The Annals of Mathematical Statistics

A Countable Policy Set for Sequential Decision Problems

John E. Rolph and Ralph E. Strauch

Full-text: Open access

Abstract

In denumerable state, denumerable action sequential decision problems in which the reward function has uniformly bounded 2nd moment, the optimal reward for the decisionmaker who restricts himself to the countable set of stationary policies consisting of those which choose some arbitrary action at all but a finite number of states will be the same as the optimal reward for the decisionmaker who optimizes over all stationary policies. Under some further restriction, he can do almost as well simply by solving a large finite state truncation of the original problem.

Article information

Source
Ann. Math. Statist., Volume 43, Number 6 (1972), 2078-2082.

Dates
First available in Project Euclid: 27 April 2007

Permanent link to this document
https://projecteuclid.org/euclid.aoms/1177690888

Digital Object Identifier
doi:10.1214/aoms/1177690888

Mathematical Reviews number (MathSciNet)
MR362770

Zentralblatt MATH identifier
0255.90002

JSTOR
links.jstor.org

Citation

Rolph, John E.; Strauch, Ralph E. A Countable Policy Set for Sequential Decision Problems. Ann. Math. Statist. 43 (1972), no. 6, 2078--2082. doi:10.1214/aoms/1177690888. https://projecteuclid.org/euclid.aoms/1177690888


Export citation