wassname/ray

mirror of https://github.com/wassname/ray.git synced 2026-08-07 11:27:43 +08:00

Files

T

History

Sven MikaandGitHub d9f1874e34 [RLlib] Minor fixes (torch GPU bugs + some cleanup). (#11609 )

2020-10-27 10:00:24 +01:00

..

[RLlib] Minor fixes (torch GPU bugs + some cleanup). (#11609 )

2020-10-27 10:00:24 +01:00

__init__.py

[RLlib] SAC algo cleanup. (#10825 )

2020-09-20 11:27:02 +02:00

README.md

[RLlib] SAC algo cleanup. (#10825 )

2020-09-20 11:27:02 +02:00

sac_tf_model.py

[RLlib] SAC algo cleanup. (#10825 )

2020-09-20 11:27:02 +02:00

sac_tf_policy.py

[RLlib] SAC algo cleanup. (#10825 )

2020-09-20 11:27:02 +02:00

sac_torch_model.py

[RLlib] SAC: log_alpha not being learnt when on GPU. (#11298 )

2020-10-12 13:48:44 -07:00

sac_torch_policy.py

[RLlib] Assert LongTensor in SAC Discrete PyTorch (#11245 )

2020-10-12 13:47:21 -07:00

sac.py

[RLlib] SAC algo cleanup. (#10825 )

2020-09-20 11:27:02 +02:00

README.md

Soft Actor Critic (SAC)

Implementations of:

Soft Actor-Critic Algorithm (SAC) and a discrete action extension.

Detailed Documentation

Implementation