Blackwell optimality in Borelian continuous-in-action Markov decision processes

Blackwell optimality in Borelian continuous-in-action Markov decision processes

0.00 Avg rating0 Votes
Article ID: iaor19981833
Volume: 35
Issue: 6
Start Page Number: 2157
End Page Number: 2182
Publication Date: Nov 1997
Journal: SIAM Journal on Control and Optimization
Authors:
Keywords: programming: dynamic, optimization
Abstract:

Necessary and sufficient conditions are obtained for the existence of ϵ-weak minima for constrained convex vector optimization problems. The characterization of ϵ-weak minima is given in terms of ϵ-optimal solutions of the associated scalar optimization problems and ϵ-directional derivatives of objective functions. The Lipschitzian continuity of ϵ-weak minima is provided under mild conditions.

Reviews

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 Your email address will not be published.