Bayes-Relational Learning of Opponent Models from Incomplete Information in No-Limit Poker

We propose an opponent modeling approach for no-limit Texas hold-em poker that starts from a (learned) prior, i.e., general expectations about opponent behavior and learns a relational regression tree-function that adapts these priors to specific opponents. An important asset is that this approach can learn from incomplete information (i.e. without knowing all players' hands in training games).

• Type: Conference
• Year: 2008
• Where: AAAI
• Authors: Marc J. V. Ponsen, Jan Ramon, Tom Croonenborghs, Kurt Driessens, Karl Tuyls
• Keywords: AAAI 2008, Intelligent Agents, Opponent Modeling Approach, Relational Regression Tree-function, Texas Hold-em Poker