Modifying the control actions to safe ones before storing in the experience buffer during SAC agent training.
3 vues (au cours des 30 derniers jours)
Afficher commentaires plus anciens
Ahmed R. Sayed
le 18 Jan 2022
Réponse apportée : Ahmed R. Sayed
le 21 Sep 2022
Hello everyone,
I am implementing a safe off-policy DRL SAC algorithm. Using an iterative convex optimization algorithm moves actions into a safe region. However, this algorithm is applied in the environment. Therefore, the existing rlSACAgent still store unsafe actions in the buffer, and the agent cannot learn the modified actions. Therefore, the iterative algorithm will be supplied with unlearned actions and takes more time to converge. My question is:
How can I store the modified actions in the experience buffer instead of the unsafe ones?
Illustrative figure:
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/866360/image.png)
Many thanks for your help.
0 commentaires
Réponse acceptée
Plus de réponses (0)
Voir également
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!