TY - JOUR
T1 - Optimal strategies for adaptive zero-sum average Markov games
AU - Minjárez-Sosa, J. Adolfo
AU - Vega-Amaya, Óscar
PY - 2013/6/1
Y1 - 2013/6/1
N2 - 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, . . ., where the disturbance process {ξn} is formed by independent and identically distributed Rk-valued random vectors, which are observable but their common density ρ* is unknown for both players. Combining suitable methods of statistical estimation of ρ* with optimization procedures, we construct a pair of average optimal strategies.
AB - 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, . . ., where the disturbance process {ξn} is formed by independent and identically distributed Rk-valued random vectors, which are observable but their common density ρ* is unknown for both players. Combining suitable methods of statistical estimation of ρ* with optimization procedures, we construct a pair of average optimal strategies.
KW - Adaptive strategies
KW - Average payoff
KW - Zero-sum Markov games
UR - http://www.scopus.com/inward/record.url?scp=84875378695&partnerID=8YFLogxK
U2 - 10.1016/j.jmaa.2012.12.011
DO - 10.1016/j.jmaa.2012.12.011
M3 - Artículo
SN - 0022-247X
VL - 402
SP - 44
EP - 56
JO - Journal of Mathematical Analysis and Applications
JF - Journal of Mathematical Analysis and Applications
IS - 1
ER -