Singularly perturbed linear programs and Markov decision processes
Optimization and Control
2016-11-23 v1
Abstract
Linear programming formulations for the discounted and long-run average MDPs have evolved along separate trajectories. In 2006, E. Altman conjectured that the two linear programming formulations of discounted and long-run average MDPs are, most likely, a manifestation of general properties of singularly perturbed linear programs. In this note we demonstrate that this is, indeed, the case.
Keywords
Cite
@article{arxiv.1611.07388,
title = {Singularly perturbed linear programs and Markov decision processes},
author = {Konstantin Avrachenkov and Jerzy Filar and Vladimir Gaitsgory and Andrew Stillman},
journal= {arXiv preprint arXiv:1611.07388},
year = {2016}
}