On discounted approximations of undiscounted stochastic games and Markov decision processes with limited randomness

It is shown that the discount factor needed to solve an undiscounted mean payoff stochastic game to optimality is exponentially close to 1, even in one-player games with a single random node and polynomially bounded rewards and transition probabilities. For the class of the so-called irreducible gam...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Operations research letters Ročník 41; číslo 4; s. 357 - 362
Hlavní autoři:	Boros, Endre, Elbassioni, Khaled, Gurvich, Vladimir, Makino, Kazuhisa
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Elsevier B.V 01.07.2013
Témata:	Discounted stochastic games Markov decision processes Pseudo-polynomial algorithms Saddle point Zero-sum stochastic games Discounted stochastic games Zero-sum stochastic games Markov decision processes Pseudo-polynomial algorithms Saddle point
ISSN:	0167-6377, 1872-7468
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	It is shown that the discount factor needed to solve an undiscounted mean payoff stochastic game to optimality is exponentially close to 1, even in one-player games with a single random node and polynomially bounded rewards and transition probabilities. For the class of the so-called irreducible games with perfect information and a constant number of random nodes, we obtain a pseudo-polynomial algorithm using discounts.
ISSN:	0167-6377 1872-7468
DOI:	10.1016/j.orl.2013.04.006