A Competitive Approach to Game Learning

Abstract

Machine learning of game strategies has often depended on competitive methods that continually develop new strategies capable of defeating previous ones. We use a very inclusive definition of game and consider a framework within which a competitive algorithm makes repeated use of a strategy learning component that can learn strategies which defeat a given set of opponents. We describe game learning in terms of sets H and X of first and second player strategies, and connect the model with more familiar models of concept learning. We show the importance of the ideas of teaching set [20] and specification number [19] k in this new context. The performance of several competitive algorithms is investigated, using both worst-case and randomized strategy learning algorithms. Our central result (Theorem 4) is a competitive algorithm that solves games in a total number of strategies polynomial in lg(jHj), lg(jX j), and k. Its use is demonstrated, including an application in concept learning ...