Title :
A parallel computer-Go player, using HDP method
Author :
Cai, Xindi ; Wunsch, Donald C., II
Author_Institution :
Dept. of Electr. & Comput. Eng., Missouri Univ., Rolla, MO, USA
Abstract :
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 19×19 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 19×19 board
Keywords :
dynamic programming; games of skill; learning (artificial intelligence); neural nets; parallel processing; search problems; Go game; alpha-beta search; evaluation functions; heuristic dynamic programming; learning algorithms; neural network; parallel search; Books; Computational intelligence; Concurrent computing; Dynamic programming; Laboratories; Law; Legal factors; Machine learning algorithms; Neural networks; Testing;
Conference_Titel :
Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-7044-9
DOI :
10.1109/IJCNN.2001.938737
