An Experiment on Inductive Learning in Chess End Games

Further progress in the application of computers to many practical fields seems to depend heavily on the success in implementing learning and inductive processes within machines. For example, to develop a consultation system for medical or plant disease diagnosis, prognosis and decision making in general, it is very desirable, perhaps even necessary, to be able to 'teach' the system through examples of correct and/or incorrect decisions, rather than by precisely describing the decision process in its full generality and then transforming this description into a computer program. A similar situation exists in computer chess. The development of computer programs playing at the master level (especially the end games) seems to be a formidable task if the programs are not eventually able to learn and improve on their decision making rules through the specific examples of games, rather than by being explicitly told all the rules. Due to easy access to human knowledge about chess and the relative simplicity of testing the results, chess is one of the most attractive testing domains for inductive inference programs. This report presents first results from an experiment on the application of an inductive learning program called AQVAL/1 developed at the University of Illinois, to chess end games. The experiments were to infer from examples the classification rules which distinguish the win position from the draw position in the single pawn end game (i.e., white king and pawn against black king). The problem of representing the human knowledge about this end game has been studied by Tan (Tan, 1972). The major and exceedingly significant result of his work is a comprehensive program which solves all known cases of this game (including all examples from Awerbach (Awerbach, 1958) and Fine (Fine, 1941). His approach, however, has certain strong limitations which make it not very prospective for the more complex end games. As Tan (/c. cit.) admits himself: