A policy-improvement type algorithm for solving zero-sum two-person stochastic games of perfect information

被引：10

作者：

Raghavan, TES ^{[1
]}

Syed, Z ^{[1
]}

机构：

[1] Univ Illinois, Dept Math Stat & Comp Sci, Chicago, IL 60680 USA

来源：

MATHEMATICAL PROGRAMMING | 2003年 / 95卷 / 03期

关键词：

stochastic games; MDP; perfect information; policy iteration;

D O I：

10.1007/s10107-002-0312-3

中图分类号：

TP31 [计算机软件];

学科分类号：

081202 ; 0835 ;

摘要：

We give a policy-improvement type algorithm to locate an optimal pure stationary strategy for discounted stochastic games with perfect information. A graph theoretic motivation for our algorithm is presented as well.

引用

页码：513 / 532

页数：20

共 30 条

[1] A policy-improvement type algorithm for solving zero-sum two-person stochastic games of perfect information
T.E.S. Raghavan
Zamir Syed
Mathematical Programming, 2003, 95 : 513 - 532
[2] Converging coevolutionary algorithm for two-person zero-sum discounted Markov games with perfect information
Chang, Hyeong Soo
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2008, 53 (02) : 596 - 601
[3] Two-Person Zero-Sum Stochastic Games with Semicontinuous Payoff
Laraki, R.
Maitra, A. P.
Sudderth, W. D.
DYNAMIC GAMES AND APPLICATIONS, 2013, 3 (02) : 162 - 171
[4] A note on two-person zero-sum communicating stochastic games
Avsar, Zeynep Muge
Baykal-Gursoy, Melike
OPERATIONS RESEARCH LETTERS, 2006, 34 (04) : 412 - 420
[5] Perfect information two-person zero-sum markov games with imprecise transition probabilities
Chang, Hyeong Soo
MATHEMATICAL METHODS OF OPERATIONS RESEARCH, 2006, 64 (02) : 335 - 351
[6] Perfect information two-person zero-sum markov games with imprecise transition probabilities
Hyeong Soo Chang
Mathematical Methods of Operations Research, 2006, 64 : 335 - 351
[7] Two-Person Zero-Sum Stochastic Games with Semicontinuous Payoff
R. Laraki
A. P. Maitra
W. D. Sudderth
Dynamic Games and Applications, 2013, 3 : 162 - 171
[8] Value set iteration for two-person zero-sum Markov games
Chang, Hyeong Soo
AUTOMATICA, 2017, 76 : 61 - 64
[9] Two-person zero-sum linear quadratic stochastic differential games by a Hilbert space method
Mou, Libin
Yong, Jiongmin
JOURNAL OF INDUSTRIAL AND MANAGEMENT OPTIMIZATION, 2006, 2 (01) : 95 - 117
[10] Algorithms for uniform optimal strategies in two-player zero-sum stochastic games with perfect information
Avrachenkov, Konstantin
Cottatellucci, Laura
Maggi, Lorenzo
OPERATIONS RESEARCH LETTERS, 2012, 40 (01) : 56 - 60

← 1 2 3 →