MDPs with Setwise Continuous Transition Probabilities
Optimization and Control
2021-08-03 v5
Abstract
This paper describes the structure of optimal policies for infinite-state Markov Decision Processes with setwise continuous transition probabilities. The action sets may be noncompact. The objective criteria are either the expected total discounted and undiscounted costs or average costs per unit time. The analysis of optimality equations and inequalities is based on the optimal selection theorem for inf-compact functions introduced in this paper.
Cite
@article{arxiv.2011.01325,
title = {MDPs with Setwise Continuous Transition Probabilities},
author = {Eugene A. Feinberg and Pavlo O. Kasyanov},
journal= {arXiv preprint arXiv:2011.01325},
year = {2021}
}