ray/rllib/agents/impala/__init__.py

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

__all__ = [
    "DEFAULT_CONFIG",
    "ImpalaTrainer",
]
[RLlib] Trainer sub-class IMPALA (instead of using `build_trainer()`). (#20570) 2021-11-30 19:08:36 +01:00			`from ray.rllib.agents.impala.impala import DEFAULT_CONFIG, 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__ = [`
			`"DEFAULT_CONFIG",`
			`"ImpalaTrainer",`
			`]`