Robustness of policies in constrained Markov decision processes

被引：15
|
作者：
Zadorojniy, A [1 ]
Shwartz, A
机构：
[1] Intel Israel Ltd, MATAM, IL-31015 Haifa, Israel
[2] Technion Israel Inst Technol, Fac Elect Engn, IL-32000 Haifa, Israel
来源：
IEEE TRANSACTIONS ON AUTOMATIC CONTROL | 2006年 / 51卷 / 04期
关键词：
constrained Markov decision process (MDP); discounted cost; Markov decision processes; robustness; sensitivity;
D O I：
10.1109/TAC.2006.872754
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
We consider the optimization of finite-state, finite-action Markov decision processes (MDPs), under constraints. Cost and constraints are discounted. We introduce a new method for investigating the continuity, and a certain type of robustness, of the optimal cost and the optimal policy under changes in the constraints. This method is also applicable for other cost criteria such as finite horizon and infinite horizon average cost.
引用
收藏
页码：635 / 638
页数：4
相关论文
共 50 条
  • [21] IDENTIFICATION OF OPTIMAL POLICIES IN MARKOV DECISION PROCESSES
    Sladky, Karel
    [J]. KYBERNETIKA, 2010, 46 (03) : 558 - 570
  • [22] Least Inferable Policies for Markov Decision Processes
    Karabag, Mustafa O.
    Ornik, Melkior
    Topcu, Ufuk
    [J]. 2019 AMERICAN CONTROL CONFERENCE (ACC), 2019, : 1224 - 1231
  • [23] Ranking policies in discrete Markov decision processes
    Peng Dai
    Judy Goldsmith
    [J]. Annals of Mathematics and Artificial Intelligence, 2010, 59 : 107 - 123
  • [24] Optimal adaptive policies for Markov decision processes
    Burnetas, AN
    Katehakis, MN
    [J]. MATHEMATICS OF OPERATIONS RESEARCH, 1997, 22 (01) : 222 - 255
  • [25] Optimal Policies for Quantum Markov Decision Processes
    Ming-Sheng Ying
    Yuan Feng
    Sheng-Gang Ying
    [J]. Machine Intelligence Research, 2021, 18 (03) : 410 - 421
  • [26] Optimal Policies for Quantum Markov Decision Processes
    Ming-Sheng Ying
    Yuan Feng
    Sheng-Gang Ying
    [J]. International Journal of Automation and Computing, 2021, 18 : 410 - 421
  • [27] Ranking policies in discrete Markov decision processes
    Dai, Peng
    Goldsmith, Judy
    [J]. ANNALS OF MATHEMATICS AND ARTIFICIAL INTELLIGENCE, 2010, 59 (01) : 107 - 123
  • [28] Dynamic Markov Decision Policies for Delay Constrained Wireless Scheduling
    Neely, Michael J.
    Supittayapornpong, Sucha
    [J]. IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2013, 58 (08) : 1948 - 1961
  • [29] Joint chance-constrained Markov decision processes
    Varagapriya, V.
    Singh, Vikas Vikram
    Lisser, Abdel
    [J]. ANNALS OF OPERATIONS RESEARCH, 2023, 322 (02) : 1013 - 1035
  • [30] Strict-sense constrained Markov decision processes
    Hsu, SP
    Arapostathis, A
    [J]. 2004 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN & CYBERNETICS, VOLS 1-7, 2004, : 194 - 199
12345