论文信息 - Learning to Play the Game of Chess

Learning to Play the Game of Chess

This paper presents NeuroChess, a program which learns to play chess from the final outcome of games. NeuroChess learns chess board evaluation functions, represented by artificial neural networks. It integrates inductive neural network learning, temporal differencing, and a variant of explanation-based learning. Performance results illustrate some of the strengths and weaknesses of this approach.

Sebastian Thrun | S. Thrun

[1] Arthur L. Samuel,et al. Some Studies in Machine Learning Using the Game of Checkers , 1967, IBM J. Res. Dev..

[2] Prasad Tadepalli,et al. Planning in games using approximately learned macros , 1989, ICML 1989.

[3] Carl Ebeling,et al. Measuring the Performance Potential of Chess Programs , 1990, Artif. Intell..

[4] Thomas S. Anantharaman,et al. A Statistical Study of Selective Min-Max Search in Computer Chess , 1991, J. Int. Comput. Games Assoc..

[5] Yann LeCun,et al. Tangent Prop - A Formalism for Specifying Selected Invariances in an Adaptive Network , 1991, NIPS.

[6] Sebastian Thrun,et al. Explanation-Based Neural Network Learning for Robot Control , 1992, NIPS.

[7] Michael Gherrity,et al. A game-learning machine , 1993 .

[8] Sebastian Thrun,et al. Explanation Based Learning: A Comparison of Symbolic and Neural Network Approaches , 1993, ICML.

[9] Andrew W. Moore,et al. Generalization in Reinforcement Learning: Safely Approximating the Value Function , 1994, NIPS.