Eventually-stationary policies for Markov decision models with non-constant discounting

Authors:
Yair Carmon;Adam Shwartz
Affiliations:
IIT, Haifa, Israel;IIT, Haifa, Israel
Venue:
Proceedings of the 3rd International Conference on Performance Evaluation Methodologies and Tools
Year:
2008

Citing 2
Cited 0

Markov decision models with weighted discounted criteria

Mathematics of Operations Research
Markov Decision Processes: Discrete Stochastic Dynamic Programming

Markov Decision Processes: Discrete Stochastic Dynamic Programming

Quantified Score

Hi-index	0.00

Visualization

Abstract

We investigate the existance of simple policies in finite discounted cost Markov Decision Processes, when the discount factor is not constant. We introduce a class called "exponentially representable" discount functions. Within this class we prove existence of optimal policies which are eventually stationary---from some time N onward, and provide an algorithm for their computation. Outside this class, optimal policies with this structure in general do not exist.