Application of Q-Learning and RBF Network in Chinese Chess Game System

Abstract

Machine game is one of the important directions of artificial intelligence research, and Chinese chess is a typical game process. This paper first introduces the game principle of Chinese chess. Then Q-learning method and evaluation function are added to train data through a large amount of self-learning. A chess game system based on Q-learning is designed and developed. The experimental results show that Chinese chess with Q-learning algorithm has the ability of evolutionary learning, which effectively improves the game level of Chinese chess.