Title: Reinforcement learning for training a computer program of Chinese chess

Authors: Wing-Kwong Wong, Han-Hung Chen, Sheng-Cheng Hsu

Addresses: Department of Electronic Engineering, National Yunlin University of Science and Technology, No. 123, University Road, Section 3, Douliou, Yunlin 64002, Taiwan. ' Institute of Computer Science and Information Engineering, National Yunlin University of Science and Technology, No. 123, University Road, Section 3, Douliou, Yunlin 64002, Taiwan. ' Department of Information Management, Nan Kai University of Technology, No. 568, Chungcheng Road, Caotun, Nantou 542, Taiwan

Abstract: Computer chess has always been an interesting subject in artificial intelligence (AI). We propose a method to design a Chinese chess program that improves its performance through training. In this study, we utilise temporal-difference learning, which is a method of reinforcement learning, where each position receives reward value from the next position and the value of the position is modified by a heuristic evaluation function. The experimental results show that the program indeed improved its performance by reinforcement learning.

Keywords: reinforcement learning; Chinese chess; intelligent information systems; computer chess; performance improvement; training; temporal-difference learning.

DOI: 10.1504/IJIIDS.2009.027685

International Journal of Intelligent Information and Database Systems, 2009 Vol.3 No.3, pp.246 - 258

Published online: 07 Aug 2009 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article