Markov decision processes with exponentially representable discounting

Markov decision processes with exponentially representable discounting

0.00 Avg rating0 Votes
Article ID: iaor20102930
Volume: 37
Issue: 1
Start Page Number: 51
End Page Number: 55
Publication Date: Jan 2009
Journal: Operations Research Letters
Authors: ,
Abstract:

We generalize the geometric discount of finite discounted cost Markov Decision Processes to ‘exponentially representable’discount functions, prove existence of optimal policies which are stationary from some time N onward, and provide an algorithm for their computation. Outside this class, optimal ‘N-stationary’ policies in general do not exist.

Reviews

Required fields are marked *. Your email address will not be published.