Download PDF

Belgian-Dutch Conference on Machine Learning, Date: 2008/05/19 - 2008/05/20

Publication date: 2008-05-01

Proceedings of the Annual Belgian-Dutch Conference on Machine Learning

Author:

Ponsen, Marc
Ramon, Jan ; Croonenborghs, Tom ; Driessens, Kurt ; Tuyls, Karl ; Wehenkel, Louis ; Geurts, Pierre ; Maree, Raphael

Keywords:

Machine learning, Multi agent systems

Abstract:

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).