ray/rllib/agents/sac at 0d0a41f598f896254a3be50ea983ef31ecd4e07c - ray

wassname/ray

Fork 0

mirror of https://github.com/wassname/ray.git synced 2026-08-10 12:30:14 +08:00

Files

T

History

Eric LiangandGitHub dd70720578 [rllib] Rename sample_batch_size => rollout_fragment_length (#7503 )

* bulk rename

* deprecation warn

* update doc

* update fig

* line length

* rename

* make pytest comptaible

* fix test

* fi sys

* rename

* wip

* fix more

* lint

* update svg

* comments

* lint

* fix use of batch steps

2020-03-14 12:05:04 -07:00

tests

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

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

__init__.py

[RLlib] SAC refactor with new SquashedGaussian distribution class. (#7272 )

2020-02-23 16:10:20 -08:00

README.md

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

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

sac_model.py

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

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

sac_policy.py

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

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

sac.py

[rllib] Rename sample_batch_size => rollout_fragment_length (#7503 )

2020-03-14 12:05:04 -07:00

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