Resume training of a DQN agent. How to avoid Epsilon from being reset to max value?
2 views (last 30 days)
Show older comments
Cecilia S.
on 9 Jun 2021
Commented: Cecilia S.
on 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 Comments
Accepted Answer
Emmanouil Tzorakoleftherakis
on 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.
More Answers (0)
See Also
Categories
Find more on Introduction to Installation and Licensing in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!