OPTIMAL CONTROL AND ZERO-SUM GAMES FOR MARKOV CHAINS OF MEAN-FIELD TYPE

被引：6
|
作者：
Choutri, Salah Eddine [1 ]
Djehiche, Boualem [1 ]
Tembine, Hamidou [2 ]
机构：
[1] KTH Royal Inst Technol, Dept Math, S-10044 Stockholm, Sweden
[2] NYU, Learning & Game Theory Lab, 19 Washington Sq North, New York, NY 10011 USA
来源：
MATHEMATICAL CONTROL AND RELATED FIELDS | 2019年 / 9卷 / 03期
基金：
瑞典研究理事会;
关键词：
Mean-field; nonlinear Markov chain; backward SDEs; optimal control; zero-sum game; saddle point; stochastic maximum principle; thinning; LARGE DEVIATIONS; LARGE NUMBERS; EXISTENCE; SYSTEMS; BSDES; LAW;
D O I：
10.3934/mcrf.2019026
中图分类号：
O29 [应用数学];
学科分类号：
070104 ;
摘要：
We establish existence of Markov chains of mean-field type with unbounded jump intensities by means of a fixed point argument using the total variation distance. We further show existence of nearly-optimal controls and, using a Markov chain backward SDE approach, we suggest conditions for existence of an optimal control and a saddle-point for respectively a control problem and a zero-sum differential game associated with payoff functionals of mean-field type, under dynamics driven by such Markov chains of mean-field type.
引用
收藏
页码：571 / 605
页数：35
相关论文
共 50 条
  • [31] Decentralized Q-Learning in Zero-sum Markov Games
    Sayin, Muhammed O.
    Zhang, Kaiqing
    Leslie, David S.
    Sar, Tamer Ba Comma
    Ozdaglar, Asuman
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
  • [32] The distribution of optimal strategies in symmetric zero-sum games
    Brandl, Florian
    GAMES AND ECONOMIC BEHAVIOR, 2017, 104 : 674 - 680
  • [33] Decomposition Techniques for Markov Zero-sum Games with Nested Information
    Zheng, Jiefu
    Castanon, David A.
    2013 IEEE 52ND ANNUAL CONFERENCE ON DECISION AND CONTROL (CDC), 2013, : 574 - 581
  • [34] Limit Optimal Trajectories in Zero-Sum Stochastic Games
    Sorin, Sylvain
    Vigeral, Guillaume
    DYNAMIC GAMES AND APPLICATIONS, 2020, 10 (02) : 555 - 572
  • [35] A Mean Field Approach for Discounted Zero-Sum Games in a Class of Systems of Interacting Objects
    Carmen G. Higuera-Chan
    J. Adolfo Minjárez-Sosa
    Dynamic Games and Applications, 2021, 11 : 512 - 537
  • [36] A Mean Field Approach for Discounted Zero-Sum Games in a Class of Systems of Interacting Objects
    Higuera-Chan, Carmen G.
    Minjarez-Sosa, J. Adolfo
    DYNAMIC GAMES AND APPLICATIONS, 2021, 11 (03) : 512 - 537
  • [37] On Canonical Forms for Zero-Sum Stochastic Mean Payoff Games
    Boros, Endre
    Elbassioni, Khaled
    Gurvich, Vladimir
    Makino, Kazuhisa
    DYNAMIC GAMES AND APPLICATIONS, 2013, 3 (02) : 128 - 161
  • [38] Almost Optimal Algorithms for Two-player Zero-Sum Linear Mixture Markov Games
    Chen, Zixiang
    Zhou, Dongruo
    Gu, Quanquan
    INTERNATIONAL CONFERENCE ON ALGORITHMIC LEARNING THEORY, VOL 167, 2022, 167
  • [39] On Canonical Forms for Zero-Sum Stochastic Mean Payoff Games
    Endre Boros
    Khaled Elbassioni
    Vladimir Gurvich
    Kazuhisa Makino
    Dynamic Games and Applications, 2013, 3 : 128 - 161
  • [40] A Certainty Equivalence Result in Team-Optimal Control of Mean-Field Coupled Markov Chains
    Arabneydi, Jalal
    Aghdam, Amir G.
    2017 IEEE 56TH ANNUAL CONFERENCE ON DECISION AND CONTROL (CDC), 2017,
12345