Finite horizon Markov decision processes with uncertain terminal payoffs

Finite horizon Markov decision processes with uncertain terminal payoffs

0.00 Avg rating0 Votes
Article ID: iaor19982369
Country: United States
Volume: 43
Issue: 5
Start Page Number: 862
End Page Number: 869
Publication Date: Sep 1995
Journal: Operations Research
Authors:
Keywords: programming: dynamic
Abstract:

This paper deals with the problem of finding an estimate of the maximal loss of optimality which can arise when terminal payoffs are uncertain and policies are restricted in some way. The original non-convex optimization problem is converted to a sequence of sub-problems involving the maximization of a bilinear function over a convex region. The paper deals solely with the theoretical issues.

Reviews

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 Your email address will not be published.