引用本文:吴耿锋,傅忠谦.基于增强型算法并能自动生成规则的模糊神经网络控制器[J].控制理论与应用,2001,18(2):241~244.[点击复制]
WU Geng-feng,FU Zhong-qian.Reinforcement Based Fuzzy Neural Network Control with Automatic Rule Generation[J].Control Theory and Technology,2001,18(2):241~244.[点击复制]
基于增强型算法并能自动生成规则的模糊神经网络控制器
Reinforcement Based Fuzzy Neural Network Control with Automatic Rule Generation
摘要点击 1423  全文点击 1526  投稿时间：1999-01-19  修订日期：2000-04-13
查看全文  查看/发表评论  下载PDF阅读器
DOI编号  
  2001,18(2):241-244
中文关键词  增强型学习  规则生成  神经网络  模糊控制器
英文关键词  reinforcement learning  rule generation  neural network  fuzzy controller
基金项目  
作者单位
吴耿锋 上海大学 计算机学院, 上海 200072 
傅忠谦 中国科技大学 电子科学技术系, 合肥 230026 
中文摘要
      给出了一种基于增强型算法并能自动生成控制规则的模糊神经网络控制器RBFNNC(reinforcements based fuzzy neural network controller). 该控制器能根据被控对象的状态通过增强型学习自动生成模糊控制规则. RBFNNC用于倒立摆小车平衡系统控制的仿真实验表明了该系统的结构及增强型学习算法是有效和成功的.
英文摘要
      A reinforcement based fuzzy neural network controller(RBFNNC) is proposed. A set of optimised fuzzy control rules can be automatically generated through reinforcement learning based on the state variables of object system. RBFNNC was applied to a cart pole balancing system and shows significant improvements on the rule generation.