
||||
<h2>ActionInfo<a class="headerlink" href="#actioninfo" title="Permalink to this headline">¶</a></h2>
|
||||
<dl class="class">
|
||||
<dt id="rl_coach.core_types.ActionInfo">
|
||||
<em class="property">class </em><code class="descclassname">rl_coach.core_types.</code><code class="descname">ActionInfo</code><span class="sig-paren">(</span><em>action: Union[int, float, numpy.ndarray, List], all_action_probabilities: float = 0, action_value: float = 0.0, state_value: float = 0.0, max_action_value: float = None, action_intrinsic_reward: float = 0</em><span class="sig-paren">)</span><a class="reference internal" href="../_modules/rl_coach/core_types.html#ActionInfo"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.core_types.ActionInfo" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property">class </em><code class="descclassname">rl_coach.core_types.</code><code class="descname">ActionInfo</code><span class="sig-paren">(</span><em>action: Union[int, float, numpy.ndarray, List], all_action_probabilities: float = 0, action_value: float = 0.0, state_value: float = 0.0, max_action_value: float = None</em><span class="sig-paren">)</span><a class="reference internal" href="../_modules/rl_coach/core_types.html#ActionInfo"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.core_types.ActionInfo" title="Permalink to this definition">¶</a></dt>
|
||||
<dd><p>Action info is a class that holds an action and various additional information details about it</p>
|
||||
<table class="docutils field-list" frame="void" rules="none">
|
||||
<col class="field-name" />
|
||||
@@ -208,8 +208,6 @@
|
||||
<li><strong>max_action_value</strong> – in case this is an action that was selected randomly, this is the value of the action
|
||||
that received the maximum value. if no value is given, the action is assumed to be the
|
||||
action with the maximum value</li>
|
||||
<li><strong>action_intrinsic_reward</strong> – can contain any intrinsic reward that the agent wants to add to this action
|
||||
selection</li>
|
||||
</ul>
|
||||
</td>
|
||||
</tr>
|
||||
|
||||
@@ -206,7 +206,7 @@
|
||||
<h3>EpisodicExperienceReplay<a class="headerlink" href="#episodicexperiencereplay" title="Permalink to this headline">¶</a></h3>
|
||||
<dl class="class">
|
||||
<dt id="rl_coach.memories.episodic.EpisodicExperienceReplay">
|
||||
<em class="property">class </em><code class="descclassname">rl_coach.memories.episodic.</code><code class="descname">EpisodicExperienceReplay</code><span class="sig-paren">(</span><em>max_size: Tuple[rl_coach.memories.memory.MemoryGranularity</em>, <em>int] = (<MemoryGranularity.Transitions: 0></em>, <em>1000000)</em>, <em>n_step=-1</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/memories/episodic/episodic_experience_replay.html#EpisodicExperienceReplay"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.memories.episodic.EpisodicExperienceReplay" title="Permalink to this definition">¶</a></dt>
|
||||
<em class="property">class </em><code class="descclassname">rl_coach.memories.episodic.</code><code class="descname">EpisodicExperienceReplay</code><span class="sig-paren">(</span><em>max_size: Tuple[rl_coach.memories.memory.MemoryGranularity</em>, <em>int] = (<MemoryGranularity.Transitions: 0></em>, <em>1000000)</em>, <em>n_step=-1</em>, <em>train_to_eval_ratio: int = 1</em><span class="sig-paren">)</span><a class="reference internal" href="../../_modules/rl_coach/memories/episodic/episodic_experience_replay.html#EpisodicExperienceReplay"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#rl_coach.memories.episodic.EpisodicExperienceReplay" title="Permalink to this definition">¶</a></dt>
|
||||
<dd><p>A replay buffer that stores episodes of transitions. The additional structure allows performing various
|
||||
calculations of total return and other values that depend on the sequential behavior of the transitions
|
||||
in the episode.</p>
|
||||
|
||||
Reference in New Issue
Block a user