Abstract
In UCT algorithm, a large number of Monte-Carlo simulations are performed and their rewards are averaged to evaluate a specified action. In this paper, we propose a general approach to enhance the UCT algorithm with knowledge-based neural controllers by adjusting the probability distribution of UCT simulations. Experimental results on Dead End, the classical predator/prey game, show that our approach improves the performance of UCT significantly.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Gelly, S., Wang, Y.: Exploration exploitation in Go: UCT for Monte-Carlo Go. In: NIPS: Neural Information Processing Systems Conference On-line trading of Exploration and Exploitation Workshop (December 2006)
Chen, K.H., Zhang, P.: Monte-carlo go with knowledge-guided simulations. ICGA Journal 31(2), 67–76 (2008)
Gelly, S., Silver, D.: Combining online and offline knowledge in UCT. In: International Conference on Machine Learning, ICML 2007 (2007)
Billings, D., Davidson, A., Schaeffer, J., Szafron, D.: The challenge of poker. Artif. Intell. 134(1-2), 201–240 (2002)
Kearns, M., Mansour, Y., Ng, A.Y.: A sparse sampling algorithm for near-optimal planning in large markov decision processes, vol. 49, pp. 193–208 (2002)
Chaslot, G., Winands, M., van den Herik, J.H., Uiterwijk, J., Bouzy, B.: Progressive strategies for Monte-Carlo tree search. In: Joint Conference on Information Sciences, Salt Lake City (2007)
Yannakakis, G., Yannakakis, G.N., Levine, J.: An evolutionary approach for interactive computer games. In: Proceedings of the Congress on Evolutionary Computation (CEC 2004), pp. 986–993. IEEE, Los Alamitos (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Xie, F., Liu, Z., Wang, Y., Huang, W., Wang, S. (2010). Systematic Improvement of Monte-Carlo Tree Search with Self-generated Neural-Networks Controllers. In: Blum, C., Battiti, R. (eds) Learning and Intelligent Optimization. LION 2010. Lecture Notes in Computer Science, vol 6073. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-13800-3_25
Download citation
DOI: https://doi.org/10.1007/978-3-642-13800-3_25
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-13799-0
Online ISBN: 978-3-642-13800-3
eBook Packages: Computer ScienceComputer Science (R0)