一种基于强化学习的ART2神经网络--RL-ART2  

A Reinforcement Learning Based ART2 Neural Network:RL-ART2

作　　者：樊建[1,2] 费敏锐[1] 

机构地区：[1]上海大学电站自动化技术重点实验室,上海200072 [2]南京陆军指挥学院作战实验中心,南京210045

出　　处：《模式识别与人工智能》2008年第3期357-362,共6页Pattern Recognition and Artificial Intelligence

基　　金：国家自然科学基金资助项目(No.60774059)

摘　　要：提出一种基于强化学习的 ART2神经网络(RL-ART2),使其利用强化学习的特性通过与环境交互而无需训练样本即可进行在线学习,同时给出该神经网络的学习算法.当 ART2神经网络运行时,通过内部竞争学习得到输出的分类模式,随后通过与环境交互得到神经网络分类模式的运行效果并对其进行评价.通过这种不断与环境的交互学习,当经过在线学习足够的时间和次数后,ART2神经网络即具有相当的识别率.移动机器人路径规划仿真实验表明,使用 RL-ART2后与未使用前相比大大减少了机器人与障碍物的碰撞次数,实践证明该方法的合理性和有效性.A reinforcement learning based ART2 neural network （ RL -ART2 ） is proposed and its learning algorithm is given. It is capable of online learning without training samples by using the characteristic of alteration with environment of reinforcement learning. In RL-ART2, the output classified pattern is got by inner competition of ART2, then the running effect of the classified pattern is gained and evaluated through altering with environment. With enough time of being online and interactive learning with environment, a certain recognition ratio of ART2 neural network is attained. The simulation results of path planning for mobile robot indicate that the collision times of robot is effectively decreased by using RL-ART2 . Moreover, the rationality and validity of RL-ART2 are also demonstrated by the results.

关 键 词：ART2神经网络 强化学习 分类模式 在线学习 避碰撞 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]