Abstract
Go gaming automation is AI relevant because during a match the search space is enormous and the game tree size is around10360, versus the 10123 for Chess. Thus, finding out methods providing efficient solutions to, is truly relevant. The Monte-Carlo-based approaches have leading Go gaming automation but efficiency is distant: to strengthen on efficiency, a hybrid automated Go player Neural-Networks-based for learning and recognition on tactics/strategic patterns, in average, during the first 2/3 parts of a match is introduced; by the remaining match’s part it uses RAVE Monte-Carlo Tree Search (MCTS). Results on the precision of pattern recognition and a comparison against competitive automated Go players are presented.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Chen, K., Chen, Z.: Static Analysis of Life and Death in the Game of Go. Information Sciences 121(1), 113–134 (1999)
Allis, L.V.: Searching for Solutions in Games and Artificial Intelligence. PhD Thesis. University of Limburg, The Netherlands (1994)
McCarthy, J.: AI as sport. Science 276(5318), 1518–1519 (1997)
Benson, D.B.: Life in the game of Go. Information Sciences 10(2), 17–29 (1976)
Yoshiaki, N.: Strategic Concepts of Go. Ishi Press (1972)
Müller, M.: Computer Go. Artificial Intelligence 134(1), 145–179 (2002)
Richards, N., Moriarty, D.E., Miikkulainen, R.: Evolving Neural Networks to Play Go. Applied Intelligence 8(1), 85–96 (1998)
van der Werf, E.C.D., van den Herik, H.J., Uiterwijk, J.W.H.M.: Learning to Estimate Potential Territory in the Game of Go. In: van den Herik, H.J., Björnsson, Y., Netanyahu, N.S. (eds.) CG 2004. LNCS, vol. 3846, pp. 81–96. Springer, Heidelberg (2006)
Bouzy, B., Cazenave, T.: Computer Go(An AI Oriented Survey. Artificial Intelligence 132(1), 39–103 (2001)
Dahl, F.A.: Honte, a Go-Playing Program Using Neural Nets. Machines that Learn to Play Games, pp. 205–223. Nova Science Publishers, Inc. (2001)
Jianming, L., Difei, Z., Rui, L.: Improve Go AI based on BP-Neural Network. In: 2008 IEEE Conference on Cybernetics and Intelligent Systems (CIS 2008), pp. 487–490. IEEE (2008)
Browne, C.B., Powley, E., Whitehouse, D., Lucas, S.M., Cowling, P.I., Rohlfshagen, P., Tavener, S., Perez, D., Samothrakis, S., Colton, S.: A Survey of Monte Carlo Tree Search Methods. IEEE Transactions on Computational Intelligence and AI in Games 4(1), 1–49 (2012)
Chaslot, G., Bakkes, S., Szita, I., Spronck, P.: Monte-Carlo Tree Search A New Framework for Game AI. In: 4th Artificial Intelligence Interactive Digital Entertainment Conference (AIIDE 2008), pp. 216–217. AAAI (2008)
Gelly, S., Silver, D.: Monte-Carlo Tree Search and Rapid Action Value Estimation in Computer Go. Artificial Intelligence 175(11), 1856–1875 (2011)
Gelly, S., Kocsis, L., Schoenauer, M., Sebag, M., Silver, D., Szepesvari, C., Teytaud, O.: The Grand Challenge of Computer Go Monte Carlo Tree Search and Extensions. Communication of the ACM 55(3), 106–113 (2012)
Berlekamp, E.R., Wolfe, D.: Mathematical Go Chilling Gets the Last Point. A K Peters Ltd. (1997)
Yee, A., Alvarado, M.: Formal Language and Reasoning for Playing Go. In: 7th Latin American Workshop on Logic / Languages, Algorithms and New Methods of Reasoning (LANMR 2011). CEUR Workshop Proceedings, pp. 125–132 (2011)
Shi-Jim, Y., Tai-Ning, Y., Chang, C., Shun-Chin, H.: Pattern Matching in Go Game Records. In: 2nd International Conference on Innovative Computing, Information and Control (ICICIC 2007), pp. 297:14. IEEE (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Yee, A., Alvarado, M. (2012). Pattern Recognition and Monte-CarloTree Search for Go Gaming Better Automation. In: Pavón, J., Duque-Méndez, N.D., Fuentes-Fernández, R. (eds) Advances in Artificial Intelligence – IBERAMIA 2012. IBERAMIA 2012. Lecture Notes in Computer Science(), vol 7637. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-34654-5_2
Download citation
DOI: https://doi.org/10.1007/978-3-642-34654-5_2
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-34653-8
Online ISBN: 978-3-642-34654-5
eBook Packages: Computer ScienceComputer Science (R0)