Structured Policies for a Sequential Design Problem with General Distributions

DOI10.1287/moor.12.1.60zbMath0616.90088OpenAlexW2076444209MaRDI QIDQ4726073

Michael Kolonko, H. Benzing

Publication date: 1987

Published in: Mathematics of Operations Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1287/moor.12.1.60

zbMATH Keywords

monotonicityconvexitygeneral distributionstotal expected rewardone-armed bandit problem

Mathematics Subject Classification ID

Dynamic programming (90C39)

Related Items (3)

Structured policies in the sequential design of experiments ⋮ On a sequential two-action decision model¹with unbounded reward functions ⋮ A Two-Armed Bandit Problem with possibility of no Information

This page was built for publication: Structured Policies for a Sequential Design Problem with General Distributions