Expected reward blows up while training (DDPG agent, reinforcement learning)
조회 수: 1 (최근 30일)
이전 댓글 표시
I am training a DDPG network and after training for around 5000 iterations, the model seems doesnot seem to converge while the expected reward keeps on increasing exponentially. What can be a possible reason and how to solve the issue.
댓글 수: 0
답변 (1개)
Emmanouil Tzorakoleftherakis
2020년 10월 12일
편집: Emmanouil Tzorakoleftherakis
2020년 10월 12일
Hello,
This answer may be helpful.
I would make sure your reward signal outputs values that make sense, and also possibly simplify the critic network.
댓글 수: 2
참고 항목
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!