Adaptive Pattern-Oriented Chess

Abstract

Psychological evidence indicates that human chess players base their assessments of chess positions on structural/perceptual patterns learned through experience. Morph is a computer chess program that has been developed to be more consistent with the cognitive models. The learning mechanism used by Morph combines weight-updating, genetic, explanation-based and temporal-difference learning to create, delete, generalize and evaluate chess positions. An associative pattern retrieval system organizes the database for efficient processing. The main objectives of the project are to demonstrate capacity of the system to learn, to deepen our understanding of the interaction of knowledge and search, and to build bridges in this area between AI and cognitive science. To strengthen connections with the cognitive literature limitations have been place on the system, such as restrictions to 1-ply search, to little domain knowledge, and to no supervised training.