Policy iteration for stochastic zero-sum games - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Documents Associated With Scientific Events Year : 2014

Policy iteration for stochastic zero-sum games

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.
Fichier principal
Vignette du fichier
Akian-NETCO2014.pdf (370.09 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01024097 , version 1 (15-07-2014)

Identifiers

  • HAL Id : hal-01024097 , version 1

Cite

Marianne Akian. Policy iteration for stochastic zero-sum games. NETCO 2014, 2014, Tours, France. ⟨hal-01024097⟩
467 View
57 Download

Share

Gmail Facebook X LinkedIn More