Study of neural network disturbance learning and application in RoboCup

作     者：彭军 Wu Ming Guo Rui Kuo-chi Lin 

作者机构：School of Information Science and Engineering Central South University Changsha 410075 P.R.China Institute for Simulation and Training University of Central Florida Orlando FL32826 U.S.A. 

出 版 物：《High Technology Letters》 (高技术通讯（英文版）)

年 卷 期：2007年第13卷第2期

页      面：203-206页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：国家高技术研究发展计划(863计划)(2001AA4422200) 

主　　题：machine learning neural networks RoboCup 

摘      要：To solve the problem of convergence to a local optimum in the multi-layer feedforward neural net-work, a new disturbance gradient algorithm is proposed. Through introducing random disturbance into the training process, the algorithm can avoid being trapped into the local optimum. The random disturbance obeys the Boltzmann distribution. The convergence of the algorithm to the global optimum is statistically guaranteed. The application of the algorithm in RoboCup, which is a complex multi-agent system, is dis-cussed. Experiment results illustrate the learning efficiency and generalization ability of the proposed al-gorithm.