AAAI Publications, Twenty-Fourth International FLAIRS Conference

Font Size: 
Learning Opponent Strategies through First Order Induction
Katie Long Genter, Santiago Ontanon, Ashwin Ram

Last modified: 2011-03-21


In a competitive game it is important to identify the opponent's strategy as quickly and accurately as possible so that an effective response can be planned. In this vein, this paper summarizes our work in exploring using first order inductive learning to learn rules for representing opponent strategies. Specifically, we use these learned rules to perform plan recognition and classify an opponent strategy as one of multiple learned strategies. Our experiments validate this novel approach in a simple real-time strategy game.

Full Text: PDF