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
..
tests	[RLlib] Redo fix bug normalize vs unsquash actions (original PR made log-likelihood test flakey). (#17014)	2021-07-13 14:01:30 -04:00
__init__.py	[RLlib] JAXPolicy prep. PR #1. (#13077)	2020-12-26 20:14:18 -05:00
dynamic_tf_policy.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
eager_tf_policy.py	[RLlib] Refactor: All tf static graph code should reside inside Policy class. (#17169)	2021-07-20 14:58:13 -04:00
policy.py	[RLlib] Discussion 3001: Fix comment on internal state shape (must be [B x S=state dim]). (#17341)	2021-07-27 21:41:53 -04:00
policy_map.py	[RLlib] Implement policy_maps (multi-agent case) in RolloutWorkers as LRU caches. (#17031)	2021-07-19 13:16:03 -04:00
policy_template.py	[RLlib] CQL loss fn fixes, MuJoCo + Pendulum benchmarks, offline-RL example script w/ json file. (#15603)	2021-05-04 19:06:19 +02:00
rnn_sequencing.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
sample_batch.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
tf_policy.py	[RLlib] Issues: 17397, 17425, 16715, 17174. When on driver, Torch|TFPolicy should not use ray.get_gpu_ids() (b/c no GPUs assigned by ray). (#17444)	2021-08-02 17:29:59 -04:00
tf_policy_template.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
torch_policy.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
torch_policy_template.py	[RLlib] CQL loss fn fixes, MuJoCo + Pendulum benchmarks, offline-RL example script w/ json file. (#15603)	2021-05-04 19:06:19 +02:00
view_requirement.py	[RLlib] Remove all non-trajectory view API code. (#14860)	2021-03-23 09:50:18 -07:00