Episode Q0 increases exponentially
Show older comments
Can anyone explain why episode Q0 in RL increases exponentially after convergence of reward to a suboptimal policy?
Answers (1)
Emmanouil Tzorakoleftherakis
on 16 Feb 2021
0 votes
Hello,
Please take a look at this answer for some suggestions. Normalizing observations, rewards, and actions can also help avoid situations like these.
Hope this helps
1 Comment
DAMODARAN B.K
on 17 Feb 2021
Edited: DAMODARAN B.K
on 17 Feb 2021
Categories
Find more on Introduction to Installation and Licensing in Help Center and File Exchange
Products
on 16 Feb 2021
on 17 Feb 2021
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!
