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

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. ’

Authors

• Steven Minton

Keywords

No keywords are indexed for this paper.