On the k-armed Bernoulli bandit: monotonicity of the total reward under an arbitrary prior distribution

DOI10.1080/02331938408842974zbMath0555.90101OpenAlexW2086509088MaRDI QIDQ3220376

Michael Kolonko, H. Benzing, Karl Hinderer

Publication date: 1984

Published in: Mathematische Operationsforschung und Statistik. Series Optimization (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/02331938408842974

zbMATH Keywords

monotonicity propertiesBayesian approachtotal rewardsuccess probabilitiesarbitrary prior distributiongambling machinek-armed Bernoulli bandit

Mathematics Subject Classification ID

Bayesian inference (62F15) Dynamic programming (90C39) Stopping times; optimal stopping problems; gambling theory (60G40) Markov and semi-Markov decision processes (90C40) Sequential statistical design (62L05) Sequential statistical analysis (62L10) Optimal stopping in statistics (62L15)

Related Items (3)

On the Bernoulli three-armed bandit problem ⋮ Structured policies in the sequential design of experiments ⋮ On monotone optimal decision rules and the stay-on-a-winner rule for the two-armed bandit

This page was built for publication: On the k-armed Bernoulli bandit: monotonicity of the total reward under an arbitrary prior distribution