Average optimal strategies for zero-sum Markov games with poorly known payoff function on one side

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

We are concerned with two-person zero-sum Markov games with Borel spaces under a long-run average criterion. The payoff function is possibly unbounded and depends on a parameter which is unknown to one of the players. The parameter and the payoff function can be estimated by implementing statistical methods. Thus, our main objective is to combine such estimation procedure with a variant of the so-called vanishing discount approach to construct an average optimal pair of strategies for the game. Our results are applied to a class of zero-sum semi-Markov games.

Original languageEnglish
Pages (from-to)105-119
Number of pages15
JournalJournal of Dynamics and Games
Volume1
Issue number1
DOIs
StatePublished - 2014

Bibliographical note

Publisher Copyright:
© 2014, American Institute of Mathematical Sciences.

Keywords

  • Average payoff criterion
  • Incomplete information
  • Payoff estimation
  • Zero-sum Markov and semi-Markov games

Fingerprint

Dive into the research topics of 'Average optimal strategies for zero-sum Markov games with poorly known payoff function on one side'. Together they form a unique fingerprint.

Cite this