%0 Journal Article
%T CMAC application using triangulation in reinforcement learning<br>基于三角剖分的小脑模型在增强学习中的应用
%A SUN Fang-yi
%A ZHENG Zhi-qiang
%A <br>孙方义
%A 郑志强
%J 计算机应用
%D 2009
%I 
%X A reinforcement learning controller based on CMAC neural networks using triangulation was studied and applied to the learning control of intercepting a ball in the RoboCup.By utilizing Kuhn triangulation based on simplex interpolation in the continuous state space of Markov Decision Processes(MDPs),the value functions of MDPs were approximated with linear triangulation so that the generalization ability of the CMAC-based reinforcement learning controller could be improved.Simulation results on the learning ...
%K reinforcement learning
%K Cerebellar Model Articulation Controller(CMAC)
%K Kuhn triangulation
%K Markov decision process<br>增强学习
%K 小脑模型关节控制器
%K 库恩三角化
%K Markov决策过程
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=831E194C147C78FAAFCC50BC7ADD1732&aid=8BA48B030FF11E210AA3B6831060872E&yid=DE12191FBD62783C&vid=771469D9D58C34FF&iid=38B194292C032A66&sid=1F8584045E0BED57&eid=BF1420E7E18952EE&journal_id=1001-9081&journal_name=计算机应用&referenced_num=0&reference_num=8