Stationary action values in reinforcement learning
1 visualizzazione (ultimi 30 giorni)
Mostra commenti meno recenti
minhyuk jeung
il 20 Giu 2022
Spostato: Angelo Yeo
il 21 Mag 2024
Hello,
I'am trying to train reinforcement learning with high dimensional actions.
ex)
ActionInfo = rlNumericSpec([9 1], ...
'LowerLimit',[0.012 0.01 0.015 0.05 92 3 0.1 3 0.012]',...
'UpperLimit',[0.030 0.03 0.1 0.3 100 5 0.3 5 0.040]');
and construct my actornetwork with "scalingLayer" and low value of neurons
ex)
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/1038805/image.jpeg)
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/1038810/image.jpeg)
but only 3~5 parameter changes (other parameter doesn't change)
ex)
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/1038815/image.jpeg)
Is there any solution to make all action parameters changeable???
Thank you for help.
1 Commento
Venu
il 14 Nov 2023
Can you provide some information regarding your learning environment, ObservationInfo?
Thanks
Risposta accettata
Più risposte (0)
Vedere anche
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!