On the Computational Complexity of Stochastic Controller Optimization in POMDPs

被引:40
|
作者
Vlassis, Nikos [1 ]
Littman, Michael L. [2 ]
Barber, David [3 ]
机构
[1] Univ Luxembourg, Luxembourg Ctr Syst Biomed, 7 Ave Hauts Fourneaux, L-4362 Esch Belval, Luxembourg
[2] Brown Univ, Dept Comp Sci, Providence, RI 02912 USA
[3] UCL, Dept Comp Sci, London WC1E 6BT, England
基金
美国国家科学基金会;
关键词
Performance; Partially observable Markov decision process; stochastic controller; bilinear program; computational complexity; Motzkin-Straus theorem; sum-of-square-roots problem; matrix fractional program; computations on polynomials; nonlinear optimization;
D O I
10.1145/2382559.2382563
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
We show that the problem of finding an optimal stochastic blind controller in a Markov decision process is an NP-hard problem. The corresponding decision problem is NP-hard in PSPACE and SQRT-SUM-hard, hence placing it in NP would imply breakthroughs in long-standing open problems in computer science. Our result establishes that the more general problem of stochastic controller optimization in POMDPs is also NP-hard. Nonetheless, we outline a special case that is convex and admits efficient global solutions.
引用
收藏
页数:8
相关论文
共 50 条
  • [41] Stochastic Optimization of an Energy Management Controller for Hybrid Electric Vehicles
    Schwarzer, Volker
    Ghorbani, Reza
    [J]. 25TH WORLD BATTERY, HYBRID AND FUEL CELL ELECTRIC VEHICLE SYMPOSIUM AND EXHIBITION PROCEEDINGS, VOLS 1 & 2, 2010, : 132 - 135
  • [42] Computational complexity optimization in H.264 video coding
    Kwon, David Nyeongkyu
    [J]. 2007 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, VOLS 1-5, 2007, : 2078 - 2081
  • [43] The optimization of kEP-SOPs: Computational complexity, approximability and experiments
    Bernasconi, Anna
    Ciriani, Valentina
    Cordone, Roberto
    [J]. ACM TRANSACTIONS ON DESIGN AUTOMATION OF ELECTRONIC SYSTEMS, 2008, 13 (02)
  • [44] Computational Complexity Measures for Many-objective Optimization Problems
    Curry, David M.
    Dagli, Cihan H.
    [J]. COMPLEX ADAPTIVE SYSTEMS, 2014, 36 : 185 - 191
  • [45] Computational Complexity Analysis and Algorithm Design for Combinatorial Optimization Problems
    Watanabe, Toshimasa
    [J]. 2012 THIRD INTERNATIONAL CONFERENCE ON NETWORKING AND COMPUTING (ICNC 2012), 2012, : 19 - 20
  • [46] Performance and computational complexity optimization in a configurable video coding system
    Kwon, D
    Agathoklis, PA
    Driessen, P
    [J]. WCNC 2003: IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE RECORD, VOLS 1-3, 2003, : 2086 - 2089
  • [47] SAMPLE COMPLEXITY OF SAMPLE AVERAGE APPROXIMATION FOR CONDITIONAL STOCHASTIC OPTIMIZATION
    Hu, Yifan
    Chen, Xin
    He, Niao
    [J]. SIAM JOURNAL ON OPTIMIZATION, 2020, 30 (03) : 2103 - 2133
  • [48] Sample complexity analysis for adaptive optimization algorithms with stochastic oracles
    Jin, Billy
    Scheinberg, Katya
    Xie, Miaolan
    [J]. MATHEMATICAL PROGRAMMING, 2024,
  • [49] Does Momentum Help in Stochastic Optimization? A Sample Complexity Analysis
    Ganesh, Swetha
    Deb, Rohan
    Thoppe, Gugan
    Budhiraja, Amarjit
    [J]. UNCERTAINTY IN ARTIFICIAL INTELLIGENCE, 2023, 216 : 602 - 612
  • [50] Computational complexity of optimization and crude range testing: a new approach motivated by fuzzy optimization
    Walster, GW
    Kreinovich, V
    [J]. FUZZY SETS AND SYSTEMS, 2003, 135 (01) : 179 - 208