On Markov Games Played by Bayesian and Boundedly-Rational Players

Muthukumaran Chandrasekaran, Yingke Chen, Prashant Doshi

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    5 Downloads (Pure)

    Abstract

    We present a new game-theoretic framework in which
    Bayesian players with bounded rationality engage in a
    Markov game and each has private but incomplete information
    regarding other players’ types. Instead of utilizing
    Harsanyi’s abstract types and a common prior, we construct
    intentional player types whose structure is explicit and induces
    a finite-level belief hierarchy. We characterize an equilibrium
    in this game and establish the conditions for existence
    of the equilibrium. The computation of finding such equilibria
    is formalized as a constraint satisfaction problem and its
    effectiveness is demonstrated on two cooperative domains.
    Original languageEnglish
    Title of host publicationProceedings of 31st AAAI Conference on Artificial Intelligence
    PublisherAAAI
    Number of pages7
    Publication statusPublished - 13 Feb 2017
    Event31st AAAI Conference on Artificial Intelligence - San Francisco, United States
    Duration: 4 Feb 20179 Feb 2017

    Publication series

    Name Proceedings of the AAAI conference on artificial intelligence
    ISSN (Electronic)2374-3468

    Conference

    Conference31st AAAI Conference on Artificial Intelligence
    Abbreviated titleAAAI-17
    CountryUnited States
    CitySan Francisco
    Period4/02/179/02/17

    Bibliographical note

    We present a new game-theoretic framework in which Bayesian players with bounded rationality engage in a Markov game and each has private but incomplete information regarding other players’ types. Instead of utilizing Harsanyi’s abstract types and a common prior, we construct intentional player types whose structure is explicit and induces a finite-level belief hierarchy. We characterize an equilibrium in this game and establish the conditions for existence of the equilibrium. The computation of finding such equilibria is formalized as a constraint satisfaction problem and its effectiveness is demonstrated on two cooperative domains.

    Fingerprint Dive into the research topics of 'On Markov Games Played by Bayesian and Boundedly-Rational Players'. Together they form a unique fingerprint.

  • Cite this

    Chandrasekaran, M., Chen, Y., & Doshi, P. (2017). On Markov Games Played by Bayesian and Boundedly-Rational Players. In Proceedings of 31st AAAI Conference on Artificial Intelligence ( Proceedings of the AAAI conference on artificial intelligence). AAAI. https://aaai.org/ocs/index.php/AAAI/AAAI17/paper/view/14334/13795