4*4-Pattern and Bayesian Learning in Monte-Carlo Go
Abstract
The paper proposes a new model of pattern, namely the 4*4-Pattern, to improve MCTS (Monte-Carlo Tree Search) in computer Go. A 4*4-Pattern provides a larger coverage space and more essential information than the original 3*3-Pattern. Nevertheless the latter is currently widely used. Due to the lack of a central symmetry, it takes greater challenges to apply a 4*4-Pattern compared to a 3*3-Pattern. Many details of a 4*4-Pattern implementation are presented, including classification, multiple matching, coding sequences, and fast lookup. Additionally, Bayesian 4*4-Pattern learning is introduced, and 4*4-Pattern libraries are automatically generated from a vast amount of professional game records. The results of our experiments show that the use of 4*4-Patterns can improve MCTS in 19*19 Go to some extent, in particular when supported by 4*4-Pattern libraries generated by Bayesian learning.
Keywords
Anchor Point Post Probability Occupancy Rate Bayesian Learning Multiple MatchPreview
Unable to display preview. Download preview PDF.
References
- 1.Bouzy, B., Chaslot, G.: Bayesian generation and integration of k-nearest-neighbor patterns for 19×19 Go. Computational Intelligence in Games, 176–181 (2005)Google Scholar
- 2.Bouzy, B., Cazenave, T.: Computer go: An AI oriented survey. Artificial Intelligence 132(1), 39–103 (2001)MathSciNetMATHCrossRefGoogle Scholar
- 3.Fuego Developer’s Documentation, http://www.cs.ualberta.ca/~games/go/fuego/fuegodoc/
- 4.Gelly, S., Silver, D.: Combining Offline and Online Knowledge in UCT. In: ICML 2007: Proceedings of the 24th International Conference on Machine Learning, pp. 273–280. Association for Computing Machinery (2007)Google Scholar
- 5.Gelly, S., et al.: Modification of UCT with Patterns in Monte-Carlo Go. Technical Report 6062. INRIA,France (2006)Google Scholar
- 6.Gelly, S., Wang, Y.: Exploration exploitation in go: UCT for Monte-Carlo go. In: On-line trading of Exploration and Exploitation Workshop (2006)Google Scholar
- 7.Minka, T.P.: A family of algorithms for approximate Bayesian inference. Massachusetts Institute of Technology (2001)Google Scholar
- 8.Müller, M.: Position Evaluation in Computer Go. ICGA Journal, pp. 219-228 (2002)Google Scholar
- 9.Silver, D., Tesauro, G.: Monte-Carlo Simulation Balancing. In: Proceedings of the 26th Annual International Conference on Machine Learning, Montreal, Quebec, Canada, pp. 954–852 (2009)Google Scholar
- 10.Stern, D., Herbrich, R., Graepel, T.: Bayesian Pattern Ranking for Move Prediction in the Game of Go. In: The 23rd International Conference on Machine Learning, pp.873–880 (2006)Google Scholar
- 11.Stern, D., Graepel, T., MacKay, D.: Modelling Uncertainty in The Game of Go. In: Advances in Neural Information Processing Systems, pp.33–40 (2004)Google Scholar
- 12.Wang, Y., Gelly, S.: Modifications of UCT and sequence-like simulations for Monte-Carlo Go. In: IEEE Symposium on Computational Intelligence and Games, pp. 175–182 (2007)Google Scholar
- 13.Wu, R., Beal, D.F.: A Memory Efficient Retrograde Algorithm and Its Application To Chess Endgames. In: More Games of No Chance, vol. 42. MSRI Publication (2002)Google Scholar
- 14.Zobrist: Feature. Extraction and Representation for Pattern Recognition and the Game of Go. PhD thesis, University of Wisconsin (1970)Google Scholar