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

页码：571 / 605

页数：35

共 50 条

[31] Policy Gradient Algorithm in Two-Player Zero-Sum Markov Games
Li Y.
Zhou J.
Feng Y.
Feng Y.
Moshi Shibie yu Rengong Zhineng/Pattern Recognition and Artificial Intelligence, 2023, 36 (01): : 81 - 91
[32] Zero-sum infinite-horizon discounted piecewise deterministic Markov games
Yonghui Huang
Zhaotong Lian
Xianping Guo
Mathematical Methods of Operations Research, 2023, 97 : 179 - 205
[33] Zero-sum infinite-horizon discounted piecewise deterministic Markov games
Huang, Yonghui
Lian, Zhaotong
Guo, Xianping
MATHEMATICAL METHODS OF OPERATIONS RESEARCH, 2023, 97 (02) : 179 - 205
[34] Zero-sum stochastic differential games of impulse versus continuous control by FBSDEs
Perninge, Magnus
JOURNAL OF MATHEMATICAL ANALYSIS AND APPLICATIONS, 2023, 527 (01)
[35] Mean-field stochastic linear-quadratic optimal control with Markov jump parameters
Ni, Yuan-Hua
Li, Xun
Zhang, Ji-Feng
SYSTEMS & CONTROL LETTERS, 2016, 93 : 69 - 76
[36] Model-free finite-horizon optimal control of discrete-time two-player zero-sum games
Wang, Wei
Chen, Xin
Du, Jianhua
INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE, 2023, 54 (01) : 167 - 179
[37] Maximum principle for mean-field zero-sum stochastic differential game with partial information and its application to finance
Wu, Jinbiao
Liu, Zaiming
EUROPEAN JOURNAL OF CONTROL, 2017, 37 : 8 - 15
[38] Adaptive Learning Based Output-Feedback Optimal Control of CT Two-Player Zero-Sum Games
Zhao, Jun
Lv, Yongfeng
Zhao, Ziliang
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 2022, 69 (03) : 1437 - 1441
[39] Nonzero-Sum Stochastic Games and Mean-Field Games with Impulse Controls
Basei, Matteo
Cao, Haoyang
Guo, Xin
MATHEMATICS OF OPERATIONS RESEARCH, 2022, 47 (01) : 341 - 366
[40] Zero-Sum Games for Finite-Horizon Semi-Markov Processes Under the Probability Criterion
Huang, Xiangxiang
Guo, Xianping
Wen, Xin
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2023, 68 (09) : 5560 - 5567

← 1 2 3 4 5 →