Expected reward blows up while training (DDPG agent, reinforcement learning)
1 view (last 30 days)
Show older comments
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 Comments
Answers (1)
Emmanouil Tzorakoleftherakis
on 12 Oct 2020
Edited: Emmanouil Tzorakoleftherakis
on 12 Oct 2020
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.
2 Comments
See Also
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!