Vector-valued Markov decision processes and systems of linear inequalities

Vector-valued Markov decision processes and systems of linear inequalities

0.00 Avg rating0 Votes
Article ID: iaor19951839
Country: Netherlands
Volume: 56
Issue: 1
Start Page Number: 159
End Page Number: 169
Publication Date: Mar 1995
Journal: Stochastic Processes and Their Applications
Authors:
Abstract:

For a vector-valued Markov decision process, the paper characterizes optimal (deterministic) stationary policies by systems of linear inequalities and presents an algorithm for finding all optimal stationary policies from among all randomized, history-remembering ones. The algorithm consists of improving the policies and of checking the optimality of a policy by solving the associated system of linear inequalities via Fourier elimination.

Reviews

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 Your email address will not be published.