A characterization of the optimal risk-sensitive average cost in finite controlled Markov chains

被引：29

作者：

Cavazos-Cadena, R ^{[1
]}

Hernández-Hernández, D

机构：

[1] Univ Autonoma Agraria Antonio Narro, Dept Estadist & Calculo, Saltillo 25315, Coahuila, Mexico

[2] Ctr Invest Matemat, Guanajuato 36000, GTO, Mexico

来源：

ANNALS OF APPLIED PROBABILITY | 2005年 / 15卷 / 1A期

关键词：

decreasing function along trajectories; stopping time; nearly optimal policies; Holder's inequality; simultaneous Doeblin condition; recurrent state;

D O I：

10.1214/105051604000000585

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：

This work concerns controlled Markov chains with finite state and action spaces. The transition law satisfies the simultaneous Doeblin condition, and the performance of a control policy is measured by the (long-run) risk-sensitive average cost criterion associated to a positive, but otherwise arbitrary, risk sensitivity coefficient. Within this context, the optimal risk-sensitive average cost is characterized via a minimization problem in a finite-dimensional Euclidean space.

引用

页码：175 / 212

页数：38

共 50 条

[21] Discounted Approximations for Risk-Sensitive Average Criteria in Markov Decision Chains with Finite State Space
Cavazos-Cadena, Rolando
Hernandez-Hernandez, Daniel
MATHEMATICS OF OPERATIONS RESEARCH, 2011, 36 (01) : 133 - 146
[22] Growth rates and average optimality in risk-sensitive Markov decision chains
Sladky, Karel
KYBERNETIKA, 2008, 44 (02) : 205 - 226
[23] Risk-sensitive probability for Markov chains
Ramezani, VR
Marcus, SI
SYSTEMS & CONTROL LETTERS, 2005, 54 (05) : 493 - 502
[24] Contractive Approximations in Risk-Sensitive Average Semi-Markov Decision Chains on a Finite State Space
Camilo-Garay, Carlos
Cavazos-Cadena, Rolando
Cruz-Suarez, Hugo
JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS, 2022, 192 (01) : 271 - 291
[25] Contractive Approximations in Risk-Sensitive Average Semi-Markov Decision Chains on a Finite State Space
Carlos Camilo-Garay
Rolando Cavazos-Cadena
Hugo Cruz-Suárez
Journal of Optimization Theory and Applications, 2022, 192 : 271 - 291
[26] Controlled Markov chains with risk-sensitive criteria:: Some (counter) examples
Brau-Rojas, A
Cavazos-Cadena, R
Fernández-Gaucherand, E
PROCEEDINGS OF THE 37TH IEEE CONFERENCE ON DECISION AND CONTROL, VOLS 1-4, 1998, : 1853 - 1858
[27] Controlled Markov chains with risk-sensitive criteria: Some (counter) examples
Brau-Rojas, Agustin
Cavazos-Cadena, Rolando
Fernandez-Gaucherand, Emmanuel
Proceedings of the IEEE Conference on Decision and Control, 1998, 2 : 1853 - 1858
[28] Discrete-time zero-sum games for Markov chains with risk-sensitive average cost criterion
Ghosh, Mrinal K.
Golui, Subrata
Pal, Chandan
Pradhan, Somnath
STOCHASTIC PROCESSES AND THEIR APPLICATIONS, 2023, 158 : 40 - 74
[29] Risk-sensitive optimal control for Markov decision processes with monotone cost
Borkar, VS
Meyn, SP
MATHEMATICS OF OPERATIONS RESEARCH, 2002, 27 (01) : 192 - 209
[30] Solution to the risk-sensitive average cost optimality equation in a class of Markov decision processes with finite state space
Cavazos-Cadena, R
MATHEMATICAL METHODS OF OPERATIONS RESEARCH, 2003, 57 (02) : 263 - 285

← 1 2 3 4 5 →