Expected reward blows up while training (DDPG agent, reinforcement learning)
3 次查看(过去 30 天)
显示 更早的评论
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.
0 个评论
回答(1 个)
Emmanouil Tzorakoleftherakis
2020-10-12
编辑:Emmanouil Tzorakoleftherakis
2020-10-12
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.
另请参阅
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!