Resume training of a DQN agent. How to avoid Epsilon from being reset to max value?

1 回表示 (過去 30 日間)
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?

採用された回答

Emmanouil Tzorakoleftherakis
Emmanouil Tzorakoleftherakis 2021 年 6 月 22 日
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.

その他の回答 (0 件)

製品


リリース

R2021a

Community Treasure Hunt

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

Start Hunting!

Translated by