Boros, Endre
[Verfasser:in];
Elbassioni, Khaled
[Verfasser:in];
Gurvich, Vladimir
[Verfasser:in];
Makino, Kazuhisa
[Verfasser:in]
;
Endre Boros and Khaled Elbassioni and Vladimir Gurvich and Kazuhisa Makino
[Mitwirkende:r]
Markov Decision Processes and Stochastic Games with Total Effective Payoff
Anmerkungen:
Diese Datenquelle enthält auch Bestandsnachweise, die nicht zu einem Volltext führen.
Beschreibung:
We consider finite Markov decision processes (MDPs) with undiscounted total effective payoff. We show that there exist uniformly optimal pure stationary strategies that can be computed by solving a polynomial number of linear programs. We apply this result to two-player zero-sum stochastic games with perfect information and undiscounted total effective payoff, and derive the existence of a saddle point in uniformly optimal pure stationary strategies.