A Matrosov Theorem for Adversarial Markov Decision Processes

被引：25
|
作者：
Teel, Andrew R. [1 ]
机构：
[1] Univ Calif Santa Barbara, Dept Elect & Comp Engn, Santa Barbara, CA 93106 USA
来源：
IEEE TRANSACTIONS ON AUTOMATIC CONTROL | 2013年 / 58卷 / 08期
基金：
美国国家科学基金会;
关键词：
ASYMPTOTIC STABILITY;
D O I：
10.1109/TAC.2013.2250073
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
Matrosov's relaxation of Lyapunov conditions for uniform global asymptotic stability in time-varying systems is extended to stochastic, set-valued discrete-time systems. Nested Matrosov functions are used to give conditions for stability that complement invariance principles for time-invariant systems. Unlike invariance principles, Matrosov functions also can be applied to general time-varying systems.
引用
收藏
页码：2142 / 2148
页数：8
相关论文
共 50 条
  • [1] A LIMIT THEOREM FOR MARKOV DECISION PROCESSES
    Staudigl, Mathias
    JOURNAL OF DYNAMICS AND GAMES, 2014, 1 (04): : 639 - 659
  • [2] Online Convex Optimization in Adversarial Markov Decision Processes
    Rosenberg, Aviv
    Mansour, Yishay
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 97, 2019, 97
  • [3] Learning Adversarial Markov Decision Processes with Delayed Feedback
    Lancewicki, Tal
    Rosenberg, Aviv
    Mansour, Yishay
    THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2022, : 7281 - 7289
  • [4] An envelope theorem and some applications to discounted Markov decision processes
    Cruz-Suarez, Hugo
    Montes-de-Oca, Raul
    MATHEMATICAL METHODS OF OPERATIONS RESEARCH, 2008, 67 (02) : 299 - 321
  • [5] An envelope theorem and some applications to discounted Markov decision processes
    Hugo Cruz-Suárez
    Raúl Montes-de-Oca
    Mathematical Methods of Operations Research, 2008, 67 : 299 - 321
  • [6] Learning Adversarial Markov Decision Processes with Bandit Feedback and Unknown Transition
    Jin, Chi
    Jin, Tiancheng
    Luo, Haipeng
    Sra, Suvrit
    Yu, Tiancheng
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 119, 2020, 119
  • [7] Robust Lagrangian and Adversarial Policy Gradient for Robust Constrained Markov Decision Processes
    Bossens, David M.
    2024 IEEE CONFERENCE ON ARTIFICIAL INTELLIGENCE, CAI 2024, 2024, : 1227 - 1239
  • [8] Follow-the-Perturbed-Leader for Adversarial Markov Decision Processes with Bandit Feedback
    Dai, Yan
    Luo, Haipeng
    Chen, Liyu
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35, NEURIPS 2022, 2022,
  • [9] A LaSalle version of Matrosov theorem
    Astolfi, Alessandro
    Praly, Laurent
    2011 50TH IEEE CONFERENCE ON DECISION AND CONTROL AND EUROPEAN CONTROL CONFERENCE (CDC-ECC), 2011, : 320 - 324
  • [10] A Matrosov theorem for strong global recurrence
    Subbaraman, Anantharaman
    Teel, Andrew R.
    AUTOMATICA, 2013, 49 (11) : 3390 - 3395
12345