Soft Actor-Critic (SAC)
Soft Actor-Critic (SAC)
Maximum Entropy Reinforcement learning
off policy
stochastic policy and not deterministic policy (Only one action is considered optimal in each state)
Codes:
rail-berkeley/softlearning(tenserslow)
[rail-berkeley/rlkit]https://github.com/rail-berkeley/rlkit (pytorch)
Title:
Author: wy
Created at
: 2023-07-23 20:16:31**Updated at :** 2023-07-24 17:09:37**Link:** https://yuuee-www.github.io/blog/2023/07/23/RL/step11/RLstep11/** License: ** This work is licensed under [CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0). [Prev posts](/2023/07/24/RL/step12/RLstep12/) [Next posts](/2023/07/23/RL/step10/RLstep10/) Comments On this page
-
© 2022 - 2024 [wy](/) 24 posts in total VISITOR COUNT TOTAL PAGE VIEWS POWERED BY [Hexo](https://hexo.io) THEME [Redefine v2.6.4](https://github.com/EvanNotFound/hexo-theme-redefine) Blog up for days hrs Min Sec
-
-
-
-
-
-
-
- Title: Soft Actor-Critic (SAC)
- Author: wy
- Created at : 2023-07-23 12:16:31
- Updated at : 2023-07-24 09:09:37
- Link: https://yue-ruby-w.site/2023/07/23/2023-07-23-RL-step11-RLstep11/
- License: This work is licensed under CC BY-NC-SA 4.0.