On the huge benefit of decisive moves in Monte-Carlo Tree Search algorithms

Proceedings of the 2010 IEEE Conference on Computational Intelligence and Games, CIG2010

Volumn , Issue , 2010, Pages 359-364

  Teytaud, Fabien ^a   Teytaud, Olivier ^a  

^a UFR 919 Laboratoire d'Informatique Pour la Mécanique et les Sciences de l'Ingénieur   (France)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTATIONAL EFFICIENCY; MONTE CARLO METHODS;

BOARD GAMES; COMPUTATIONAL OVERHEADS; HIGH-EFFICIENCY; MONTE CARLO TREE SEARCH (MCTS); MONTE-CARLO TREE SEARCHES; UPPER CONFIDENCE BOUND;

ARTIFICIAL INTELLIGENCE;

EID: 79960542525     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ITW.2010.5593334     Document Type: Conference Paper

References (33)

1. J.-Y Audibert, R. Munos, and C. Szepesvari. Use of variance estimation in the multi-armed bandit problem. In NIPS 20 Workhop on On-line Trading of Exloration and Eploitation, 2006.
2. P. Auer. Using confdence bounds for exploitation-exploration trade-ol. The Joural of Machine Learing Researh, 3:397-422, 2003.
3. A. Auger and O. Teytaud. Continuous lunches a f plus the design of optimal optimization algorithms. Algorithmica, Accepted.
4. B. Bruegmann. Monte-Carlo Go. Unpublished, 1993.
5. T. Cazenave. Nested monte-carlo search. In C. Boutilier, editor, JCAl, pages 456-46 1, 2009.
6. T. Cazenave and A. Safdine. Utilisation de la recherche arborescente monte-carlo au hex. Revue d 'Intelligence Artijcielle, 23(2-3): 183-202, 2009.
7. G. Chaslot, C. Fiter, J.-S. Hoock, A. Rimmel, and O. Teytaud. Adding expert knowledge and exploration in Monte-Carlo Tree Search. In Advances in Computer Games, Pampiona Espagne, 2009. Springer.
8. G. Chaslot, I.-T. Saito, B. Bouzy, I. W. H. M. Uiterwijk, and H. I. van den Herik. Monte-Carlo Strategies for Computer Go. In P.-Y. Schobbens, W. Vanhoof, and G. Schwanen, editors, Proceedings of the 18th BeNeLux Conference on Artificial Intelligence. Namur, Belgium, pages 83-91, 2006.
9. G. Chaslot, M. Winands, I. Uiterwijk, H. van den Herik, and B. Bouzy. Progressive strategies for monte-carlo tree search. In P. Wang et al., editors, Proceedings of the 10th Joint Conference on Information Sciences (JCIS 2(07), pages 655-661. World Scientific Publishing Co. Pte. Ltd., 2007.
10. R. Coulom. Efficient selectivity and backup operators in montecarlo tree search. In P. Ciancarini and H. J. van den Herik. editors. Proceedings of the 5th International Conference on Computers and Games. Turin. Italy, pages 72-83, 2006.
11. R. Coulom. Computing "elo ratings" of move patterns in the game of go. ICGA Journal, 30(4): 198-208, 2007.
12. M. Crasmaru. On the complexity of Tsume-Go. 1558:222-231, 1999.
13. M. Crasmaru and I. Tromp. Ladders are PSPACE-complete. In Computers and Games, pages 241-249, 2000.
14. F De Mesmay, A. Rimmel, Y. Voronenko, and M. Piischel. Bandit-Based Optimization on Graphs with Application to Library Performance Tuning. In ICML, MontnaI Canada, 2009.
15. Z. Galil and G. F. Italiano. Data structures and algorithms for disjoint set union problems. ACM Comput. Surv., 23(3):319-344, 1991.
16. S. Gelly and D. Silver. Combining online and offline knowledge in UCT. In ICML '07: Proceedings of the 24th international conference on Machine learning, pages 273-280, New York, NY, USA, 2007. ACM Press.
17. L. R. Harris. The heuristic search and the game of chess-a study of quiescene, sacrifices, and plan oriented play. In IJCAI, pages 334-339, 1975.
18. L. Kocsis and C. Szepesvari. Bandit based monte-carlo planning. In 15th European Conference on Machine Learning (ECML), pages 282-293, 2006. (Pubitemid 44618839)
19. T Lai and H. Robbins. Asymptotically efficient adaptive allocation rules. Advances in Applied Mathematics, 6:4-22, 1985.
20. C.-S. Lee, M.-H. Wang, G. Chaslot, I.-B. Hoock, A. Rimmel, O. Tey-taud, S.-R. Tsai, S.-c. Hsu, and T.-P. Hong. The Computational In telligence of MoGo Revealed in Taiwan's Computer Go Tournaments. IEEE Transactions on Computational Intelligence and AI in games, 2009.
21. R. I. Lorentz. Amazons discover monte-carlo. In CG '08: Proceedings of the 6th international conference on Computers and Games, pages 13-24, Berlin, Heidelberg, 2008. Springer-Verlag.
22. I. Nash. Some games and machines for playing them. Technical Report D-II64, Rand Corporation, 1952
23. Reisch. Hex is PSPACE-complete. ACTAINF: Acta Informatica, 15:167-191, 1981.
24. M. Robson. The complexity of go. In IFIP Congress, pages 413-417, 1983.
25. P. Rolet, M. Sebag, and O. Teytaud. Optimal active learning through billiards and upper confidence trees in continous domains. In Pro ceedings of the ECML conference, pages 302-317, 2009.
26. M. P. D. Schadd, M. H. M. Winands, H. I. van den Herik, G. Chaslot, and I. W. H. M. Uiterwijk. Single-player monte-carlo tree search. In H. I. van den Herik, X. Xu, Z. Ma, and M. H. M. Winands, editors, Computers and Games, volume 5131 of Lecture Notes in Computer Science, pages 1-12. Springer, 2008.
27. R. W. Schmittberger. New Rules for Classic Games. Wiley, 1992.
28. S. Sharma, Z. Kobti, and S. Goodwin. Knowledge generation for improving simulations in uct for general game playing. pages 49-55. 2008.
29. F Teytaud and O. Teytaud. Creating an Upper-Confidence-Tree program for Havannah. In ACG 12, pages 65-74, Pamplona Espagne, 2009.
30. Y. Wang, I.-Y Audibert, and R. Munos. Algorithms for infinitely many-armed bandits. In Advances in Neural Information Processing Systems, volume 21, 2008.
31. y Wang and S. Gelly. Modifications of UCT and sequence-like simulations for Monte-Carlo Go. In IEEE Symposium on Computational Intelligence and Games. Honolulu. Hawaii, pages 175-182, 2007. (Pubitemid 47431300)
32. Wikipedia. Havannah, 2009.
33. S. Zilberstein. Resource-bounded reasoning in intelligent systems. Computing Surveys, 28(4), 1996.