Non-randomized policies for constrained Markov decision processes

被引：18
|
作者：
Chen, Richard C.
Feinberg, Eugene A.
机构：
[1] USN, Res Lab, Div Radar, Washington, DC 20375 USA
[2] SUNY Stony Brook, Dept Appl Math & Stat, Stony Brook, NY 11794 USA
来源：
MATHEMATICAL METHODS OF OPERATIONS RESEARCH | 2007年 / 66卷 / 01期
关键词：
constrained Markov; decision processes; dynamic programming; non-randomized policies;
D O I：
10.1007/s00186-006-0133-x
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 addresses constrained Markov decision processes, with expected discounted total cost criteria, which are controlled by non-randomized policies. A dynamic programming approach is used to construct optimal policies. The convergence of the series of finite horizon value functions to the infinite horizon value function is also shown. A simple example illustrating an application is presented.
引用
收藏
页码：165 / 179
页数：15
相关论文
共 50 条
  • [1] Non-randomized policies for constrained Markov decision processes
    Richard C. Chen
    Eugene A. Feinberg
    [J]. Mathematical Methods of Operations Research, 2007, 66 : 165 - 179
  • [2] Non-randomized control of constrained Markov decision processes
    Chen, Richard C.
    Feinberg, Eugene A.
    [J]. 2006 AMERICAN CONTROL CONFERENCE, VOLS 1-12, 2006, 1-12 : 1593 - +
  • [3] Robustness of policies in constrained Markov decision processes
    Zadorojniy, A
    Shwartz, A
    [J]. IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2006, 51 (04) : 635 - 638
  • [4] Compactness of the space of non-randomized policies in countable-state sequential decision processes
    Chen, Richard C.
    Feinberg, Eugene A.
    [J]. MATHEMATICAL METHODS OF OPERATIONS RESEARCH, 2010, 71 (02) : 307 - 323
  • [5] Compactness of the space of non-randomized policies in countable-state sequential decision processes
    Richard C. Chen
    Eugene A. Feinberg
    [J]. Mathematical Methods of Operations Research, 2010, 71 : 307 - 323
  • [6] Optimal policies for constrained average-cost Markov decision processes
    Juan González-Hernández
    César E. Villarreal
    [J]. TOP, 2011, 19 : 107 - 120
  • [7] Optimal policies for constrained average-cost Markov decision processes
    Gonzalez-Hernandez, Juan
    Villarreal, Cesar E.
    [J]. TOP, 2011, 19 (01) : 107 - 120
  • [8] Reinforcement Learning of Risk-Constrained Policies in Markov Decision Processes
    Brazdil, Tomas
    Chatterjee, Krishnendu
    Novotny, Petr
    Vahala, Jiri
    [J]. THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 9794 - 9801
  • [9] On constrained Markov decision processes
    Haviv, M
    [J]. OPERATIONS RESEARCH LETTERS, 1996, 19 (01) : 25 - 28
  • [10] Learning in Constrained Markov Decision Processes
    Singh, Rahul
    Gupta, Abhishek
    Shroff, Ness B.
    [J]. IEEE TRANSACTIONS ON CONTROL OF NETWORK SYSTEMS, 2023, 10 (01): : 441 - 453
12345