Learning to Estimate Potential Territory in the Game of Go

This paper investigates methods for estimating potential territory in the game of Go. We have tested the performance of direct methods known from the literature, which do not require a notion of life and death. Several enhancements are introduced which can improve the performance of the direct methods. New trainable methods are presented for learning to estimate potential territory from examples. The trainable methods can be used in combination with our previously developed method for predicting life and death [25]. Experiments show that all methods are greatly improved by adding knowledge of life and death.

[1]  H. Jaap van den Herik,et al.  Learning to score final positions in the game of Go , 2003, Theor. Comput. Sci..

[2]  H. Jaap van den Herik,et al.  Learning to predict life and death from Go game records , 2005, Inf. Sci..

[3]  Zhixing Chen,et al.  Semi-Empirical Quantitative Theory of Go Part I: Estimation of the Influence of a Wall , 2002, J. Int. Comput. Games Assoc..

[4]  H. Jaap van den Herik,et al.  Solving Go on Small Boards , 2003, J. Int. Comput. Games Assoc..

[5]  Martin Müller,et al.  Computer Go , 2002, Artif. Intell..

[6]  Bruno Bouzy.  Mathematical Morphology Applied to Computer Go , 2003, Int. J. Pattern Recognit. Artif. Intell..

[7]  Jonathan Leonard Ryder,et al.  Heuristic analysis of large trees as generated in the game of Go , 1971 .

[8]  Markus Enzenberger,et al.  Evaluation in Go by a Neural Network using Soft Segmentation , 2003, ACG.

[9]  Anil K. Jain,et al.  39 Dimensionality and sample size considerations in pattern recognition practice , 1982, Classification, Pattern Recognition and Reduction of Dimensionality.

[10]  Fredrik A. Dahl,et al.  Honte, a go-playing program using neural nets , 2001 .

[11]  Martin Müller.  Position Evaluation in Computer Go , 2002, J. Int. Comput. Games Assoc..

[12]  Keh-Hsun Chen.  Some Practical Techniques for Global Search in Go , 2000, J. Int. Comput. Games Assoc..

[13]  Martin A. Riedmiller,et al.  A direct adaptive method for faster backpropagation learning: the RPROP algorithm , 1993, IEEE International Conference on Neural Networks.

[14]  David B. Benson,et al.  Life in the game of Go , 1976 .

[15]  Richard Bellman,et al.  Adaptive Control Processes: A Guided Tour , 1961, The Mathematical Gazette.

[16]  Terrence J. Sejnowski,et al.  Temporal Difference Learning of Position Evaluation in the Game of Go , 1993, NIPS.

[17]  Albert L. Zobrist,et al.  A model of visual organization for the game of GO , 1899, AFIPS '69 (Spring).

[18]  Bruno Bouzy,et al.  Computer Go: An AI oriented survey , 2001, Artif. Intell..

[19]  Keh-Hsun Chen.  Computer Go: Knowledge, Search, and Move Decision , 2001, J. Int. Comput. Games Assoc..