Documentation fix
This commit is contained in:
Gal Novik committed
1 parent
05c1005e94
commit
7e3aca22eb
5 files changed
+8
-8
No files matched your search
@@ -132,7 +132,7 @@ When playing with the environment using the :code:`--play` flag, the environment
|
||||
|
||||
.. code-block:: python
|
||||
|
||||
coach -p Breakout_DQN -r
|
||||
coach -p Atari_DQN -lvl breakout -r
|
||||
|
||||
Dumping GIFs
|
||||
++++++++++++
|
||||
@@ -145,7 +145,7 @@ The files are dumped after every evaluation episode, and are saved into the expe
|
||||
|
||||
.. code-block:: python
|
||||
|
||||
coach -p Breakout_A3C -n 4 -dg
|
||||
coach -p Atari_A3C -lvl breakout -n 4 -dg
|
||||
|
||||
Switching Between Deep Learning Frameworks
|
||||
------------------------------------------
|
||||
|
||||
+1
-1
@@ -1 +1 @@
|
||||
Search.setIndex({docnames:["components/additional_parameters","components/agents/imitation/bc","components/agents/imitation/cil","components/agents/index","components/agents/other/dfp","components/agents/policy_optimization/ac","components/agents/policy_optimization/cppo","components/agents/policy_optimization/ddpg","components/agents/policy_optimization/hac","components/agents/policy_optimization/pg","components/agents/policy_optimization/ppo","components/agents/value_optimization/bs_dqn","components/agents/value_optimization/categorical_dqn","components/agents/value_optimization/double_dqn","components/agents/value_optimization/dqn","components/agents/value_optimization/dueling_dqn","components/agents/value_optimization/mmc","components/agents/value_optimization/n_step","components/agents/value_optimization/naf","components/agents/value_optimization/nec","components/agents/value_optimization/pal","components/agents/value_optimization/qr_dqn","components/agents/value_optimization/rainbow","components/architectures/index","components/core_types","components/data_stores/index","components/environments/index","components/exploration_policies/index","components/filters/index","components/filters/input_filters","components/filters/output_filters","components/memories/index","components/memory_backends/index","components/orchestrators/index","components/spaces","contributing/add_agent","contributing/add_env","dashboard","design/control_flow","design/horizontal_scaling","design/network","dist_usage","features/algorithms","features/benchmarks","features/environments","features/index","index","selecting_an_algorithm","test","usage"],envversion:{"sphinx.domains.c":1,"sphinx.domains.changeset":1,"sphinx.domains.cpp":1,"sphinx.domains.javascript":1,"sphinx.domains.math":2,"sphinx.domains.python":1,"sphinx.domains.rst":1,"sphinx.domains.std":1,"sphinx.ext.todo":1,"sphinx.ext.viewcode":1,sphinx:55},filenames:["components/additional_parameters.rst","components/agents/imitation/bc.rst","components/agents/imitation/cil.rst","components/agents/index.rst","components/agents/other/dfp.rst","components/agents/policy_optimization/ac.rst","components/agents/policy_optimization/cppo.rst","components/agents/policy_optimization/ddpg.rst","components/agents/policy_optimization/hac.rst","components/agents/policy_optimization/pg.rst","components/agents/policy_optimization/ppo.rst","components/agents/value_optimization/bs_dqn.rst","components/agents/value_optimization/categorical_dqn.rst","components/agents/value_optimization/double_dqn.rst","components/agents/value_optimization/dqn.rst","components/agents/value_optimization/dueling_dqn.rst","components/agents/value_optimization/mmc.rst","components/agents/value_optimization/n_step.rst","components/agents/value_optimization/naf.rst","components/agents/value_optimization/nec.rst","components/agents/value_optimization/pal.rst","components/agents/value_optimization/qr_dqn.rst","components/agents/value_optimization/rainbow.rst","components/architectures/index.rst","components/core_types.rst","components/data_stores/index.rst","components/environments/index.rst","components/exploration_policies/index.rst","components/filters/index.rst","components/filters/input_filters.rst","components/filters/output_filters.rst","components/memories/index.rst","components/memory_backends/index.rst","components/orchestrators/index.rst","components/spaces.rst","contributing/add_agent.rst","contributing/add_env.rst","dashboard.rst","design/control_flow.rst","design/horizontal_scaling.rst","design/network.rst","dist_usage.rst","features/algorithms.rst","features/benchmarks.rst","features/environments.rst","features/index.rst","index.rst","selecting_an_algorithm.rst","test.rst","usage.rst"],objects:{"rl_coach.agents.actor_critic_agent":{ActorCriticAlgorithmParameters:[5,0,1,""]},"rl_coach.agents.agent":{Agent:[3,0,1,""]},"rl_coach.agents.agent.Agent":{act:[3,1,1,""],call_memory:[3,1,1,""],choose_action:[3,1,1,""],collect_savers:[3,1,1,""],create_networks:[3,1,1,""],emulate_act_on_trainer:[3,1,1,""],emulate_observe_on_trainer:[3,1,1,""],get_predictions:[3,1,1,""],get_state_embedding:[3,1,1,""],handle_episode_ended:[3,1,1,""],init_environment_dependent_modules:[3,1,1,""],learn_from_batch:[3,1,1,""],log_to_screen:[3,1,1,""],observe:[3,1,1,""],parent:[3,2,1,""],phase:[3,2,1,""],post_training_commands:[3,1,1,""],prepare_batch_for_inference:[3,1,1,""],register_signal:[3,1,1,""],reset_evaluation_state:[3,1,1,""],reset_internal_state:[3,1,1,""],restore_checkpoint:[3,1,1,""],run_pre_network_filter_for_inference:[3,1,1,""],save_checkpoint:[3,1,1,""],set_environment_parameters:[3,1,1,""],set_incoming_directive:[3,1,1,""],set_session:[3,1,1,""],setup_logger:[3,1,1,""],sync:[3,1,1,""],train:[3,1,1,""],update_log:[3,1,1,""],update_step_in_episode_log:[3,1,1,""],update_transition_before_adding_to_replay_buffer:[3,1,1,""]},"rl_coach.agents.bc_agent":{BCAlgorithmParameters:[1,0,1,""]},"rl_coach.agents.categorical_dqn_agent":{CLine truncated
|
||||
Search.setIndex({docnames:["components/additional_parameters","components/agents/imitation/bc","components/agents/imitation/cil","components/agents/index","components/agents/other/dfp","components/agents/policy_optimization/ac","components/agents/policy_optimization/cppo","components/agents/policy_optimization/ddpg","components/agents/policy_optimization/hac","components/agents/policy_optimization/pg","components/agents/policy_optimization/ppo","components/agents/value_optimization/bs_dqn","components/agents/value_optimization/categorical_dqn","components/agents/value_optimization/double_dqn","components/agents/value_optimization/dqn","components/agents/value_optimization/dueling_dqn","components/agents/value_optimization/mmc","components/agents/value_optimization/n_step","components/agents/value_optimization/naf","components/agents/value_optimization/nec","components/agents/value_optimization/pal","components/agents/value_optimization/qr_dqn","components/agents/value_optimization/rainbow","components/architectures/index","components/core_types","components/data_stores/index","components/environments/index","components/exploration_policies/index","components/filters/index","components/filters/input_filters","components/filters/output_filters","components/memories/index","components/memory_backends/index","components/orchestrators/index","components/spaces","contributing/add_agent","contributing/add_env","dashboard","design/control_flow","design/horizontal_scaling","design/network","dist_usage","features/algorithms","features/benchmarks","features/environments","features/index","index","selecting_an_algorithm","test","usage"],envversion:{"sphinx.domains.c":1,"sphinx.domains.changeset":1,"sphinx.domains.cpp":1,"sphinx.domains.javascript":1,"sphinx.domains.math":2,"sphinx.domains.python":1,"sphinx.domains.rst":1,"sphinx.domains.std":1,"sphinx.ext.todo":1,"sphinx.ext.viewcode":1,sphinx:55},filenames:["components/additional_parameters.rst","components/agents/imitation/bc.rst","components/agents/imitation/cil.rst","components/agents/index.rst","components/agents/other/dfp.rst","components/agents/policy_optimization/ac.rst","components/agents/policy_optimization/cppo.rst","components/agents/policy_optimization/ddpg.rst","components/agents/policy_optimization/hac.rst","components/agents/policy_optimization/pg.rst","components/agents/policy_optimization/ppo.rst","components/agents/value_optimization/bs_dqn.rst","components/agents/value_optimization/categorical_dqn.rst","components/agents/value_optimization/double_dqn.rst","components/agents/value_optimization/dqn.rst","components/agents/value_optimization/dueling_dqn.rst","components/agents/value_optimization/mmc.rst","components/agents/value_optimization/n_step.rst","components/agents/value_optimization/naf.rst","components/agents/value_optimization/nec.rst","components/agents/value_optimization/pal.rst","components/agents/value_optimization/qr_dqn.rst","components/agents/value_optimization/rainbow.rst","components/architectures/index.rst","components/core_types.rst","components/data_stores/index.rst","components/environments/index.rst","components/exploration_policies/index.rst","components/filters/index.rst","components/filters/input_filters.rst","components/filters/output_filters.rst","components/memories/index.rst","components/memory_backends/index.rst","components/orchestrators/index.rst","components/spaces.rst","contributing/add_agent.rst","contributing/add_env.rst","dashboard.rst","design/control_flow.rst","design/horizontal_scaling.rst","design/network.rst","dist_usage.rst","features/algorithms.rst","features/benchmarks.rst","features/environments.rst","features/index.rst","index.rst","selecting_an_algorithm.rst","test.rst","usage.rst"],objects:{"rl_coach.agents.actor_critic_agent":{ActorCriticAlgorithmParameters:[5,0,1,""]},"rl_coach.agents.agent":{Agent:[3,0,1,""]},"rl_coach.agents.agent.Agent":{act:[3,1,1,""],call_memory:[3,1,1,""],choose_action:[3,1,1,""],collect_savers:[3,1,1,""],create_networks:[3,1,1,""],emulate_act_on_trainer:[3,1,1,""],emulate_observe_on_trainer:[3,1,1,""],get_predictions:[3,1,1,""],get_state_embedding:[3,1,1,""],handle_episode_ended:[3,1,1,""],init_environment_dependent_modules:[3,1,1,""],learn_from_batch:[3,1,1,""],log_to_screen:[3,1,1,""],observe:[3,1,1,""],parent:[3,2,1,""],phase:[3,2,1,""],post_training_commands:[3,1,1,""],prepare_batch_for_inference:[3,1,1,""],register_signal:[3,1,1,""],reset_evaluation_state:[3,1,1,""],reset_internal_state:[3,1,1,""],restore_checkpoint:[3,1,1,""],run_pre_network_filter_for_inference:[3,1,1,""],save_checkpoint:[3,1,1,""],set_environment_parameters:[3,1,1,""],set_incoming_directive:[3,1,1,""],set_session:[3,1,1,""],setup_logger:[3,1,1,""],sync:[3,1,1,""],train:[3,1,1,""],update_log:[3,1,1,""],update_step_in_episode_log:[3,1,1,""],update_transition_before_adding_to_replay_buffer:[3,1,1,""]},"rl_coach.agents.bc_agent":{BCAlgorithmParameters:[1,0,1,""]},"rl_coach.agents.categorical_dqn_agent":{CLine truncated
|
||||
+2
-2
@@ -292,7 +292,7 @@ When working with single-threaded algorithms, the rendered image will be represe
|
||||
Keep in mind that rendering the environment in single-threaded algorithms may slow the training to some extent.
|
||||
When playing with the environment using the <code class="code docutils literal notranslate"><span class="pre">--play</span></code> flag, the environment will be rendered automatically without the need for specifying the <code class="code docutils literal notranslate"><span class="pre">-r</span></code> flag.</p>
|
||||
<p><em>Example:</em></p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">coach</span> <span class="o">-</span><span class="n">p</span> <span class="n">Breakout_DQN</span> <span class="o">-</span><span class="n">r</span>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">coach</span> <span class="o">-</span><span class="n">p</span> <span class="n">Atari_DQN</span> <span class="o">-</span><span class="n">lvl</span> <span class="n">breakout</span> <span class="o">-</span><span class="n">r</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -302,7 +302,7 @@ When playing with the environment using the <code class="code docutils literal n
|
||||
To dump GIF files, use the <code class="code docutils literal notranslate"><span class="pre">-dg</span></code> flag.
|
||||
The files are dumped after every evaluation episode, and are saved into the experiment directory, under a gifs sub-directory.</p>
|
||||
<p><em>Example:</em></p>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">coach</span> <span class="o">-</span><span class="n">p</span> <span class="n">Breakout_A3C</span> <span class="o">-</span><span class="n">n</span> <span class="mi">4</span> <span class="o">-</span><span class="n">dg</span>
|
||||
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">coach</span> <span class="o">-</span><span class="n">p</span> <span class="n">Atari_A3C</span> <span class="o">-</span><span class="n">lvl</span> <span class="n">breakout</span> <span class="o">-</span><span class="n">n</span> <span class="mi">4</span> <span class="o">-</span><span class="n">dg</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
Reference in new issue
Block a user