Fundamental Performance Limitations with Kullback-Leibler Control Cost

被引:0
|
作者
Sun, Yu [1 ]
Mehta, Prashant G. [1 ]
机构
[1] Univ Illinois, Coordinated Sci Lab, Urbana, IL 61801 USA
关键词
D O I
10.1109/CDC.2010.5717133
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This research concerns fundamental performance limitations in control of discrete time nonlinear systems. The fundamental limitations are expressed in terms of the average cost of an infinite horizon optimal control problem. The control cost is defined by using a certain Kullback-Leibler divergence metric recently introduced by Todorov [1]. The limitations are obtained via analysis of a linear eigenvalue problem defined only by the open loop dynamics. For a linear time invariant (LTI) system the fundamental limitation is shown to depend upon the unstable eigenvalues, as in the classical Bode formula. For a more general class of nonlinear systems, it is shown that the limitation arise only if the open-loop dynamics are non-ergodic.
引用
收藏
页码:7063 / 7068
页数:6
相关论文
共 50 条
  • [1] Online Markov Decision Processes With Kullback-Leibler Control Cost
    Guan, Peng
    Raginsky, Maxim
    Willett, Rebecca M.
    [J]. IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2014, 59 (06) : 1423 - 1438
  • [2] Online Markov Decision Processes with Kullback-Leibler Control Cost
    Guan, Peng
    Raginsky, Maxim
    Willett, Rebecca
    [J]. 2012 AMERICAN CONTROL CONFERENCE (ACC), 2012, : 1388 - 1393
  • [3] Kullback-Leibler Control in Boolean Control Networks
    Toyoda, Mitsuru
    Wu, Yuhu
    [J]. IEEE TRANSACTIONS ON CYBERNETICS, 2024, 54 (08) : 4429 - 4442
  • [4] The Kullback-Leibler autodependogram
    Bagnato, L.
    De Capitani, L.
    Punzo, A.
    [J]. JOURNAL OF APPLIED STATISTICS, 2016, 43 (14) : 2574 - 2594
  • [5] THE KULLBACK-LEIBLER DISTANCE
    KULLBACK, S
    [J]. AMERICAN STATISTICIAN, 1987, 41 (04): : 340 - 340
  • [6] Kullback-Leibler Boosting
    Liu, C
    Shum, HY
    [J]. 2003 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2003, : 587 - 594
  • [7] Matrix CFAR detectors based on symmetrized Kullback-Leibler and total Kullback-Leibler divergences
    Hua, Xiaoqiang
    Cheng, Yongqiang
    Wang, Hongqiang
    Qin, Yuliang
    Li, Yubo
    Zhang, Wenpeng
    [J]. DIGITAL SIGNAL PROCESSING, 2017, 69 : 106 - 116
  • [8] Performance monitoring of MIMO control system using Kullback-Leibler divergence
    Wu, Ping
    [J]. CANADIAN JOURNAL OF CHEMICAL ENGINEERING, 2018, 96 (07): : 1559 - 1565
  • [9] Chained Kullback-Leibler Divergences
    Pavlichin, Dmitri S.
    Weissman, Tsachy
    [J]. 2016 IEEE INTERNATIONAL SYMPOSIUM ON INFORMATION THEORY, 2016, : 580 - 584
  • [10] The Kullback-Leibler number and thermodynamics
    Nyengeri, H
    [J]. PHYSICA SCRIPTA, 2001, 64 (02): : 105 - 107