The game of Go has simple rules to learn but requires complex strategies to play well, and, the conventional tree search algorithm for computer games is not suited for Go program. Thus, the game of Go is an ideal problem domain for machine learning algorithms. This paper examines the performance of a 19x19 computer Go player, using heuristic dynamic programming (HDP) and parallel alpha-beta search. The neural network based Go player learns good Go evaluation functions and wins about 30% of the games in a test series on 19x19 board
D. C. Wunsch and X. Cai, "A Parallel Computer-Go Player, using HDP Method," Proceedings of the International Joint Conference on Neural Networks, 2001. IJCNN '01, Institute of Electrical and Electronics Engineers (IEEE), Jan 2001.
The definitive version is available at http://dx.doi.org/10.1109/IJCNN.2001.938737
International Joint Conference on Neural Networks, 2001. IJCNN '01
Electrical and Computer Engineering
Keywords and Phrases
Go Game; Alpha-Beta Search; Dynamic Programming; Evaluation Functions; Games of Skill; Heuristic Dynamic Programming; Learning (Artificial Intelligence); Learning Algorithms; Neural Nets; Neural Network; Parallel Processing; Parallel Search; Search Problems
Article - Conference proceedings
© 2001 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.