View(s) :
6 (0 ULiège)
Download(s) :
0 (0 ULiège)
Saddle Point Conditions for Antagonistic Positional Games in Complex Markov Decision Processes
p. 105-116
Abstract
A class of stochastic antagonistic positional games for Markov decision processes with average and expected total discounted costs optimization criteria are formu lated and studied. Saddle point conditions in the considered class of games that extend saddle point conditions for deterministic parity games are derived. Further more algorithms for determining the optimal stationary strategies of the players are proposed and grounded
Text
References
Bibliographical reference
Dmitrii Lozovanu and Stefan Pickl, « Saddle Point Conditions for Antagonistic Positional Games in Complex Markov Decision Processes », CASYS, 30 | 2014, 105-116.
Electronic reference
Dmitrii Lozovanu and Stefan Pickl, « Saddle Point Conditions for Antagonistic Positional Games in Complex Markov Decision Processes », CASYS [Online], 30 | 2014, Online since 17 October 2024, connection on 27 December 2024. URL : http://popups.uliege.be/3041-539x/index.php?id=4641
Authors
Dmitrii Lozovanu
Institute of Mathematics and Computer Science, Academy of Sciences of Moldova, Academy str., 5, Chisinau, MD-2028, Moldova
Stefan Pickl
Institute for Theoretical Computer Science, Mathematics and Operations Research, Universität der Bundeswehr München 85577 Neubiberg-München, Germany