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

2003 ◽  
Vol 95 (3) ◽  
pp. 513-532 ◽  
Author(s):  
T.E.S. Raghavan ◽  
Zamir Syed
2020 ◽  
Vol 22 (02) ◽  
pp. 2040008
Author(s):  
P. Mondal ◽  
S. K. Neogy ◽  
A. Gupta ◽  
D. Ghorui

Zero-sum two-person discounted semi-Markov games with finite state and action spaces are studied where a collection of states having Perfect Information (PI) property is mixed with another collection of states having Additive Reward–Additive Transition and Action Independent Transition Time (AR-AT-AITT) property. For such a PI/AR-AT-AITT mixture class of games, we prove the existence of an optimal pure stationary strategy for each player. We develop a policy improvement algorithm for solving discounted semi-Markov decision processes (one player version of semi-Markov games) and using it we obtain a policy-improvement type algorithm for computing an optimal strategy pair of a PI/AR-AT-AITT mixture semi-Markov game. Finally, we extend our results when the states having PI property are replaced by a subclass of Switching Control (SC) states.


2012 ◽  
Vol 40 (1) ◽  
pp. 56-60 ◽  
Author(s):  
Konstantin Avrachenkov ◽  
Laura Cottatellucci ◽  
Lorenzo Maggi

2019 ◽  
Vol 9 (4) ◽  
pp. 1026-1041
Author(s):  
K. Avrachenkov ◽  
V. Ejov ◽  
J. A. Filar ◽  
A. Moghaddam

2001 ◽  
Vol 54 (2) ◽  
pp. 291-301 ◽  
Author(s):  
Anna Jaśkiewicz ◽  
Andrzej S. Nowak

Author(s):  
Anna Jaśkiewicz ◽  
Andrzej S. Nowak
Keyword(s):  

Sign in / Sign up

Export Citation Format

Share Document