Monte Carlo go has a way to go

Authors:
Haruhiro Yoshimoto;Kazuki Yoshizoe;Tomoyuki Kaneko;Akihiro Kishimoto;Kenjiro Taura
Affiliations:
Department of Information and Communication Engineering, University of Tokyo, Japan;Graduate School of Information Science and Technology, University of Tokyo, Japan;Department of Graphics and Computer Sciences, University of Tokyo, Japan;Department of Media Architecture, Future University-Hakodate, Japan;Department of Information and Communication Engineering, University of Tokyo, Japan
Venue:
AAAI'06 proceedings of the 21st national conference on Artificial intelligence - Volume 2
Year:
2006

Citing 9
Cited 0

Measuring the performance potential of chess programs

Artificial Intelligence - Special issue on computer chess
Expected-Outcome: A General Model of Static Evaluation

IEEE Transactions on Pattern Analysis and Machine Intelligence
A high-performance, portable implementation of the MPI message passing interface standard

Parallel Computing
Computer Go

Artificial Intelligence - Chips challenging champions: games, computers and Artificial Intelligence
The challenge of poker

Artificial Intelligence - Chips challenging champions: games, computers and Artificial Intelligence
World-championship-caliber Scrabble

Artificial Intelligence - Chips challenging champions: games, computers and Artificial Intelligence
GIB: Steps Toward an Expert-Level Bridge-Playing Program

IJCAI '99 Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence
Associating domain-dependent knowledge and Monte Carlo approaches within a Go program

Information Sciences: an International Journal
Associating shallow and selective global tree search with monte carlo for 9 × 9 go

CG'04 Proceedings of the 4th international conference on Computers and Games

Quantified Score

Hi-index	0.00

Visualization

Abstract

Monte Carlo Go is a promising method to improve the performance of computer Go programs. This approach determines the next move to play based on many Monte Carlo samples. This paper examines the relative advantages of additional samples and enhancements for Monte Carlo Go. By parallelizing Monte Carlo Go, we could increase sample sizes by two orders of magnitude. Experimental results obtained in 9 × 9 Go show strong evidence that there are trade-offs among these advantages and performance, indicating a way for Monte Carlo Go to go.