首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于马氏决策向量过程模型的有限阶段期望总报酬准则及其最优方程
引用本文:陈杰,刘再明,邢灵博.基于马氏决策向量过程模型的有限阶段期望总报酬准则及其最优方程[J].数学理论与应用,2011(4):7-13.
作者姓名:陈杰  刘再明  邢灵博
作者单位:琼州学院理工学院;中南大学数学科学与计算技术学院;
基金项目:琼州学院青年基金资助项目,编号QYQN201126
摘    要:在马氏决策向量过程模型的理论基础上,结合决策向量和相合度等新定义,进一步提出有限阶段期望总报酬准则和最优方程,并证明最优方程的解的存在性.

关 键 词:马氏决策向量过程模型  报酬准则  最优方程  存在性

The Finite Stage of Expected Totall Reward Model and Optimality Equation of Markov in Decision-making Vector Processes
Chen Jie Liu Zaiming Xing Lingbo.The Finite Stage of Expected Totall Reward Model and Optimality Equation of Markov in Decision-making Vector Processes[J].Mathematical Theory and Applications,2011(4):7-13.
Authors:Chen Jie Liu Zaiming Xing Lingbo
Institution:Chen Jie1 Liu Zaiming2 Xing Lingbo1(1.College of Science and Engineering,Qiongzhou University,Sanya 572022,China)(2.School of Mathematics,Central South University,Changsha 410075)
Abstract:By applying Markov decision-making vector processes theory and the new definition of decision-making vector,consistency degree,ETC.This paper will study the finite stage of expected totall reward model and optimality equation in Markov decision-making vector processes.Finally we proved the existence of solutions in the optimality equation.
Keywords:Markov decision-making vector processes Expected totall reward model Optimality equation Existence  
本文献已被 CNKI 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号