Optimal stationary policies in the vector-valued Markov decision process

Optimal stationary policies in the vector-valued Markov decision process

0.00 Avg rating0 Votes
Article ID: iaor1993331
Country: Netherlands
Volume: 42
Issue: 1
Start Page Number: 149
End Page Number: 156
Publication Date: Aug 1992
Journal: Stochastic Processes and Their Applications
Authors:
Keywords: markov processes
Abstract:

This paper is concerned with the vector-valued Markov decision process and considers the characterization of optimal stationary policies among the set of all (randomized, history-dependent) policies. Using the scalarization technique developed for the vector maximizing problem in the nonlinear programming, it presents a necessary condition and a (different) sufficient condition for a statinary policy to be optimal among the set of all policies.

Reviews

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 Your email address will not be published.