A linear classifier outperforms UCT in 9×9 Go

Proceedings of the 2011 International Conference on Artificial Intelligence, ICAI 2011

Volumn 2, Issue , 2011, Pages 804-807

  Sylvester, N ^a   Lohre, B ^a   Dodson, S ^a   Drake, P ^a  

^a LEWIS AND CLARK COLLEGE   (United States)

Author keywords

Board game; Go; Machine learning; Monte Carlo methods; Neural network

Indexed keywords

BOARD GAMES; COMPUTER GO; GO; LINEAR CLASSIFIERS; MONTE CARLO; SEARCH TREES; TREE SEARCH; UPPER CONFIDENCE BOUND;

LEARNING SYSTEMS; NEURAL NETWORKS;

TREES (MATHEMATICS);

EID: 84858984504     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (11)

1. H. Baier and P. Drake. "The Power of Forgetting: Improving the Last-Good-Reply Policy in Monte-Carlo Go," in IEEE Transactions on Computational Intelligence and AI in Games, vol. 2, no. 4, pp. 303-309, 2010.
2. K. Baker. "The Way to Go." Internet: http://www.usgo.org/usa/ waytogo/index.asp, accessed June 5, 2011.
3. M. Enzenberger. "Evaluation in Go by a Neural Network Using Soft Segmentation," in Proceedings of the 10th Advances in Computer Games Conference, 2003, pp. 97-109.
4. S. Gelly and D. Silver. "Combining online and offline knowledge in UCT," in Proceedings of the 24th International Conference on Machine Learning, pp. 273-280.2007.
5. S. Gelly et al. "Modification of UCT with Patterns in Monte-Carlo Go," INRIA, France, 2006. pp. 1-21.
6. L. Kocsis and C. Szepesvái. "Bandit Based Monte-Carlo Planning," in Machine Learning: ECML 2006,1st ed., vol 4214. J. Furnkranz, T. Scheffer, and M. Spiliopoulou, Ed. Berlin: Springer. 2006, pp.282-293.
7. M. Müller. "Computer Go," in Artificial Intelligence, 2002, pp. 145-179.
8. A. Rimmel et al. "Current Frontiers in Computer Go," in IEEE Transactions on Computational Intelligence and Artificial Intelligence in Games, vol. 2, no. 4, pp. 229-238, 2010.
9. D. Rumelhart, J. McClelland. Parallel Distributed Processing. Cambridge, MA: The MIT Press, 1988.
10. S. Russell and P. Norvig. Artificial Intelligence: A Modern Approach. Saddle River, NJ: Pearson, 2003.
11. I. Sutskever and V. Nair. "Mimicking Go Experts with Convolutional Neural Networks," in Artificial Neural Networks - ICANN 2008,1st ed., vol. 5164. V. Kurková, R. Neruda, J. Koutník., Ed. Berlin: Springer, 2008, pp.101-110.