Resume training of a DQN agent. How to avoid Epsilon from being reset to max value?
3 Ansichten (letzte 30 Tage)
Ältere Kommentare anzeigen
Cecilia S.
am 9 Jun. 2021
Kommentiert: Cecilia S.
am 22 Jun. 2021
When I want to resume training of an agent, I simply load it and set the "resetexperiencebuffer" option to false, but this does not avoid the exploration (depending on epsilon) to start anew. Is there any way to make the agent start from the exact point it left off without manually setting the epsilon value?
0 Kommentare
Akzeptierte Antwort
Emmanouil Tzorakoleftherakis
am 22 Jun. 2021
Hello,
This is currently not possible, but it is a great enhancement idea. I have informed the developers about your request and it will be considered for a future release.
Weitere Antworten (0)
Siehe auch
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!