On Markov Games Played by Bayesian and Boundedly-Rational Players

Muthukumaran Chandrasekaran, Yingke Chen, Prashant Doshi

AAAI 2017 pp. 437-443

doi:10.1609/AAAI.V31I1.10566 /aaai/2017/chandrasekaran2017aaai-markov/

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 {\em 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.

PDF AAAI Semantic Scholar

Cite

Text

Chandrasekaran et al. "On Markov Games Played by Bayesian and Boundedly-Rational Players." AAAI Conference on Artificial Intelligence, 2017. doi:10.1609/AAAI.V31I1.10566

Markdown

[Chandrasekaran et al. "On Markov Games Played by Bayesian and Boundedly-Rational Players." AAAI Conference on Artificial Intelligence, 2017.](https://mlanthology.org/aaai/2017/chandrasekaran2017aaai-markov/) doi:10.1609/AAAI.V31I1.10566

BibTeX

@inproceedings{chandrasekaran2017aaai-markov,
  title     = {{On Markov Games Played by Bayesian and Boundedly-Rational Players}},
  author    = {Chandrasekaran, Muthukumaran and Chen, Yingke and Doshi, Prashant},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2017},
  pages     = {437-443},
  doi       = {10.1609/AAAI.V31I1.10566},
  url       = {https://mlanthology.org/aaai/2017/chandrasekaran2017aaai-markov/}
}