Randomized Strategies are Useless in Markov Decision Processes
Résumé
We show that in a Markov decision process with arbitrary payoff mapping, restricting the set of behavioral strategies from randomized to deterministic does not influence the value of the game nor the existence of almost-surely or positively winning strategies. This result still holds for Markov decision processes with partial observation.
Origine : Fichiers produits par l'(les) auteur(s)