ray/rllib/agents/impala/__init__.py

from ray.rllib.agents.impala.impala import DEFAULT_CONFIG, ImpalaConfig, ImpalaTrainer

__all__ = [
    "ImpalaConfig",
    "ImpalaTrainer",
    "DEFAULT_CONFIG",
]
Revert "[RLlib] Move (A/DD)?PPO and IMPALA algos to `algorithms` dir and rename policy and trainer classes. (#25346)" (#25420) This reverts commit e4ceae19ef60f135a253fdd9f1270720bdbd96ec. Reverts #25346 linux://python/ray/tests:test_client_library_integration never fail before this PR. In the CI of the reverted PR, it also fails (https://buildkite.com/ray-project/ray-builders-pr/builds/34079#01812442-c541-4145-af22-2a012655c128). So high likely it's because of this PR. And test output failure seems related as well (https://buildkite.com/ray-project/ray-builders-branch/builds/7923#018125c2-4812-4ead-a42f-7fddb344105b) 2022-06-03 03:38:44 +00:00			`from ray.rllib.agents.impala.impala import DEFAULT_CONFIG, ImpalaConfig, ImpalaTrainer`
[rllib] Basic IMPALA implementation (using deepmind's reference vtrace.py) (#2504) Rename AsyncSamplesOptimizer -> AsyncReplayOptimizer Add AsyncSamplesOptimizer that implements the IMPALA architecture integrate V-trace with a3c policy graph audit V-trace integration benchmark compare vs A3C and with V-trace on/off PongNoFrameskip-v4 on IMPALA scaling from 16 to 128 workers, solving Pong in <10 min. For reference, solving this env takes ~40 minutes for Ape-X and several hours for A3C. 2018-08-01 20:53:53 -07:00
[RLlib] Trainer sub-class IMPALA (instead of using `build_trainer()`). (#20570) 2021-11-30 19:08:36 +01:00			`__all__ = [`
[RLlib] IMPALA TrainerConfig objects. (#24375) 2022-05-02 12:05:30 +02:00			`"ImpalaConfig",`
[RLlib] Trainer sub-class IMPALA (instead of using `build_trainer()`). (#20570) 2021-11-30 19:08:36 +01:00			`"ImpalaTrainer",`
[RLlib] IMPALA TrainerConfig objects. (#24375) 2022-05-02 12:05:30 +02:00			`"DEFAULT_CONFIG",`
[RLlib] Trainer sub-class IMPALA (instead of using `build_trainer()`). (#20570) 2021-11-30 19:08:36 +01:00			`]`