Article ID Journal Published Year Pages File Type
4616902 Journal of Mathematical Analysis and Applications 2013 13 Pages PDF
Abstract

We consider a class of discrete-time two person zero-sum Markov games with Borel state and action spaces, and possibly unbounded payoffs. The game evolves according to the recursive equation xn+1=F(xn,an,bn,ξn),n=0,1,…xn+1=F(xn,an,bn,ξn),n=0,1,…, where the disturbance process {ξn}{ξn} is formed by independent and identically distributed RkRk-valued random vectors, which are observable but their common density ρ∗ρ∗ is unknown for both players. Combining suitable methods of statistical estimation of ρ∗ρ∗ with optimization procedures, we construct a pair of average optimal strategies.

Related Topics
Physical Sciences and Engineering Mathematics Analysis
Authors
, ,