mirror of
https://github.com/wassname/ray.git
synced 2026-07-27 11:26:41 +08:00
Eric LiangandGitHub
9ea57c2a93
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.
4 lines
116 B
Python
4 lines
116 B
Python
from ray.rllib.agents.impala.impala import ImpalaAgent, DEFAULT_CONFIG
|
|
|
|
__all__ = ["ImpalaAgent", "DEFAULT_CONFIG"]
|