Policy iteration for stochastic zero-sum games

Marianne Akian 1, 2
2 MAXPLUS - Max-plus algebras and mathematics of decision
CMAP - Centre de Mathématiques Appliquées - Ecole Polytechnique, Inria Saclay - Ile de France
Abstract : Recent results of Ye and Hansen, Miltersen and Zwick show that policy iteration for one or two player (perfect information) zero-sum stochastic games, restricted to instances with a fixed discount rate, is strongly polynomial. We show that policy iteration for mean-payoff zero-sum stochastic games is also strongly polynomial when restricted to instances with bounded first mean return time to a given state. The proof is based on methods of nonlinear Perron-Frobenius theory, allowing us to reduce the mean-payoff problem to a discounted problem with state dependent discount rate. Our analysis also shows that policy iteration remains strongly polynomial for discounted problems in which the discount rate can be state dependent (and even negative) at certain states, provided that the spectral radii of the nonnegative matrices associated to all strategies are bounded from above by a fixed constant strictly less than 1.
Type de document :
Document associé à des manifestations scientifiques
NETCO 2014, 2014, Tours, France
Liste complète des métadonnées

Contributeur : Estelle Bouzat <>
Soumis le : mardi 15 juillet 2014 - 16:07:24
Dernière modification le : mercredi 23 janvier 2019 - 10:29:26
Document(s) archivé(s) le : vendredi 21 novembre 2014 - 18:50:38


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-01024097, version 1


Marianne Akian. Policy iteration for stochastic zero-sum games. NETCO 2014, 2014, Tours, France. 〈hal-01024097〉



Consultations de la notice


Téléchargements de fichiers