Sven Mika 924f11cd45 [RLlib] Torch algos use now-framework-agnostic MultiGPUTrainOneStep execution op (~33% speedup for PPO-torch + GPU). (#17371)		2021-08-03 11:35:49 -04:00
..
test_appo.py	[RLlib] Attention Net prep PR #1: Smaller cleanups. (#12447)	2020-11-27 16:25:47 -08:00
test_ddppo.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_ppo.py	[RLlib] Torch algos use now-framework-agnostic MultiGPUTrainOneStep execution op (~33% speedup for PPO-torch + GPU). (#17371)	2021-08-03 11:35:49 -04:00