%0 Journal Article
%T Fuzzy cerebellar model arithmetic controller with automatic state partition for value function approximation<br>一种状态自动划分的模糊小脑模型关节控制器值函数拟合方法
%A MIN Hua-qing
%A ZENG Jia-an
%A LUO Rong-hua
%A ZHU Jin-hui
%A <br>闵华清
%A 曾嘉安
%A 罗荣华
%A 朱金辉
%J 控制理论与应用
%D 2011
%I 
%X In continuous-state space or large discrete-state space, the reinforcement learning (RL) uses function approximation approaches to represent the value function in seeking the optimal policy. However the structures of function approximators which will greatly influence the learning performance are often designed in advance. To generate the structure of function approximator automatically, a novel function approximator called the automatic state-partition-based fuzzy cerebellar model arithmetic controller (ASP-FCMAC) is proposed. In ASP-FCMAC, the variation tendency of Bellman error is used to determine the best time to perform state partition and two mechanisms are also discussed for determining which state should be partitioned at each time step. Experimental results in solving mountain car problem and RoboCup Keepaway problem demonstrate that ASP-FCMAC can automatically generate the structure of FCMAC for effective reinforcement learning.
%K reinforcement learning
%K value function
%K automatic state partition
%K fuzzy CMAC<br>强化学习
%K 值函数
%K 状态自动划分
%K 模糊小脑关节模型控制器
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=970898A57DFC021F93AB51667BAED7F7&aid=F4AA7FD8CB6EA9C62EBDE225C1CA2BF8&yid=9377ED8094509821&vid=D3E34374A0D77D7F&iid=0B39A22176CE99FB&sid=80BD0A2EF8664214&eid=89AC6B0ADBEA2741&journal_id=1000-8152&journal_name=控制理论与应用&referenced_num=0&reference_num=8