基于状态软集结的相对值迭代算法(英文)  

Relative Value Iteration Algorithm with Soft State Aggregation

作　　者：胡光华[1] 吴沧浦[1] 乔治.瑟彬珂 

机构地区：[1]北京理工大学自动控制系,北京100081 [2]达特茅斯学院工学院

出　　处：《控制理论与应用》2000年第3期415-418,共4页Control Theory & Applications

基　　金：Foundationitem :supportedbytheNationalNaturalScienceFoundationofChina (696740 0 5) .

摘　　要：在大规模随机控制问题中 ,值函数逼近是一种克服维数灾的方法 .考虑平均模型马氏决策规划 (MDP)的状态软集结相对值迭代算法 ,在Span压缩的条件下 ,证明了该算法的收敛性 ,同时还给出了其误差估计 .A straightforward way to dispel the curse of dimensionality in large stochastic control problems is to replace the lookup table with a generalized function approximator such as state aggregation. The relative value iteration algorithm for average reward Markov decision processes (MDP) with soft state aggregation is investigated. Under a condition of the contraction with span semi norm, the convergence of the proposed algorithm is proved and an error bound of the approximation is also given.

关 键 词：随机控制 状态软集结 相对值 迭代算法 

分 类 号：TP13[自动化与计算机技术—控制理论与控制工程]