Solutions for zero-sum two-player games with noncompact decision sets and unbounded payoffs

被引：0

作者：

Feinberg, Eugene A. ^{[1
]}

Kasyanov, Pavlo O. ^{[2
]}

Zgurovsky, Michael Z. ^{[2
]}

机构：

[1] SUNY Stony Brook, Dept Appl Math & Stat, Stony Brook, NY 11794 USA

[2] Natl Tech Univ Ukraine, Inst Appl Syst Anal, Igor Sikorsky Kyiv Polytech Inst, Kiev, Ukraine

来源：

NAVAL RESEARCH LOGISTICS | 2023年 / 70卷 / 05期

关键词：

noncompact action sets; solution; two-person game; unbounded payoffs; value; MINIMAX INEQUALITIES; KKM THEOREM; EXISTENCE; EQUILIBRIA;

D O I：

10.1002/nav.22111

中图分类号：

C93 [管理学]; O22 [运筹学];

学科分类号：

070105 ; 12 ; 1201 ; 1202 ; 120202 ;

摘要：

This article provides sufficient conditions for the existence of solutions for two-person zero-sum games with inf/sup-compact payoff functions and with possibly noncompact decision sets for both players. Payoff functions may be unbounded, and we do not assume any convexity/concavity-type conditions. For such games expected payoff may not exist for some pairs of strategies. The results of this article imply several classic facts. The article also provides sufficient conditions for the existence of a value and solutions for each player. The results of this article are illustrated with the number guessing game.

引用

页码：493 / 506

页数：14

共 50 条

[41] GPI-Based design for partially unknown nonlinear two-player zero-sum games
Yu, Lin
Xiong, Junlin
Xie, Min
[J]. JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS, 2023, 360 (03): : 2068 - 2088
[42] Decentralized Single-Timescale Actor Critic on Zero-Sum Two-Player Stochastic Games
Guo, Hongyi
Fu, Zuyue
Yang, Zhuoran
Wang, Zhaoran
[J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139, 2021, 139
[43] Online solution of nonlinear two-player zero-sum games using synchronous policy iteration
Vamvoudakis, Kyriakos G.
Lewis, F. L.
[J]. INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL, 2012, 22 (13) : 1460 - 1483
[44] Policy gradient algorithm and its convergence analysis for two-player zero-sum Markov games
Wang, Zhuo
Li, Yongqiang
Feng, Yu
Feng, Yuanjing
[J]. Zhejiang Daxue Xuebao (Gongxue Ban)/Journal of Zhejiang University (Engineering Science), 2024, 58 (03): : 480 - 491
[45] Sufficient Conditions for Optimality in Finite-Horizon Two-Player Zero-Sum Hybrid Games
Leudo, Santiago J.
Sanfelice, Ricardo G.
[J]. 2022 IEEE 61ST CONFERENCE ON DECISION AND CONTROL (CDC), 2022, : 3268 - 3273
[46] Learning Extensive-Form Perfect Equilibria in Two-Player Zero-Sum Sequential Games
Bernasconi, Martino
Marchesi, Alberto
Trovo, Francesco
[J]. INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 238, 2024, 238
[47] The lagging anchor algorithm: Reinforcement learning in two-player zero-sum games with imperfect information
Dahl, FA
[J]. MACHINE LEARNING, 2002, 49 (01) : 5 - 37
[48] A Meta-evolutionary Learning Algorithm for Opponent Adaptation in Two-player Zero-sum Games
Wu, Zhe
Li, Kai
Xu, Hang
Xing, Jun-Liang
[J]. Zidonghua Xuebao/Acta Automatica Sinica, 2022, 48 (10): : 2462 - 2473
[49] Equilibrium strategies of two-player nonzero-sum games with fuzzy payoffs
Gao, Jinwu
Liu, Zhi-Qiang
Liu, Yan-Kui
[J]. 2007 IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS, VOLS 1-4, 2007, : 882 - +
[50] Feature Selection Scheme Based on Zero-Sum Two-Player Game
Touazi, Azzedine
Mokdad, Fatiha
Bouchaffra, Djamel
[J]. 2014 22ND INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2014, : 1342 - 1347

← 1 2 3 4 5 →