Policy iteration algorithm for zero-sum stochastic games with mean payoff - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Comptes Rendus. Mathématique Year : 2006

Policy iteration algorithm for zero-sum stochastic games with mean payoff

Abstract

We give a policy iteration algorithm to solve zero-sum stochastic games with finite state and action spaces and perfect information, when the value is defined in terms of the mean payoff per turn. This algorithm does not require any irreducibility assumption on the Markov chains determined by the strategies of the players. It is based on a discrete nonlinear analogue of the notion of reduction of a super-harmonic function.
Fichier principal
Vignette du fichier
CRASPreprint.pdf (108.81 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

inria-00144146 , version 1 (01-05-2007)

Identifiers

Cite

Jean Cochet-Terrasson, Stéphane Gaubert. Policy iteration algorithm for zero-sum stochastic games with mean payoff. Comptes Rendus. Mathématique, 2006, 343 (5), pp.377-382. ⟨10.1016/j.crma.2006.07.011⟩. ⟨inria-00144146⟩
153 View
346 Download

Altmetric

Share

Gmail Facebook X LinkedIn More