Optimal strategies for adaptive zero-sum average Markov games

J. Adolfo Minjárez-Sosa*, Óscar Vega-Amaya

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

6 Scopus citations

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, . . ., 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.

Original languageEnglish
Pages (from-to)44-56
Number of pages13
JournalJournal of Mathematical Analysis and Applications
Volume402
Issue number1
DOIs
StatePublished - 1 Jun 2013

Keywords

  • Adaptive strategies
  • Average payoff
  • Zero-sum Markov games

Fingerprint

Dive into the research topics of 'Optimal strategies for adaptive zero-sum average Markov games'. Together they form a unique fingerprint.

Cite this