TWO-PERSON ZERO-SUM STOCHASTIC GAMES

被引：1

作者：

Baykal-Guersoy, Melike ^{[1
]}

机构：

[1] Rutgers State Univ, Dept Ind Engn, Piscataway, NJ 08855 USA

来源：

ANNALS OF OPERATIONS RESEARCH | 1991年 / 28卷 / 01期

关键词：

D O I：

10.1007/BF02055578

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：

Two-person zero-sum stochastic games with finite state and action spaces are considered. The expected average payoff criterion is introduced. In the special case of single controller games it is shown that the optimal stationary policies and the value of the game can be obtained from the optimal solutions to a pair of dual programs. For multichain structures, a decomposition algorithm is given which produces such optimal stationary policies for both players. In the case of both players controlling the transitions, a generalized game is obtained, the solution of which gives the optimal policies.

引用

页码：135 / 152

页数：18

共 50 条

[21] Multiagent Inverse Reinforcement Learning for Two-Person Zero-Sum Games
Lin, Xiaomin
Beling, Peter A.
Cogill, Randy
[J]. IEEE TRANSACTIONS ON GAMES, 2018, 10 (01) : 56 - 68
[22] Value set iteration for two-person zero-sum Markov games
Chang, Hyeong Soo
[J]. AUTOMATICA, 2017, 76 : 61 - 64
[23] Two-Person Adversarial Games are Zero-Sum: An elaboration of a folk theorem
Khan, M. Ali
Pedersen, Arthur Paul
Schrittesser, David
[J]. ECONOMICS LETTERS, 2024, 242
[24] The Design of ϵ-Optimal Strategy for Two-Person Zero-Sum Markov Games
Xie, Kaiyun
Xiong, Junlin
[J]. IEEE CONTROL SYSTEMS LETTERS, 2024, 8 : 2349 - 2354
[25] A Note on Linear Complementarity via Two-Person Zero-Sum Games
Dubey, Dipti
Neogy, S. K.
Raghavan, T. E. S.
[J]. INTERNATIONAL GAME THEORY REVIEW, 2023, 25 (01)
[26] The notion of strong saddle points in two-person zero-sum games
Smol'yakov, ER
[J]. DOKLADY MATHEMATICS, 2001, 64 (01) : 102 - 105
[27] A TRANSITION FROM TWO-PERSON ZERO-SUM GAMES TO COOPERATIVE GAMES WITH FUZZY PAYOFFS
Cevikel, A. C.
Ahlatcioglu, M.
[J]. IRANIAN JOURNAL OF FUZZY SYSTEMS, 2018, 15 (07): : 121 - 131
[28] A Potential Reduction Algorithm for Ergodic Two-Person Zero-Sum Limiting Average Payoff Stochastic Games
Boros, Endre
Elbassioni, Khaled
Gurvich, Vladimir
Makino, Kazuhisa
[J]. COMBINATORIAL OPTIMIZATION AND APPLICATIONS (COCOA 2014), 2014, 8881 : 694 - 709
[29] Reinforcement learning for exploratory linear-quadratic two-person zero-sum stochastic differential games
Sun, Zhongshi
Jia, Guangyan
[J]. APPLIED MATHEMATICS AND COMPUTATION, 2023, 442
[30] Classification of matrix types for multicriteria two-person zero-sum matrix games
Tanaka, T
Higuchi, M
[J]. CONTROL APPLICATIONS OF OPTIMIZATION 2000, VOLS 1 AND 2, 2000, : 659 - 668

← 1 2 3 4 5 →