Expected reward blows up while training (DDPG agent, reinforcement learning)

3 views (last 30 days)
Sayak Mukherjee
Sayak Mukherjee on 12 Oct 2020
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.

Answers (1)

Emmanouil Tzorakoleftherakis
Edited: Emmanouil Tzorakoleftherakis on 12 Oct 2020
This answer may be helpful.
I would make sure your reward signal outputs values that make sense, and also possibly simplify the critic network.

Community Treasure Hunt

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

Start Hunting!

Translated by