Not Logged In

PapersDB

Bayes' bluff: Opponent modelling in poker

• Finnegan Southey
• Michael Bowling, University of Alberta
• Bryce Larson, Department of Computing Science, University of Alberta
• Carmelo Piccione, Department of Computing Science, University of Alberta
• Neil Burch, Department of Computing Science, University of Alberta
• Darse Billings, Department of Computing Science, University of Alberta
• Chris Rayner, Department of Computing Science, University of Alberta

Poker is a challenging problem for articial intelligence, with non-deterministic dynamics, partial observability, and the added difculty of unknown adversaries. Modelling all of the uncertainties in this domain is not an easy task. In this paper we present a Bayesian probabilistic model for a broad class of poker games, separating the uncertainty in the game dynamics from the uncertainty of the opponent's strategy. We then describe approaches to two key subproblems: (i) inferring a posterior over opponent strategies given a prior distribution and observations of their play, and (ii) playing an appropriate response to that distribution. We demonstrate the overall approach on a reduced version of poker using Dirichlet priors and then on the full game of Texas hold'em using a more informed prior. We demonstrate methods for playing effective responses to the opponent, based on the posterior.

Citation

BibTeX

@incollection{Southey+al:UAI05,
  author = {Finnegan Southey and Michael Bowling and Bryce Larson and Carmelo
    Piccione and Neil Burch and Darse Billings and Chris Rayner},
  title = {Bayes' bluff: Opponent modelling in poker},
  Pages = {550-558},
  booktitle = {Conference on Uncertainty in Artificial Intelligence (UAI)},
  year = 2005,
}

Last Updated: April 24, 2007
Submitted by William Thorne

• Home
• Search
  • Advanced Search
• Publications
  • View Publication Entries
• Authors
  • View Authors
• User
  • Login or Register