Machine Learning in Computer Chess: The Next Generation

Abstract

Ten years ago the ICCA Journal published an overview of machine-learning approaches to computer chess (Skiena, 1986). The author’s results were rather pessimistic. In particular he concluded that “with the exception of rote learning in the opening book, few results have trickled into competitive programs” and that “there appear no research projects on the horizon offering reason for optimism.”

In this paper we will update Skiena’s work with research that has been conducted in this area since the publication of his paper. By doing so we hope to show that at least Skiena’s second conclusion is no longer valid.