论文信息 - From Simple Features to Sophisticated Evaluation Functions

From Simple Features to Sophisticated Evaluation Functions

This paper discusses a practical framework for the semi-automatic construction of evaluation-functions for games. Based on a structured evaluation function representation, a procedure for exploring the feature space is presented that is able to discover new features in a computationally feasible way. Besides the theoretical aspects, related practical issues such as the generation of training positions, feature selection, and weight fitting in large linear systems are discussed. Finally, we present experimental results for Othello, which demonstrate the potential of the described approach.

Michael Buro | M. Buro

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

[2] Stephen Jose Hanson,et al. Meiosis Networks , 1989, NIPS.

[3] William H. Press,et al. Numerical recipes , 1990 .

[4] Romeo Çollaku,et al. Deep thought , 1991, Nature.

[5] Robert Levinson,et al. Adaptive Pattern-Oriented Chess , 1991, AAAI Conference on Artificial Intelligence.

[6] William H. Press,et al. Numerical Recipes in C, 2nd Edition , 1992 .

[7] Gerald Tesauro,et al. TD-Gammon, a Self-Teaching Backgammon Program, Achieves Master-Level Play , 1994, Neural Computation.

[8] Gerald Tesauro,et al. Temporal Difference Learning and TD-Gammon , 1995, J. Int. Comput. Games Assoc..

[9] Gerald Tesauro,et al. TD-Gammon: A Self-Teaching Backgammon Program , 1995 .

[10] Gerald Tesauro,et al. Temporal difference learning and TD-Gammon , 1995, CACM.

[11] Doina Precup,et al. Constructive Function Approximation TITLE2 , 1997 .

[12] Michael Buro. Experiments with Multi-ProbCut and a New High-Quality Evaluation Function for Othello , 1997 .

[13] Michael Buro,et al. The Othello Match of the Year: Takeshi Murakami vs. Logistello , 1997, J. Int. Comput. Games Assoc..

[14] Doina Precup,et al. Constructive Function Approximation , 1998 .