WanXing Wang 72bd2d7e09 [Core] Support back pressure for actor tasks. (#20894) ... Resubmit the PR https://github.com/ray-project/ray/pull/19936 I've figure out that the test case `//rllib:tests/test_gpus::test_gpus_in_local_mode` failed due to deadlock in local mode. In local mode, if the user code submits another task during the executing of current task, the `CoreWorker::actor_task_mutex_` may cause deadlock. The solution is quite simple, release the lock before executing task in local mode. In the commit 7c2f61c76c: 1. Release the lock in local mode to fix the bug. @scv119 2. `test_local_mode_deadlock` added to cover the case. @rkooo567 3. Left a trivial change in `rllib/tests/test_gpus.py` to make the `RAY_CI_RLLIB_DIRECTLY_AFFECTED ` to take effect.		2021-12-13 23:56:07 -08:00
..
data	[RLlib] CQL BC loss fixes; PPO/PG/A2|3C action normalization fixes (#16531)	2021-06-30 12:32:11 +02:00
git_bisect	[release tests] Switch from yaml.load to yaml.safe_load (#19365)	2021-10-13 17:27:25 -07:00
__init__.py	[rllib] Try moving RLlib to top level dir (#5324)	2019-08-05 23:25:49 -07:00
conftest.py	[rllib] Pull out experimental dsl into rllib.execution module, add initial unit tests (#7958)	2020-04-10 00:56:08 -07:00
mock_worker.py	[RLlib] Move all jenkins RLlib-tests into bazel (rllib/BUILD). (#7178)	2020-02-15 14:50:44 -08:00
run_regression_tests.py	[RLlib] Add all simple learning tests as framework=tf2. (#19273)	2021-11-02 12:10:17 +01:00
test_attention_net_learning.py	[RLlib] Support native tf.keras.Models (part 2) - Default keras models for Vision/RNN/Attention. (#15273)	2021-04-30 19:26:30 +02:00
test_catalog.py	[RLlib] Fix custom multi action distr (#13681)	2021-01-28 19:28:48 +01:00
test_checkpoint_restore.py	[RLlib] Upgrade gym version to 0.21 and deprecate pendulum-v0. (#19535)	2021-11-03 16:24:00 +01:00
test_dependency_tf.py	[RLlib] Fix test_dependency_torch and fix custom logger support for RLlib. (#15120)	2021-04-24 08:13:41 +02:00
test_dependency_torch.py	[tune] re-enable tensorboardx without torch installed (#17403)	2021-07-29 10:39:38 +01:00
test_dnc.py	[RLlib] Add RNN-SAC agent (#16577)	2021-07-25 10:04:52 -04:00
test_eager_support.py	[RLlib] Upgrade gym version to 0.21 and deprecate pendulum-v0. (#19535)	2021-11-03 16:24:00 +01:00
test_env_with_subprocess.py	[Core] Second pass at privatizing APIs. (#17885)	2021-08-18 20:56:33 -07:00
test_exec_api.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
test_execution.py	[RLlib] Rename metrics_smoothing_episodes into metrics_num_episodes_for_smoothing for clarity. (#20983)	2021-12-11 20:33:35 +01:00
test_export.py	[RLlib] Upgrade gym version to 0.21 and deprecate pendulum-v0. (#19535)	2021-11-03 16:24:00 +01:00
test_external_env.py	[RLlib] Batch-size for truncate_episode batch_mode should be confgurable in agent-steps (rather than env-steps), if needed. (#12420)	2020-12-08 16:41:45 -08:00
test_external_multi_agent_env.py	[RLlib] Replace "seq_lens" w/ SampleBatch.SEQ_LENS. (#17928)	2021-08-21 17:05:48 +02:00
test_filters.py	[RLlib] Switch off preprocessors by default for PGTrainer. (#21008)	2021-12-13 12:04:23 +01:00
test_gpus.py	[Core] Support back pressure for actor tasks. (#20894)	2021-12-13 23:56:07 -08:00
test_ignore_worker_failure.py	Revert "Revert [RLlib] POC: PGTrainer class that works by sub-classing, not trainer_template.py." (#20285)	2021-11-16 12:26:47 +01:00
test_io.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
test_local.py	[RLlib] Minor fixes (torch GPU bugs + some cleanup). (#11609)	2020-10-27 10:00:24 +01:00
test_lstm.py	[RLlib] Minor fixes/cleanups; chop_into_sequences now handles nested data. (#19408)	2021-11-05 14:39:28 +01:00
test_model_imports.py	[RLlib](deps): Bump tensorflow from 2.4.1 to 2.5.0 in /python/requirements/rllib (#15849)	2021-08-16 10:55:48 +02:00
test_multi_agent_env.py	[RLlib] Change return type of try_reset to MultiEnvDict (#20868)	2021-12-06 14:15:33 +01:00
test_multi_agent_pendulum.py	[RLlib] Minor fixes (torch GPU bugs + some cleanup). (#11609)	2020-10-27 10:00:24 +01:00
test_nested_action_spaces.py	[RLlib] Experimental no-flatten option for actions/prev-actions. (#20918)	2021-12-11 14:57:58 +01:00
test_nested_observation_spaces.py	[RLlib] Switch off preprocessors by default for PGTrainer. (#21008)	2021-12-13 12:04:23 +01:00
test_nn_framework_import_errors.py	Add error messages for missing tf and torch imports (#20205)	2021-11-16 16:30:53 -08:00
test_perf.py	[RLlib] Batch-size for truncate_episode batch_mode should be confgurable in agent-steps (rather than env-steps), if needed. (#12420)	2020-12-08 16:41:45 -08:00
test_pettingzoo_env.py	[RLlib] Trainer sub-class PPO/DDPPO (instead of build_trainer()). (#20571)	2021-11-23 23:01:05 +01:00
test_placement_groups.py	Revert "Revert [RLlib] POC: PGTrainer class that works by sub-classing, not trainer_template.py." (#20285)	2021-11-16 12:26:47 +01:00
test_ray_client.py	[RLlib Testig] Split and unflake more CI tests (make sure all jobs are < 30min). (#18591)	2021-09-15 22:16:48 +02:00
test_reproducibility.py	[RLlib] Auto-framework, retire use_pytorch in favor of framework=... (#8520)	2020-05-27 16:19:13 +02:00
test_rllib_train_and_evaluate.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
test_supported_multi_agent.py	[RLlib] Issue 18280: A3C/IMPALA multi-agent not working. (#19100)	2021-10-07 23:57:53 +02:00
test_supported_spaces.py	[RLlib] Switch off preprocessors by default for PGTrainer. (#21008)	2021-12-13 12:04:23 +01:00
test_timesteps.py	[RLlib] Switch off preprocessors by default for PGTrainer. (#21008)	2021-12-13 12:04:23 +01:00
test_vector_env.py	[RLlib; Docs overhaul] Docstring cleanup: Environments. (#19784)	2021-10-29 10:46:52 +02:00