You are not currently logged in.
Access your personal account or get JSTOR access through your library or other institution:
If You Use a Screen ReaderThis content is available through Read Online (Free) program, which relies on page scans. Since scans are not currently available to screen readers, please contact JSTOR User Support for access. We'll provide a PDF copy for your screen reader.
A Modified Form of the Iterative Method of Dynamic Programming
Arie Hordijk and Henk Tijms
The Annals of Statistics
Vol. 3, No. 1 (Jan., 1975), pp. 203-208
Published by: Institute of Mathematical Statistics
Stable URL: http://www.jstor.org/stable/2958088
Page Count: 6
Since scans are not currently available to screen readers, please contact JSTOR User Support for access. We'll provide a PDF copy for your screen reader.
Preview not available
This paper considers the discrete time finite state Markovian decision problem with the average return criterion. A modified form of the iterative method of dynamic programming is studied. Under the assumption that the maximal average return is independent of the initial state the asymptotic behaviour of the sequence of functions generated by this modified method is found. It is shown that the modified iterative method supplies both upper and lower bounds on the maximal average return and ε-optimal policies. Moreover, a convergence result is proved for the policies produced by the modified iterative method.
The Annals of Statistics © 1975 Institute of Mathematical Statistics