Verifiable conditions for average optimality of continuous-time Markov decision processes

被引：0
|
作者：
Zou, Xiaolong [1 ]
Huang, Yonghui [2 ]
机构：
[1] Guangzhou Univ, Sch Econ & Stat, Guangzhou 510006, Guangdong, Peoples R China
[2] Sun Yat Sen Univ, Sch Math, Guangzhou 510275, Guangdong, Peoples R China
来源：
OPERATIONS RESEARCH LETTERS | 2016年 / 44卷 / 06期
关键词：
Continuous-time Markov decision processes; Average reward criterion; Unbounded transition rates; Optimal stationary policy; New optimality condition;
D O I：
10.1016/j.orl.2016.09.007
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：
In this paper we provide another set of verifiable conditions for the average optimality of continuous time Markov decision processes (CTMDP) in Polish spaces with unbounded transition rates. Under the new conditions which are imposed on the primitive data of the model of the CTMDP and thus easy to verify, we also establish the existence of an average optimal stationary policy. Finally, we propose two examples to illustrate the newness of the conditions. (C) 2016 Elsevier B.V. All rights reserved.
引用
收藏
页码：742 / 746
页数：5
相关论文
共 50 条
  • [31] LOGARITHMIC REGRET BOUNDS FOR CONTINUOUS-TIME AVERAGE-REWARD MARKOV DECISION PROCESSES
    Gao, Xuefeng
    Zhou, Xun Yu
    SIAM Journal on Control and Optimization, 2024, 62 (05) : 2529 - 2556
  • [32] Policy Iteration for Continuous-Time Average Reward Markov Decision Processes in Polish Spaces
    Zhu, Quanxin
    Yang, Xinsong
    Huang, Chuangxia
    ABSTRACT AND APPLIED ANALYSIS, 2009,
  • [33] Risk-sensitive average continuous-time Markov decision processes with unbounded rates
    Wei, Qingda
    Chen, Xian
    OPTIMIZATION, 2019, 68 (04) : 773 - 800
  • [34] Asymptotic Optimality and Rates of Convergence of Quantized Stationary Policies in Continuous-Time Markov Decision Processes
    Wu, Xiao
    Tang, Yanqiu
    DISCRETE DYNAMICS IN NATURE AND SOCIETY, 2022, 2022
  • [35] FINITE-HORIZON OPTIMALITY FOR CONTINUOUS-TIME MARKOV DECISION PROCESSES WITH UNBOUNDED TRANSITION RATES
    Guo, Xianping
    Huang, Xiangxiang
    Huang, Yonghui
    ADVANCES IN APPLIED PROBABILITY, 2015, 47 (04) : 1064 - 1087
  • [36] ANOTHER SET OF VERIFIABLE CONDITIONS FOR AVERAGE MARKOV DECISION PROCESSES WITH BOREL SPACES
    Zou, Xiaolong
    Guo, Xianping
    KYBERNETIKA, 2015, 51 (02) : 276 - 292
  • [37] The Transformation Method for Continuous-Time Markov Decision Processes
    Piunovskiy, Alexey
    Zhang, Yi
    JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS, 2012, 154 (02) : 691 - 712
  • [38] Impulsive control for continuous-time Markov decision processes
    Université Bordeaux, IMB, INRIA Bordeaux Sud-Ouest, 200 Avenue de la Vieille Tour, Talence Cedex
    33405, France
    不详
    L69 7ZL, United Kingdom
    Adv Appl Probab, 1 (106-127):
  • [39] IMPULSIVE CONTROL FOR CONTINUOUS-TIME MARKOV DECISION PROCESSES
    Dufour, Francois
    Piunovskiy, Alexei B.
    ADVANCES IN APPLIED PROBABILITY, 2015, 47 (01) : 106 - 127
  • [40] Continuous-Time Markov Decision Processes with Controlled Observations
    Huang, Yunhan
    Kavitha, Veeraruna
    Zhu, Quanyan
    2019 57TH ANNUAL ALLERTON CONFERENCE ON COMMUNICATION, CONTROL, AND COMPUTING (ALLERTON), 2019, : 32 - 39
12345