Combiner connaissances expertes, hors-ligne, transientes et en ligne pour l'exploration Monte-Carlo: Apprentissage et MC

Revue d'Intelligence Artificielle

Volumn 23, Issue 2-3, 2009, Pages 203-220

  Chaslot, Guillaume ^a   Chatriot, Louis ^a   Fiter, Christophe ^a   Gelly, Sylvain ^a   Hoock, Jean Baptiste ^a   Perez, Julien ^a   Rimmel, Arpad ^a   Teytaud, Olivier ^a  

^a CNRS   (France)

Author keywords

Combining predictors; Expert knowledge; Monte Carlo tree search; Offline learning; Online learning; Transient learning

Indexed keywords

DATA MINING; E-LEARNING; INTELLIGENT SYSTEMS; LEARNING SYSTEMS;

COMBINING PREDICTORS; EXPERT KNOWLEDGE; MONTE-CARLO TREE SEARCHES; OFF-LINE LEARNING; ONLINE LEARNING;

MONTE CARLO METHODS;

EID: 77954370188     PISSN: 0992499X     EISSN: None     Source Type: Journal    
DOI: 10.3166/ria.23.203-220     Document Type: Article

References (18)

1. Agrawal R., « The Continuum-Armed Bandit Problem», SIAM J. Control Optim., vol. 33, no 6, p. 1926-1951, 1995.
2. Auer P., Cesa-Bianchi N., Fischer P., « Finite-time analysis of the multiarmed bandit problem», Machine Learning, vol. 47, no 2/3, p. 235-256, 2002.
3. Banks J. S., Sundaram R. K., « Denumerable-Armed Bandits », Econometrica, vol. 60, no 5, p. 1071-96, September, 1992. available at http://ideas.repec.org/a/ecm/emetrp/v60y1992i5p1071-96.html.
4. Bouzy B., « Associating domain-dependent knowledge and Monte-Carlo approaches within a go program », vol. 175, no 4, p. 247-257, 2005.
5. Bouzy B., Chaslot G., « Bayesian generation and integration of k-nearest-neighbor patterns for 19×19 Go », G. Kendall and Simon Lucas, editors, IEEE 2005 Symposium on Computational Intelligence in Games, Colchester, UK, p. 176-181, 2005.
6. Bouzy B., Helmstetter B., « Monte Carlo go developments », in E. A. Heinz, H. J. van den Herik, H. Iida (eds), 10th Advances in Computer Games, Kluwer Academic Publishers, p. 159-174, 2003.
7. Bruegmann B., « Monte-Carlo Go », Unpublished, 1993.
8. Chaslot G., Saito J.-T., Bouzy B., Uiterwijk J. W. H. M., van den Herik H. J., « Monte-Carlo Strategies for Computer Go », in P.-Y. Schobbens, W. Vanhoof, G. Schwanen (eds), Proceedings of the 18th BeNeLux Conference on Artificial Intelligence, Namur, Belgium, p. 83-91, 2006.
9. Chaslot G., Winands M., Uiterwijk J., van den Herik H., Bouzy B., « Progressive Strategies for Monte-Carlo Tree Search », in P. Wang et al. (eds), Proceedings of the 10th Joint Conference on Information Sciences (JCIS 2007), World Scientific Publishing Co. Pte. Ltd., p. 655-661, 2007.
10. Coquelin P.-A., Munos R., « Bandit Algorithms for Tree Search », Proceedings of UAI'07, 2007.
11. Coulom R., « Efficient Selectivity and Backup Operators in Monte-Carlo Tree Search », In P. Ciancarini and H. J. van den Herik, editors, Proceedings of the 5th International Conference on Computers and Games, Turin, Italy, 2006.
12. Coulom R., « Computing Elo Ratings of Move Patterns in the Game of Go », Computer Games Workshop, Amsterdam, The Netherlands, 2007.
13. Dani V., Hayes T. P., « Robbing the bandit: less regret in online geometric optimization against an adaptive adversary », SODA '06: Proceedings of the seventeenth annual ACM-SIAM symposium on Discrete algorithm, ACM Press, New York, NY, USA, p. 937-943, 2006.
14. Gelly S., Silver D., « Combining online and offline knowledge in UCT », ICML '07: Proceedings of the 24th international conference on Machine learning, ACM Press, New York, NY, USA, p. 273-280, 2007.
15. Kocsis L., Szepesvari C., « Bandit-based Monte-Carlo Planning », ECML'06, p. 282-293, 2006.
16. Lai T., Robbins H., « Asymptotically efficient adaptive allocation rules », Advances in applied mathematics, vol. 6, p. 4-22, 1985.
17. Ralaivola L., Wu L., Baldi P., « SVM and pattern-enriched common fate graphs for the game of Go », Proceedings of ESANN 2005, p. 485-490, 2005.
18. Wang Y., Gelly S., « Modifications of UCT and sequence-like simulations for Monte-Carlo Go », IEEE Symposium on Computational Intelligence and Games, Honolulu, Hawaii, p. 175-182, 2007.