Using Kuliback-Leibler divergence to model opponents in poker

Opponent modeling is an essential approach for building competitive computer agents in imperfect information games. This paper presents a novel approach to develop opp onent modeling techniques. The approach applies neural networks which are separately trained on different datasct to build K- model clustering opponent models. KullbackL eibler (KL) divergence is used to exploit a safety mode on opponent modeling. Given a parameter d that controls the max divergence between a model's centre point and the units belong to it, the approach is proved to provide a lower bound of expected payoff which is above the minimax payo ff for correctly clustered players. Even for the players that are incorrectly clustered, the lower bound can also be unlimi ted approximated with sufficient history data, In our experi ments, agent with the novel model shows an improved class ification efficiency of opponent modeling comparing with relative researches. And also, the new agent performs better when playing against poker agent HITSZ-CS-13 which participate Annual Computer Poker Competition of 2013.