A Short Note on Stationary Distributions of Unichain Markov Decision Processes
Probability
2007-05-23 v1
Abstract
Dealing with unichain MDPs, we consider stationary distributions of policies that coincide in all but states. In these states each policy chooses one of two possible actions. We show that the stationary distributions of n+1 such policies uniquely determine the stationary distributions of all other such policies. An explicit formula for calculation is given.
Cite
@article{arxiv.math/0604452,
title = {A Short Note on Stationary Distributions of Unichain Markov Decision Processes},
author = {Ronald Ortner},
journal= {arXiv preprint arXiv:math/0604452},
year = {2007}
}