HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Journal articles

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.
Document type :
Journal articles
Complete list of metadata

https://hal.inria.fr/inria-00144146
Contributor : Stephane Gaubert Connect in order to contact the contributor
Submitted on : Tuesday, May 1, 2007 - 5:25:52 PM
Last modification on : Friday, February 4, 2022 - 3:08:18 AM
Long-term archiving on: : Wednesday, April 7, 2010 - 3:30:50 AM

File

CRASPreprint.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

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

Share

Metrics

Record views

142

Files downloads

330