On a sequential two-action decision model with unbounded reward functions

On a sequential two-action decision model with unbounded reward functions

0.00 Avg rating0 Votes
Article ID: iaor1988724
Country: Germany
Volume: 20
Start Page Number: 127
End Page Number: 134
Publication Date: Mar 1989
Journal: Optimization
Authors: , ,
Keywords: decision theory
Abstract:

Several decision problems such as bandit problems, stopping problems, and portfolio problems, can be considered as special sequential two-action Markov decision models. In this paper such models are studied; a stopping rule is given, and monotonicity properties of the maximum expected total discounted reward and of an optimal policy are established. The theory is illustrated by two examples.

Reviews

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 Your email address will not be published.