ray/rllib/agents/sac at d0fab84e4dfdddc64cb4275ff98cf67f84ff86a0 - ray

wassname/ray

Fork 0

mirror of https://github.com/wassname/ray.git synced 2026-08-14 12:40:23 +08:00

Files

T

History

Sven MikaandGitHub d0fab84e4d [RLlib] DDPG PyTorch version. (#7953 )

The DDPG/TD3 algorithms currently do not have a PyTorch implementation. This PR adds PyTorch support for DDPG/TD3 to RLlib.
This PR:
- Depends on the re-factor PR for DDPG (Functional Algorithm API).
- Adds learning regression tests for the PyTorch version of DDPG and a DDPG (torch)
- Updates the documentation to reflect that DDPG and TD3 now support PyTorch.

* Learning Pendulum-v0 on torch version (same config as tf). Wall time a little slower (~20% than tf).
* Fix GPU target model problem.

2020-04-16 10:20:01 +02:00

tests

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

2020-04-15 13:25:16 +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] SAC Torch (incl. Atari learning) (#7984 )

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

sac_tf_policy.py

[RLlib] DDPG PyTorch version. (#7953 )

2020-04-16 10:20:01 +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] SAC Torch (incl. Atari learning) (#7984 )

2020-04-15 13:25:16 +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