DQN learns at first but then worsens.
4 views (last 30 days)
Show older comments
Hi, I am training a DQN agent with a simevent model. I am testing out different hyperparameters, but everytime the agent learns (reward goes higher) at first for a while, but then goes down. I have tested different learning rate, exploration epsilon, and discount factors. But the shape of training progress is pretty much same in all combinations. Is there any potential way I can fix this issue?
0 Comments
Answers (1)
Emmanouil Tzorakoleftherakis
on 22 Apr 2021
Edited: Emmanouil Tzorakoleftherakis
on 22 Apr 2021
To confirm that this is an exploration issue, can you try setting the EpsilonMin param to a high value? e.g. 0.99. If after doing that you still see the same result, there is likely something else going on.
2 Comments
Emmanouil Tzorakoleftherakis
on 23 Apr 2021
Hard to tell, but it's strange to me that the episode curve is similar every time. That makes me think that there is something specific about the way you have modeled your environment model that guides the training through a similar path each time.
See Also
Categories
Find more on Training and Simulation in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!