ray/rllib/agents/sac at 8cf37726d2d4bc9744287a8a49d9b6e065af66aa - ray

wassname/ray

Fork 0

mirror of https://github.com/wassname/ray.git synced 2026-07-22 13:00:49 +08:00

Files

T

History

Sven MikaandGitHub f7e4dae852 [RLlib] DQN and SAC Atari benchmark fixes. (#7962 )

* Add Atari SAC-discrete (learning MsPacman in 40k ts up to 780 rewards).
* SAC loss function test case fix.

2020-04-17 08:49:15 +02:00

tests

[RLlib] DQN and SAC Atari benchmark fixes. (#7962 )

2020-04-17 08:49:15 +02:00

__init__.py

[RLlib] SAC Torch (incl. Atari learning) (#7984 )

2020-04-15 13:25:16 +02:00

README.md

[RLlib] SAC add discrete action support. (#7320 )

2020-03-06 10:37:12 -08:00

sac_tf_model.py

[RLlib] DQN and SAC Atari benchmark fixes. (#7962 )

2020-04-17 08:49:15 +02:00

sac_tf_policy.py

[RLlib] DQN and SAC Atari benchmark fixes. (#7962 )

2020-04-17 08:49:15 +02:00

sac_torch_model.py

[RLlib] SAC Torch (incl. Atari learning) (#7984 )

2020-04-15 13:25:16 +02:00

sac_torch_policy.py

[RLlib] SAC Torch (incl. Atari learning) (#7984 )

2020-04-15 13:25:16 +02:00

sac.py

[RLlib] DQN and SAC Atari benchmark fixes. (#7962 )

2020-04-17 08:49:15 +02:00

README.md

Implementation of the Soft Actor-Critic algorithm:

[1] Soft Actor-Critic Algorithms and Applications - T. Haarnoja, A. Zhou, K. Hartikainen, et. al https://arxiv.org/abs/1812.05905.pdf

For supporting discrete action spaces, we implemented this patch on top of the original algorithm: [2] Soft Actor-Critic for Discrete Action Settings - Petros Christodoulou https://arxiv.org/pdf/1910.07207v2.pdf