| .. |
|
documentation
|
[RLlib; Documentation] RLlib README overhaul. (#20249)
|
2021-11-18 18:08:40 +01:00 |
|
env
|
[RLlib] QMIX better defaults + added to CI learning tests (#21332)
|
2022-01-04 08:54:41 +01:00 |
|
export
|
[RLlib] Experimental no-flatten option for actions/prev-actions. (#20918)
|
2021-12-11 14:57:58 +01:00 |
|
inference_and_serving
|
[RLlib] Issue 20062: Action inference examples missing (#20144)
|
2021-11-10 18:49:06 +01:00 |
|
models
|
[RLlib] Use SampleBrach instead of input dict whenever possible (#20746)
|
2021-12-02 13:11:26 +01:00 |
|
policy
|
[RLlib] Switch off preprocessors by default for PGTrainer. (#21008)
|
2021-12-13 12:04:23 +01:00 |
|
serving
|
[RLlib] Issue 18668: Unity3D env client/server example not working (fix + add to test cases). (#18942)
|
2021-09-30 08:30:20 +02:00 |
|
simulators/sumo
|
[RLlib] Integration with SUMO Simulator (#11710)
|
2020-11-03 09:45:03 +01:00 |
|
tune
|
[Release] Refactor User Tests (#20028)
|
2021-11-05 17:28:37 -07:00 |
|
__init__.py
|
[rllib] Try moving RLlib to top level dir (#5324)
|
2019-08-05 23:25:49 -07:00 |
|
action_masking.py
|
[RLlib] Document and extend action mask example. (#20390)
|
2021-11-16 13:20:41 +01:00 |
|
attention_net.py
|
Revert "Revert [RLlib] POC: Deprecate build_policy (policy template) for torch only; PPOTorchPolicy (#20061) (#20399)" (#20417)
|
2021-11-16 14:49:41 +01:00 |
|
attention_net_supervised.py
|
[RLlib] Support easy use_attention=True flag for using the GTrXL model. (#11698)
|
2021-01-01 14:06:23 -05:00 |
|
autoregressive_action_dist.py
|
[RLlib] Better example scripts: Description --no-tune and --local-mode CLI options (autoregressive_action_dist.py) (#17705)
|
2021-08-16 22:08:13 +02:00 |
|
bare_metal_policy_with_custom_view_reqs.py
|
[RLlib] Upgrade gym version to 0.21 and deprecate pendulum-v0. (#19535)
|
2021-11-03 16:24:00 +01:00 |
|
batch_norm_model.py
|
[RLlib] Upgrade gym version to 0.21 and deprecate pendulum-v0. (#19535)
|
2021-11-03 16:24:00 +01:00 |
|
cartpole_lstm.py
|
[RLlib] CQL BC loss fixes; PPO/PG/A2|3C action normalization fixes (#16531)
|
2021-06-30 12:32:11 +02:00 |
|
centralized_critic.py
|
[RLlib] Trainer sub-class PPO/DDPPO (instead of build_trainer()). (#20571)
|
2021-11-23 23:01:05 +01:00 |
|
centralized_critic_2.py
|
[RLlib] Re-do: Trainer: Support add and delete Policies. (#16569)
|
2021-06-21 13:46:01 +02:00 |
|
checkpoint_by_custom_criteria.py
|
[RLlib] Examples scripts add argparse help and replace --torch with --framework. (#15832)
|
2021-05-18 13:18:12 +02:00 |
|
coin_game_env.py
|
[RLlib] Re-do: Trainer: Support add and delete Policies. (#16569)
|
2021-06-21 13:46:01 +02:00 |
|
complex_struct_space.py
|
[RLlib] Switch off preprocessors by default for PGTrainer. (#21008)
|
2021-12-13 12:04:23 +01:00 |
|
compute_adapted_gae_on_postprocess_trajectory.py
|
[RLlib] Example containing a proposal for computing an adapted (time-dependent) GAE used by the PPO algorithm (via callback on_postprocess_trajectory) (#20850)
|
2021-12-09 14:48:56 +01:00 |
|
curriculum_learning.py
|
[RLlib] Add simple curriculum learning API and example script. (#15740)
|
2021-05-16 17:35:10 +02:00 |
|
custom_env.py
|
[RLlib Testig] Split and unflake more CI tests (make sure all jobs are < 30min). (#18591)
|
2021-09-15 22:16:48 +02:00 |
|
custom_eval.py
|
[RLlib] Allow for evaluation to run by timesteps (alternative to episodes) and add auto-setting to make sure train doesn't ever have to wait for eval (e.g. long episodes) to finish. (#20757)
|
2021-12-04 13:26:33 +01:00 |
|
custom_experiment.py
|
[RLlib] CQL BC loss fixes; PPO/PG/A2|3C action normalization fixes (#16531)
|
2021-06-30 12:32:11 +02:00 |
|
custom_fast_model.py
|
[RLlib] Refactor: All tf static graph code should reside inside Policy class. (#17169)
|
2021-07-20 14:58:13 -04:00 |
|
custom_input_api.py
|
[RLlib] Rename metrics_smoothing_episodes into metrics_num_episodes_for_smoothing for clarity. (#20983)
|
2021-12-11 20:33:35 +01:00 |
|
custom_keras_model.py
|
[RLlib] Unify all RLlib Trainer.train() -> results[info][learner][policy ID][learner_stats] and add structure tests. (#18879)
|
2021-09-30 16:39:05 +02:00 |
|
custom_logger.py
|
[RLlib] Upgrade gym version to 0.21 and deprecate pendulum-v0. (#19535)
|
2021-11-03 16:24:00 +01:00 |
|
custom_loss.py
|
[RLlib] Fix ModelV2 custom metrics for torch. (#16734)
|
2021-07-01 13:01:40 +02:00 |
|
custom_metrics_and_callbacks.py
|
[RLlib; Docs overhaul] Docstring cleanup: Evaluation (#19783)
|
2021-10-29 12:03:56 +02:00 |
|
custom_metrics_and_callbacks_legacy.py
|
[RLlib] Fix all example scripts to run on GPUs. (#11105)
|
2020-10-02 23:07:44 +02:00 |
|
custom_model_api.py
|
[RLlib] Use SampleBrach instead of input dict whenever possible (#20746)
|
2021-12-02 13:11:26 +01:00 |
|
custom_model_loss_and_metrics.py
|
[RLlib] Unify all RLlib Trainer.train() -> results[info][learner][policy ID][learner_stats] and add structure tests. (#18879)
|
2021-09-30 16:39:05 +02:00 |
|
custom_observation_filters.py
|
[RLlib] No Preprocessors; preparatory PR #1 (#18367)
|
2021-09-09 08:10:42 +02:00 |
|
custom_rnn_model.py
|
[RLlib] CQL BC loss fixes; PPO/PG/A2|3C action normalization fixes (#16531)
|
2021-06-30 12:32:11 +02:00 |
|
custom_tf_policy.py
|
[RLlib] Fix failing test cases: Soft-deprecate ModelV2.from_batch (in favor of ModelV2.__call__). (#19693)
|
2021-10-25 15:00:00 +02:00 |
|
custom_torch_policy.py
|
[RLlib] JAXPolicy prep. PR #1. (#13077)
|
2020-12-26 20:14:18 -05:00 |
|
custom_train_fn.py
|
[RLlib Testig] Split and unflake more CI tests (make sure all jobs are < 30min). (#18591)
|
2021-09-15 22:16:48 +02:00 |
|
custom_vector_env.py
|
[RLlib] Discussion 2294: Custom vector env example and fix. (#16083)
|
2021-07-28 10:40:04 -04:00 |
|
deterministic_training.py
|
[rllib] Add deterministic test to gpu (#19306)
|
2021-10-26 10:11:39 -07:00 |
|
dmlab_watermaze.py
|
Remove future imports (#6724)
|
2020-01-09 00:15:48 -08:00 |
|
eager_execution.py
|
[RLlib] Fix failing test cases: Soft-deprecate ModelV2.from_batch (in favor of ModelV2.__call__). (#19693)
|
2021-10-25 15:00:00 +02:00 |
|
env_rendering_and_recording.py
|
[RLlib] Allow for evaluation to run by timesteps (alternative to episodes) and add auto-setting to make sure train doesn't ever have to wait for eval (e.g. long episodes) to finish. (#20757)
|
2021-12-04 13:26:33 +01:00 |
|
fractional_gpus.py
|
[RLlib] Fix ModelV2 custom metrics for torch. (#16734)
|
2021-07-01 13:01:40 +02:00 |
|
hierarchical_training.py
|
[RLlib] Add worker arg (optional) to policy_mapping_fn. (#18184)
|
2021-09-17 12:07:11 +02:00 |
|
iterated_prisoners_dilemma_env.py
|
[RLlib] Re-do: Trainer: Support add and delete Policies. (#16569)
|
2021-06-21 13:46:01 +02:00 |
|
lstm_auto_wrapping.py
|
[RLlib] Preparatory PR for: Documentation on Model Building. (#13260)
|
2021-01-08 10:56:09 +01:00 |
|
mobilenet_v2_with_lstm.py
|
[RLlib] Examples scripts add argparse help and replace --torch with --framework. (#15832)
|
2021-05-18 13:18:12 +02:00 |
|
multi_agent_cartpole.py
|
[RLlib] Add worker arg (optional) to policy_mapping_fn. (#18184)
|
2021-09-17 12:07:11 +02:00 |
|
multi_agent_custom_policy.py
|
[RLlib] Redo simplify multi agent config dict: Reverted b/c seemed to break test_typing (non RLlib test). (#17046)
|
2021-07-15 05:51:24 -04:00 |
|
multi_agent_independent_learning.py
|
[RLlib] Revert "Revert "updated pettingzoo wrappers, env versions, urls"" (#21339)
|
2022-01-04 18:30:26 +01:00 |
|
multi_agent_parameter_sharing.py
|
[RLlib] Revert "Revert "updated pettingzoo wrappers, env versions, urls"" (#21339)
|
2022-01-04 18:30:26 +01:00 |
|
multi_agent_two_trainers.py
|
[RLlib] Add worker arg (optional) to policy_mapping_fn. (#18184)
|
2021-09-17 12:07:11 +02:00 |
|
nested_action_spaces.py
|
[RLlib] Fix crash when using StochasticSampling exploration (most PG-style algos) w/ tf and numpy > 1.19.5 (#18366)
|
2021-09-06 12:14:00 +02:00 |
|
offline_rl.py
|
[RLlib] Allow for evaluation to run by timesteps (alternative to episodes) and add auto-setting to make sure train doesn't ever have to wait for eval (e.g. long episodes) to finish. (#20757)
|
2021-12-04 13:26:33 +01:00 |
|
parallel_evaluation_and_training.py
|
[RLlib] Allow for evaluation to run by timesteps (alternative to episodes) and add auto-setting to make sure train doesn't ever have to wait for eval (e.g. long episodes) to finish. (#20757)
|
2021-12-04 13:26:33 +01:00 |
|
parametric_actions_cartpole.py
|
[RLlib] Examples scripts add argparse help and replace --torch with --framework. (#15832)
|
2021-05-18 13:18:12 +02:00 |
|
parametric_actions_cartpole_embeddings_learnt_by_model.py
|
[RLlib] New and changed version of parametric actions cartpole example + small suggested update in policy_client.py (#15664)
|
2021-07-28 15:25:09 -04:00 |
|
partial_gpus.py
|
[RLlib] Fix ModelV2 custom metrics for torch. (#16734)
|
2021-07-01 13:01:40 +02:00 |
|
preprocessing_disabled.py
|
[RLlib] No Preprocessors (part 2). (#18468)
|
2021-09-23 12:56:45 +02:00 |
|
random_parametric_agent.py
|
[RLlib] Unify the way we create local replay buffer for all agents (#19627)
|
2021-10-26 20:56:02 +02:00 |
|
re3_exploration.py
|
[RLlib] Support for RE3 exploration algorithm (for tf) (#19551)
|
2021-12-07 13:26:34 +01:00 |
|
recsim_with_slateq.py
|
[RLlib] Examples scripts add argparse help and replace --torch with --framework. (#15832)
|
2021-05-18 13:18:12 +02:00 |
|
remote_base_env_with_custom_api.py
|
[RLlib] Update a few things to get rid of the remote_vector_env deprecation warning. (#20753)
|
2021-12-02 13:10:44 +01:00 |
|
remote_envs_with_inference_done_on_main_node.py
|
[RLlib] Trainer sub-class PPO/DDPPO (instead of build_trainer()). (#20571)
|
2021-11-23 23:01:05 +01:00 |
|
restore_1_of_n_agents_from_checkpoint.py
|
[RLlib] Add worker arg (optional) to policy_mapping_fn. (#18184)
|
2021-09-17 12:07:11 +02:00 |
|
rnnsac_stateless_cartpole.py
|
[RLlib] Add RNN-SAC agent (#16577)
|
2021-07-25 10:04:52 -04:00 |
|
rock_paper_scissors_multiagent.py
|
[RLlib] POC: Run PGTrainer w/o the distr. exec API (Trainer's new training_iteration method). (#20984)
|
2021-12-21 08:39:05 +01:00 |
|
rollout_worker_custom_workflow.py
|
[Tune] Remove legacy resources implementations in Runner and Executor. (#19773)
|
2021-11-12 12:33:39 -08:00 |
|
saving_experiences.py
|
[Core] First pass at privatizing non-public Python APIs. (#14607)
|
2021-03-10 22:47:28 -08:00 |
|
sb2rllib_rllib_example.py
|
[RLlib] Better example scripts: Description --no-tune and --local-mode CLI options (#17038)
|
2021-07-26 22:25:48 -04:00 |
|
sb2rllib_sb_example.py
|
[RLlib] Examples for training, saving, loading, testing an agent with SB & RLlib (#15897)
|
2021-05-19 16:36:59 +02:00 |
|
self_play_league_based_with_open_spiel.py
|
[RLlib] Add worker arg (optional) to policy_mapping_fn. (#18184)
|
2021-09-17 12:07:11 +02:00 |
|
self_play_with_open_spiel.py
|
[RLlib] Add worker arg (optional) to policy_mapping_fn. (#18184)
|
2021-09-17 12:07:11 +02:00 |
|
sumo_env_local.py
|
[RLlib] Re-do: Trainer: Support add and delete Policies. (#16569)
|
2021-06-21 13:46:01 +02:00 |
|
trajectory_view_api.py
|
[RLlib] Custom view requirements (e.g. for prev-n-obs) work with compute_single_action and compute_actions_from_input_dict. (#18921)
|
2021-09-30 15:03:37 +02:00 |
|
two_step_game.py
|
[RLlib] QMIX better defaults + added to CI learning tests (#21332)
|
2022-01-04 08:54:41 +01:00 |
|
two_trainer_workflow.py
|
[RLlib] Replay buffer API (cleanups; docstrings; renames; move into rllib/execution/buffers dir) (#20552)
|
2021-11-19 11:57:37 +01:00 |
|
unity3d_env_local.py
|
[RLlib] Examples scripts add argparse help and replace --torch with --framework. (#15832)
|
2021-05-18 13:18:12 +02:00 |
|
vizdoom_with_attention_net.py
|
[RLlib] Examples scripts add argparse help and replace --torch with --framework. (#15832)
|
2021-05-18 13:18:12 +02:00 |
