Average cost dynamic programming equations for controlled Markov chains with partial observations

被引：43

作者：

Borkar, VS ^{[1
]}

机构：

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

来源：

SIAM JOURNAL ON CONTROL AND OPTIMIZATION | 2000年 / 39卷 / 03期

关键词：

average cost control; controlled Markov chains; partial observations; dynamic programming; vanishing discount limit;

D O I：

10.1137/S0363012998345172

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The value function for the average cost control of class of partially observed Markov chains is derived as the vanishing discount limit, in suitable sense, of the value functions for the corresponding discounted cost problems. The limiting procedure is justified by bounds derived using a simple coupling argument.

引用

页码：673 / 681

页数：9

共 9 条

[1] Dynamic programming for ergodic control of Markov chains under partial observations (vol 39, pg 673, 2000)
Borkar, Vivek S.
SIAM JOURNAL ON CONTROL AND OPTIMIZATION, 2007, 45 (06) : 2299 - 2304
[2] Controlled Markov chains with risk-sensitive criteria:: Average cost, optimality equations, and optimal solutions
Cavazos-Cadena, R
Fernández-Gaucherand, E
MATHEMATICAL METHODS OF OPERATIONS RESEARCH, 1999, 49 (02) : 299 - 324
[3] A dynamic programming approach for finite Markov processes and algorithms for the calculation of the limit matrix in Markov chains
Pickl, Stefan
Lozovanu, Dmitrii
OPTIMIZATION, 2011, 60 (10-11) : 1339 - 1358
[4] A new value iteration method for the average cost dynamic programming problem
Bertsekas, DP
SIAM JOURNAL ON CONTROL AND OPTIMIZATION, 1998, 36 (02) : 742 - 759
[5] DYNAMIC PROGRAMMING FOR CONTROLLED MARKOV FAMILIES: ABSTRACTLY AND OVER MARTINGALE MEASURES
Zitkovic, Gordan
SIAM JOURNAL ON CONTROL AND OPTIMIZATION, 2014, 52 (03) : 1597 - 1621
[6] DISCRETE-TIME CONTROLLED MARKOV-PROCESSES WITH AVERAGE COST CRITERION - A SURVEY
ARAPOSTATHIS, A
BORKAR, VS
FERNANDEZGAUCHERAND, E
GHOSH, MK
MARCUS, SI
SIAM JOURNAL ON CONTROL AND OPTIMIZATION, 1993, 31 (02) : 282 - 344
[7] INFINITE HORIZON AVERAGE COST DYNAMIC PROGRAMMING SUBJECT TO TOTAL VARIATION DISTANCE AMBIGUITY
Tzortzis, Ioannis
Charalambous, Charalambos D.
Charalambous, Themistoklis
SIAM JOURNAL ON CONTROL AND OPTIMIZATION, 2019, 57 (04) : 2843 - 2872
[8] ON THE STABILITY OF SOME CONTROLLED MARKOV CHAINS AND ITS APPLICATIONS TO STOCHASTIC APPROXIMATION WITH MARKOVIAN DYNAMIC
Andrieu, Christophe
Tadic, Vladislav B.
Vihola, Matti
ANNALS OF APPLIED PROBABILITY, 2015, 25 (01) : 1 - 45
[9] Value iteration in a class of average controlled Markov chains with unbounded costs: Necessary and sufficient conditions for pointwise convergence
CavazosCadena, R
FernandezGaucherand, E
JOURNAL OF APPLIED PROBABILITY, 1996, 33 (04) : 986 - 1002

← 1 →