Maximizing the length of a success run for many-armed bandits

DOI10.1016/0304-4149(83)90039-XzbMath0517.90087MaRDI QIDQ1053621

Donald A. Berry, Bert E. Fristedt

Publication date: 1983

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

zbMATH Keywords

sequential decisionssampling strategysuper-regularityBernoulli populationsexistence of optimal strategygambling with discountingmany-armed banditsmaximization of expected total rewardstay on a winner rule

Mathematics Subject Classification ID

Dynamic programming (90C39)

Related Items (1)

Gittins Index for Simple Family of Markov Bandit Processes with Switching Cost and No Discounting

Cites Work

• Bernoulli one-armed bandits - Arbitrary discount sequences
• Bernoulli two-armed bandits with geometric termination
• Some Concepts of Dependence
• Inequalities: theory of majorization and its applications

This page was built for publication: Maximizing the length of a success run for many-armed bandits