Verification of Markov Decision Processes with Risk-Sensitive Measures

被引:0
|
作者
Cubuktepe, Murat [1 ]
Topcu, Ufuk [1 ]
机构
[1] Univ Texas Austin, Dept Aerosp Engn & Engn Mech, 201 E 24th St, Austin, TX 78712 USA
关键词
PROSPECT-THEORY;
D O I
暂无
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 develop a method for computing policies in Markov decision processes with risk-sensitive measures subject to temporal logic constraints. Specifically, we use a particular risk-sensitive measure from cumulative prospect theory, which has been previously adopted in psychology and economics. The nonlinear transformation of the probabilities and utility functions yields a nonlinear programming problem, which makes computation of optimal policies typically challenging. We show that this nonlinear weighting function can be accurately approximated by the difference of two convex functions. This observation enables efficient policy computation using convex-concave programming. We demonstrate the effectiveness of the approach on several scenarios.
引用
收藏
页码:2371 / 2377
页数:7
相关论文
共 50 条
  • [1] RISK-SENSITIVE MARKOV DECISION PROCESSES
    HOWARD, RA
    MATHESON, JE
    [J]. MANAGEMENT SCIENCE SERIES A-THEORY, 1972, 18 (07): : 356 - 369
  • [2] More Risk-Sensitive Markov Decision Processes
    Baeuerle, Nicole
    Rieder, Ulrich
    [J]. MATHEMATICS OF OPERATIONS RESEARCH, 2014, 39 (01) : 105 - 120
  • [3] Markov decision processes with risk-sensitive criteria: an overview
    Nicole Bäuerle
    Anna Jaśkiewicz
    [J]. Mathematical Methods of Operations Research, 2024, 99 : 141 - 178
  • [4] Risk-Sensitive and Average Optimality in Markov Decision Processes
    Sladky, Karel
    [J]. PROCEEDINGS OF 30TH INTERNATIONAL CONFERENCE MATHEMATICAL METHODS IN ECONOMICS, PTS I AND II, 2012, : 799 - 804
  • [5] On Risk-Sensitive Piecewise Deterministic Markov Decision Processes
    Guo, Xin
    Zhang, Yi
    [J]. APPLIED MATHEMATICS AND OPTIMIZATION, 2020, 81 (03): : 685 - 710
  • [6] RISK-SENSITIVE AVERAGE OPTIMALITY IN MARKOV DECISION PROCESSES
    Sladky, Karel
    [J]. KYBERNETIKA, 2018, 54 (06) : 1218 - 1230
  • [7] Markov decision processes with risk-sensitive criteria: an overview
    Baeuerle, Nicole
    Jaskiewicz, Anna
    [J]. MATHEMATICAL METHODS OF OPERATIONS RESEARCH, 2024, 99 (1-2) : 141 - 178
  • [8] On Risk-Sensitive Piecewise Deterministic Markov Decision Processes
    Xin Guo
    Yi Zhang
    [J]. Applied Mathematics & Optimization, 2020, 81 : 685 - 710
  • [9] Partially Observable Risk-Sensitive Markov Decision Processes
    Baeuerle, Nicole
    Rieder, Ulrich
    [J]. MATHEMATICS OF OPERATIONS RESEARCH, 2017, 42 (04) : 1180 - 1196
  • [10] Risk-sensitive Markov Decision Processes with Risk Constraints of Coherent Risk Measures in Fuzzy and Stochastic Environment
    Yoshida, Yuji
    [J]. IJCCI: PROCEEDINGS OF THE 11TH INTERNATIONAL JOINT CONFERENCE ON COMPUTATIONAL INTELLIGENCE, 2019, : 269 - 277