Constraint-Based Generalization: LeaMing Game-Playing Plans from Single Examples

Book One

Volume

Proceedings of the AAAI Conference on Artificial Intelligence, 4

Learning

Constraint-based Generalization is a technique for deducing generalizations from a single example. We show how this technique can be used for learning tactical combinations in games and discuss an implementation which learns forced wins in tic-tat-toe, go-moku, and chess.