Risk-sensitive finite-horizon piecewise deterministic Markov decision processes

被引：6

作者：

Huang, Yonghui ^{[1
,3
]}

Lian, Zhaotong ^{[2
]}

Guo, Xianping ^{[1
,3
]}

机构：

[1] Sun Yat Sen Univ, Sch Math, Guangzhou 510275, Guangdong, Peoples R China

[2] Univ Macau, Fac Business Adm, Macau, Peoples R China

[3] Sun Yat Sen Univ, Guangdong Prov Key Lab Computat Sci, Guangzhou 510275, Guangdong, Peoples R China

来源：

OPERATIONS RESEARCH LETTERS | 2020年 / 48卷 / 01期

基金：

中国国家自然科学基金;

关键词：

Piecewise deterministic Markov decision processes; Risk sensitive; Finite horizon; Unbounded transition rates; HJB equation; Optimal policy;

D O I：

10.1016/j.orl.2019.05.001

中图分类号：

C93 [管理学]; O22 [运筹学];

学科分类号：

070105 ; 12 ; 1201 ; 1202 ; 120202 ;

摘要：

This paper deals with risk-sensitive piecewise deterministic Markov decision processes, where the expected exponential utility of a finite horizon reward is to be maximized. Both the transition rates and reward functions are allowed to be unbounded. Feynman-Kac's formula is developed in our setup, using which along with an approximation technique, we establish the associated Hamilton-Jacobi-Bellman equation and the existence of risk-sensitive optimal policies under suitable conditions. (C) 2019 Elsevier B.V. All rights reserved.

引用

页码：96 / 103

页数：8

共 50 条

[1] On Risk-Sensitive Piecewise Deterministic Markov Decision Processes
Guo, Xin
Zhang, Yi
[J]. APPLIED MATHEMATICS AND OPTIMIZATION, 2020, 81 (03): : 685 - 710
[2] On Risk-Sensitive Piecewise Deterministic Markov Decision Processes
Xin Guo
Yi Zhang
[J]. Applied Mathematics & Optimization, 2020, 81 : 685 - 710
[3] Risk-sensitive infinite-horizon discounted piecewise deterministic Markov decision processes
Yonghui Huang
Zhaotong Lian
Xianping Guo
[J]. Operational Research, 2022, 22 : 5791 - 5816
[4] Risk-sensitive infinite-horizon discounted piecewise deterministic Markov decision processes
Huang, Yonghui
Lian, Zhaotong
Guo, Xianping
[J]. OPERATIONAL RESEARCH, 2022, 22 (05) : 5791 - 5816
[5] Finite-horizon piecewise deterministic Markov decision processes with unbounded transition rates
Huang, Yonghui
Guo, Xianping
[J]. STOCHASTICS-AN INTERNATIONAL JOURNAL OF PROBABILITY AND STOCHASTIC PROCESSES, 2019, 91 (01) : 67 - 95
[6] Continuous-time Markov decision processes with risk-sensitive finite-horizon cost criterion
Wei, Qingda
[J]. MATHEMATICAL METHODS OF OPERATIONS RESEARCH, 2016, 84 (03) : 461 - 487
[7] Continuous-time Markov decision processes with risk-sensitive finite-horizon cost criterion
Qingda Wei
[J]. Mathematical Methods of Operations Research, 2016, 84 : 461 - 487
[8] Multiconstrained Finite-Horizon Piecewise Deterministic Markov Decision Processes with Unbounded Transition Rates
Huang, Yonghui
Guo, Xianping
[J]. MATHEMATICS OF OPERATIONS RESEARCH, 2020, 45 (02) : 641 - 659
[9] Risk probability optimization of finite horizon piecewise deterministic Markov decision processes
Huo, Haifeng
Wen, Xian
[J]. OPTIMIZATION, 2024,
[10] Finite-horizon variance penalised Markov decision processes
Collins E.J.
[J]. Operations-Research-Spektrum, 1997, 19 (1) : 35 - 39

← 1 2 3 4 5 →