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_apex_dqn.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
test_dqn.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
test_r2d2.py	[RLlib] Support native tf.keras.Models (part 2) - Default keras models for Vision/RNN/Attention. (#15273)	2021-04-30 19:26:30 +02:00
test_simple_q.py	[RLlib] Refactor: All tf static graph code should reside inside Policy class. (#17169)	2021-07-20 14:58:13 -04:00