MATLAB Answers

Soft Actor Critic deploy mean path only

2 ビュー (過去 30 日間)
Hi, I'm wondering if there's a way to only deploy the mean path of the SAC agent after it's been trained? This is useful to create more stable actions after the network has been trained.
Should I extract the network weights manually, create a network, then extract an output path for the mean network?


Emmanouil Tzorakoleftherakis
Emmanouil Tzorakoleftherakis 2021 年 5 月 13 日
Please take a look at this option here which was added in R2021a to allow exactly the behavior you mentioned.
Hope this helps
  1 件のコメント
Tech Logg Ding
Tech Logg Ding 2021 年 5 月 13 日
Thank you for the reply. That setting works. I've also tried the roundabout way of extracting the actor neural network and modifying it to only have the mean path. Then I deploy the actor neural network into the simulation to act as a controller. Both method works!


その他の回答 (0 件)

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by