Nonstationary Policies and Average Optimality in Multichain Markov Decision Processes with a General Action Space

被引：0
作者：
A. Y. Golubin
机构：
[1] Institute of Electronics and Mathematics,
来源：
Journal of Mathematical Sciences | 2004年 / 123卷 / 1期
关键词：
Decision Process; General Action; Action Space; Markov Decision Process; Average Optimality;
D O I：
10.1023/B:JOTH.0000036314.29733.3d
中图分类号：
学科分类号：
摘要：
引用
收藏
页码：3733 / 3740
页数：7
相关论文
共 15 条
  • [1] Arapostathis A.(1993)Discrete-time controlled Markov processes with average cost criterion SIAM J. Contr. Optim. 31 282-344
  • [2] Borkar V. S.(1968)Multichain Markov renewal programs SIAM J. Appl. Math. 16 468-487
  • [3] Fernandez-Gaucherand E.(1978)The existence of a stationary "εoptimal policy for a finite Markov chain Teor. Veroyatn. Primen. 23 297-313
  • [4] Ghosh M. K.(1967)Existence of stationary optimal policies for some Markov renewal programs SIAM Rev. 9 573-576
  • [5] Markus S. I.(1980)Mean value analysis of closed multichain queueing networks J.A.C.M. 27 313-322
  • [6] Denardo E. V.(1987)Control of service rates in networks of queues Adv. Appl. Probab. 19 202-218
  • [7] Fox B.(1977)Survey of measurable selection theorems SIAM J. Contr. Optim. 16 859-903
  • [8] Feinberg E. A.(1985)The optimality equations in multichain denumerable Markov decision processes with average cost criterion: The bounded cost case Statist. Decisions 3 143-165
  • [9] Fox B.(undefined)undefined undefined undefined undefined-undefined
  • [10] Lavenberg S. S.(undefined)undefined undefined undefined undefined-undefined
12