Applying Artificial Neural Network combined with TD(λ) to Computer Chinese Chess

摘要：

This paper discusses whether Artificial Neural Network combined with TD(λ) method can be successfully applied to computer Chinese chess. Artificial Neural Network (ANN) is used to represent the evaluation function. Learning occurs by using TD(λ) algorithm on the results of high-level database games. Experiments show that the proposed technique can improve the performance of computer Chinese chess.

关键词： Computer Chinese chess Evaluation function Artificial neural network TD(λ)algorithm

作者: Jue Wang Ran Cheng Jiao Wang

作者单位: College of Information Science and Engineering, Northeastern University, Shenyang 110004

会议类型: 国际会议

会议名称: 2009年中国控制与决策会议(2009 Chinese Control and Decision Conference)

会议地点: 广西桂林

会议语种:英文

页码: 3207-3211

在线出版日期: 2009-06-17（万方平台首次上网日期，不代表论文的发表时间）