Application of Monte-Carlo Tree Search in Tsumego of Computer Go

Fang Wang; Ying Peng

doi:10.4028/www.scientific.net/AMM.239-240.1344

Paper Titles

An Anycast Routing Algorithm Based on the Combination of Genetic Algorithm and Ant Colony Algorithm
p.1324

Trust-Based Particle Swarm Optimization for Grid Task Scheduling
p.1331

Image Fusion Using Wavelet Transform and Fuzzy Reasoning
p.1336

Study on Application of Genetic Algorithm in Maintenance Support Schedule
p.1340

Application of Monte-Carlo Tree Search in Tsumego of Computer Go
p.1344

Research on Improved Ant Colony Algorithm for the Optimization of the Large Storage Picking Path Based on RFID
p.1348

Position Estimation of Single Camera Visual System Based on Total Least Squares Algorithm
p.1352

Spectrum Measurement Network Based on Labview
p.1356

Area Partition-Based Suppression Algorithm for Contention-Based Forwarding in Mobile Ad-Hoc Networks
p.1360

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 239-240Application of Monte-Carlo Tree Search in Tsumego...

Application of Monte-Carlo Tree Search in Tsumego of Computer Go

Abstract:

The Tsumego problem in Go is a basic and essential problem to be overcome in implementing a computer Go program. This paper proposed a reality of Monte-Carlo tree search in Tsumego of computer Go which using Monte-Carlo evaluation as an alternative for a positional evaluation function. The advantage of this technique is that it requires few domain knowledge or expert input.

You might also be interested in these eBooks

Measurement Technology and its Application

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 239-240)

Pages:

1344-1347

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.239-240.1344

Citation:

Cite this paper

Online since:

December 2012

Authors:

Fang Wang, Ying Peng

Keywords:

Computer Go, Monte-Carlo Tree Search, Tsumego

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Bruno Bouzy. Associating domain-dependent knowledge and Monte Carlo approaches within a Go program. Joint Conference on Information Sciences (2003).

DOI: 10.1016/j.ins.2004.04.010

Google Scholar

[2] Bruno Bouzy. Associating shallow and selective global tree search with Monte Carlo for 9x9 Go. In K. Chen, editor, Proceedings of 4th Computer and Games Conference, RamatGan (2004).

DOI: 10.1007/11674399_5

Google Scholar

[3] Bruno Bouzy. Move pruning techniques for Monte-Carlo Go. In Proceedings of the 11th Advances in Computer Game conference, page 15 (2005).

Google Scholar

[4] Bruno Bouzy and Guillaume Chaslot. Monte-Carlo Go Reinforcement Learning Experiments. In IEEE 2006 Symposium on Computational Intelligence in Games, Reno, USA (2006).

DOI: 10.1109/cig.2006.311699

Google Scholar

[5] J. Burmeister, Studies in Human and Computer Go: Assessing the Game of Go as a Research Domain for Cognitive Science, PhD thesis, University of Queensland (2000).

DOI: 10.14264/262054c

Google Scholar

[6] R. Cant and J. Churchill and D. Al-Dabass, Using Hard and Soft Artificial Intelligence Algorithms to Simulate Human Go Playing Techniques, International Journal of Simulation, vol 2, no 1, pages 31-49 (2001).

Google Scholar

[7] Michael Chung, Michael Buro, and Jonathan Schaeffer. Monte-Carlo planning in RTS games. In Proceedings of the IEEE Symposium on Computational Intelligence and Games (2005).

Google Scholar

[8] Markus Enzenberger. Evaluation in Go by a neural network using soft segmentation. In Proceedings of the 10th Advances in Computer Games Conference, Graz (2003).

DOI: 10.1007/978-0-387-35706-5_7

Google Scholar

[9] Gerald Tesauro. Programming backgammon using self-teaching neural nets. Artificial Intelligence, 134: 181–199 (2002).

DOI: 10.1016/s0004-3702(01)00110-2

Google Scholar