A further remark on dynamic programming for partially observed Markov processes

被引：16

作者：

Borkar, VS

Budhiraja, A

机构：

[1] Tata Inst Fundamental Res, Sch Technol & Comp Sci, Bombay 400005, Maharashtra, India

[2] Univ N Carolina, Dept Stat, Chapel Hill, NC 27599 USA

来源：

STOCHASTIC PROCESSES AND THEIR APPLICATIONS | 2004年 / 112卷 / 01期

关键词：

controlled Markov processes; dynamic programming; partial observations; ergodic cost; vanishing discount; pseudo-atom;

D O I：

10.1016/j.spa.2004.01.011

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

In (Stochastic Process. Appl. 103 (2003) 293), a pair of dynamic programming inequalities were derived for the 'separated' ergodic control problem for partially observed Markov processes, using the 'vanishing discount' argument. In this note, we strengthen these results to derive a single dynamic programming equation for the same. (C) 2004 Elsevier B.V. All rights reserved.

引用

页码：79 / 93

页数：15

共 14 条

[1]

[Anonymous], 1991, PITMAN RES NOTES MAT

[2]

Borkar V. S., 1989, Pitman Research Notes in Math. Series, V203

[3] WHITE-NOISE REPRESENTATIONS IN STOCHASTIC-REALIZATION THEORY [J].