Episode Q0 increases exponentially
18 Ansichten (letzte 30 Tage)
Ältere Kommentare anzeigen
Can anyone explain why episode Q0 in RL increases exponentially after convergence of reward to a suboptimal policy?
0 Kommentare
Antworten (1)
Emmanouil Tzorakoleftherakis
am 16 Feb. 2021
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 Kommentar
Siehe auch
Kategorien
Mehr zu Training and Simulation finden Sie in Help Center und File Exchange
Produkte
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!