Dynamic allocation policies for the finite horizon one armed bandit problem

DOI10.1080/07362999808809563zbMath0980.62060OpenAlexW2040602080WikidataQ126241327 ScholiaQ126241327MaRDI QIDQ4215901

Michael N. Katehakis, Apostolos N. Burnetas

Publication date: 21 January 1999

Published in: Stochastic Analysis and Applications (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/07362999808809563

zbMATH Keywords

finite horizonexponential familyoptimal sequential allocation

Mathematics Subject Classification ID

Sequential statistical design (62L05)

Related Items (2)

Resource capacity allocation to stochastic dynamic competitors: knapsack problem for perishable items and index-knapsack heuristic ⋮ ASYMPTOTICALLY OPTIMAL MULTI-ARMED BANDIT POLICIES UNDER A COST CONSTRAINT

Cites Work

• On Sequential Designs for Maximizing the Sum of $n$ Observations
• Extensions of the multiarmed bandit problem: The discounted case
• The Multi-Armed Bandit Problem: Decomposition and Computation
• Some aspects of the sequential design of experiments
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Dynamic allocation policies for the finite horizon one armed bandit problem