In stochastic games with perfect information, in each state at most one player has more than one action available. We propose two algorithms which find the uniform optimal strategies for zero-sum two-player stochastic games with perfect information. Such strategies are optimal for the long term average criterion as well. We prove the convergence for one algorithm, which presents a higher complexity than the other one, for which we provide numerical analysis.
Type:
Rapport
Date:
2010-07-27
Department:
Systèmes de Communication
Eurecom Ref:
3191
Copyright:
© INRIA. Personal use of this material is permitted. The definitive version of this paper was published in and is available at :
See also: