Episode Q0 increases exponentially

4 visualizzazioni (ultimi 30 giorni)
DAMODARAN B.K
DAMODARAN B.K il 16 Feb 2021
Modificato: DAMODARAN B.K il 17 Feb 2021
Can anyone explain why episode Q0 in RL increases exponentially after convergence of reward to a suboptimal policy?

Accedi per rispondere a questa domanda.

Risposte (1)

Emmanouil Tzorakoleftherakis
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 Commento
DAMODARAN B.K
DAMODARAN B.K il 17 Feb 2021
Modificato: DAMODARAN B.K il 17 Feb 2021
is episode Q0, criticnetwork output or target value?

Accedi per commentare.

Categorie

Scopri di più su Introduction to Installation and Licensing in Help Center e File Exchange

Tag

Prodotti

Community Treasure Hunt

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

Start Hunting!

Translated by