Sven MikaandGitHub 20ef4a8603 [RLlib] Cleanup/unify all test cases. (#7533)

2020-03-11 20:39:47 -07:00

..

tests

[RLlib] Cleanup/unify all test cases. (#7533)

2020-03-11 20:39:47 -07:00

__init__.py

[rllib] Add Decentralized DDPPO trainer and documentation (#7088)

2020-02-10 15:28:27 -08:00

appo_policy.py

[rllib] implemented compute_advantages without gae (#6941)

2020-01-31 22:25:45 -08:00

appo.py

[rllib] implemented compute_advantages without gae (#6941)

2020-01-31 22:25:45 -08:00

ddppo.py

[rllib] Add Decentralized DDPPO trainer and documentation (#7088)

2020-02-10 15:28:27 -08:00

ppo_tf_policy.py

[RLlib] Implement PPO torch version. (#6826)

2020-01-20 23:06:50 -08:00

ppo_torch_policy.py

Fix issue with torch PPO not handling action spaces of shape=(>1,). (#7398)

2020-03-02 10:53:19 -08:00

ppo.py

[RLlib] PPO torch memory leak and unnecessary torch.Tensor creation and gc'ing. (#7238)

2020-02-22 11:02:31 -08:00

utils.py

Remove future imports (#6724)

2020-01-09 00:15:48 -08:00