.. |
data
|
53206dd440
[RLlib] CQL BC loss fixes; PPO/PG/A2|3C action normalization fixes (#16531)
|
3 年之前 |
git_bisect
|
5cee8a1985
[release tests] Switch from yaml.load to yaml.safe_load (#19365)
|
3 年之前 |
__init__.py
|
5d7afe8092
[rllib] Try moving RLlib to top level dir (#5324)
|
5 年之前 |
conftest.py
|
31b40b00f6
[rllib] Pull out experimental dsl into rllib.execution module, add initial unit tests (#7958)
|
4 年之前 |
mock_worker.py
|
2e60f0d4d8
[RLlib] Move all jenkins RLlib-tests into bazel (rllib/BUILD). (#7178)
|
4 年之前 |
run_regression_tests.py
|
2d24ef0d32
[RLlib] Add all simple learning tests as `framework=tf2`. (#19273)
|
3 年之前 |
test_attention_net_learning.py
|
e973b726c2
[RLlib] Support native tf.keras.Models (part 2) - Default keras models for Vision/RNN/Attention. (#15273)
|
3 年之前 |
test_catalog.py
|
4bc257f4fb
[RLlib] Fix custom multi action distr (#13681)
|
3 年之前 |
test_checkpoint_restore.py
|
026bf01071
[RLlib] Upgrade gym version to 0.21 and deprecate pendulum-v0. (#19535)
|
3 年之前 |
test_dependency_tf.py
|
354c960fff
[RLlib] Fix test_dependency_torch and fix custom logger support for RLlib. (#15120)
|
3 年之前 |
test_dependency_torch.py
|
44d209dd5f
[tune] re-enable tensorboardx without torch installed (#17403)
|
3 年之前 |
test_dnc.py
|
fba8461663
[RLlib] Add RNN-SAC agent (#16577)
|
3 年之前 |
test_eager_support.py
|
026bf01071
[RLlib] Upgrade gym version to 0.21 and deprecate pendulum-v0. (#19535)
|
3 年之前 |
test_env_with_subprocess.py
|
d958457d07
[Core] Second pass at privatizing APIs. (#17885)
|
3 年之前 |
test_exec_api.py
|
ed85f59194
[RLlib] Unify all RLlib Trainer.train() -> results[info][learner][policy ID][learner_stats] and add structure tests. (#18879)
|
3 年之前 |
test_execution.py
|
89fbfc00f8
[RLlib] Some minor cleanups (buffer buffer_size -> capacity and others). (#19623)
|
3 年之前 |
test_export.py
|
026bf01071
[RLlib] Upgrade gym version to 0.21 and deprecate pendulum-v0. (#19535)
|
3 年之前 |
test_external_env.py
|
e40b14d255
[RLlib] Batch-size for truncate_episode batch_mode should be confgurable in agent-steps (rather than env-steps), if needed. (#12420)
|
3 年之前 |
test_external_multi_agent_env.py
|
494ddd98c1
[RLlib] Replace "seq_lens" w/ SampleBatch.SEQ_LENS. (#17928)
|
3 年之前 |
test_filters.py
|
2746fc0476
[RLlib] Auto-framework, retire `use_pytorch` in favor of `framework=...` (#8520)
|
4 年之前 |
test_gpus.py
|
3f89f35e52
[RLlib] Better error messages and hints; + failure-mode tests; (#18466)
|
3 年之前 |
test_ignore_worker_failure.py
|
246787cdd9
Revert "[RLlib] POC: `PGTrainer` class that works by sub-classing, not `trainer_template.py`. (#20055)" (#20284)
|
2 年之前 |
test_io.py
|
649580d735
[RLlib] Redo simplify multi agent config dict: Reverted b/c seemed to break test_typing (non RLlib test). (#17046)
|
3 年之前 |
test_local.py
|
d9f1874e34
[RLlib] Minor fixes (torch GPU bugs + some cleanup). (#11609)
|
4 年之前 |
test_lstm.py
|
f3397b6f48
[RLlib] Minor fixes/cleanups; chop_into_sequences now handles nested data. (#19408)
|
3 年之前 |
test_model_imports.py
|
91d01f7211
[RLlib](deps): Bump tensorflow from 2.4.1 to 2.5.0 in /python/requirements/rllib (#15849)
|
3 年之前 |
test_multi_agent_env.py
|
9c73871da0
[RLlib; Docs overhaul] Docstring cleanup: Evaluation (#19783)
|
3 年之前 |
test_multi_agent_pendulum.py
|
d9f1874e34
[RLlib] Minor fixes (torch GPU bugs + some cleanup). (#11609)
|
4 年之前 |
test_nested_observation_spaces.py
|
902e854af2
[RLlib; Docs overhaul] Docstring cleanup: Environments. (#19784)
|
3 年之前 |
test_perf.py
|
e40b14d255
[RLlib] Batch-size for truncate_episode batch_mode should be confgurable in agent-steps (rather than env-steps), if needed. (#12420)
|
3 年之前 |
test_pettingzoo_env.py
|
3e010c5760
[rllib] bug fix for rllib pettingzoo pistonball_v4 example (#17701)
|
3 年之前 |
test_placement_groups.py
|
246787cdd9
Revert "[RLlib] POC: `PGTrainer` class that works by sub-classing, not `trainer_template.py`. (#20055)" (#20284)
|
2 年之前 |
test_ray_client.py
|
8a72824c63
[RLlib Testig] Split and unflake more CI tests (make sure all jobs are < 30min). (#18591)
|
3 年之前 |
test_reproducibility.py
|
2746fc0476
[RLlib] Auto-framework, retire `use_pytorch` in favor of `framework=...` (#8520)
|
4 年之前 |
test_rllib_train_and_evaluate.py
|
026bf01071
[RLlib] Upgrade gym version to 0.21 and deprecate pendulum-v0. (#19535)
|
3 年之前 |
test_supported_multi_agent.py
|
c3e3fc7637
[RLlib] Issue 18280: A3C/IMPALA multi-agent not working. (#19100)
|
3 年之前 |
test_supported_spaces.py
|
f3397b6f48
[RLlib] Minor fixes/cleanups; chop_into_sequences now handles nested data. (#19408)
|
3 年之前 |
test_timesteps.py
|
53206dd440
[RLlib] CQL BC loss fixes; PPO/PG/A2|3C action normalization fixes (#16531)
|
3 年之前 |
test_vector_env.py
|
902e854af2
[RLlib; Docs overhaul] Docstring cleanup: Environments. (#19784)
|
3 年之前 |