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: | Wakuta Kazuyoshi |
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.