Soft Actor Critic deploy mean path only

3 views (last 30 days)
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?

Accepted Answer

Emmanouil Tzorakoleftherakis
Hello,
Please take a look at this option here which was added in R2021a to allow exactly the behavior you mentioned.
Hope this helps
  1 Comment
Tech Logg Ding
Tech Logg Ding on 13 May 2021
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!

Sign in to comment.

More Answers (0)

Community Treasure Hunt

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

Start Hunting!