scholarly journals Singularly Perturbed Markov Decision Processes: A Multiresolution Algorithm

2014 ◽  
Vol 52 (6) ◽  
pp. 3854-3886 ◽  
Author(s):  
Chin Pang Ho ◽  
Panos Parpas
2016 ◽  
Vol 44 (3) ◽  
pp. 297-301
Author(s):  
Konstantin Avrachenkov ◽  
Jerzy A. Filar ◽  
Vladimir Gaitsgory ◽  
Andrew Stillman

1983 ◽  
Vol 20 (04) ◽  
pp. 835-842
Author(s):  
David Assaf

The paper presents sufficient conditions for certain functions to be convex. Functions of this type often appear in Markov decision processes, where their maximum is the solution of the problem. Since a convex function takes its maximum at an extreme point, the conditions may greatly simplify a problem. In some cases a full solution may be obtained after the reduction is made. Some illustrative examples are discussed.


Sign in / Sign up

Export Citation Format

Share Document