PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Linear Dependence of Stationary Distributions in Ergodic Markov Decision Processes
Ronald Ortner
Operations Research Letters Volume 35, Number 5, pp. 619-626, 2007.

Abstract

In ergodic MDPs we consider stationary distributions of policies that coincide in all but n states, in which one of two possible actions is chosen. We give conditions and formulas for linear dependence of the stationary distributions of n+2 such policies, and show some results about combinations and mixtures of policies.

EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:3252
Deposited By:Ronald Ortner
Deposited On:31 January 2008