Adaptive Pattern-Oriented Chess

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