PyTorch implementation of Soft Actor Critic (SAC)
SAC is an off-policy actor critic reinforcement learning algorithm based on entropy maximisation.
Tested with PyBullet envs
 |
|---|
| HalfCheetahBulletEnv |
 |
|---|
| InvertedPendulumBulletEnv |
-
Notifications
You must be signed in to change notification settings - Fork 0
Soft Actor Critic implementation in PyTorch
License
mihonen/sac_pytorch
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Soft Actor Critic implementation in PyTorch
Topics
Resources
License
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published