Policies without Memory for the Infinite-Armed Bernoulli Bandit under the Average-Reward Criterion

DOI10.1017/S0269964800004149MaRDI QIDQ5485352zbMATHFDO

Authors Stephen J. Herschkorn, Erol A. Peköz, Sheldon M. Ross

Publication date 30 August 2006

Published in Probability in the Engineering and Informational Sciences (Search for Journal in Brave)

Mathematics Subject Classification ID

Sequential statistical methods (62L99) Special processes (60K99) Stochastic games, stochastic differential games (91A15)

Recommendations

• Some memoryless bandit policies
• Optimal Bayesian strategies for the infinite-armed Bernoulli bandit
• Bandit problems with infinitely many arms
• Denumerable-Armed Bandits
• On the Bernoulli three-armed bandit problem

Cites work

• Nonparametric bandit methods
• Some problems of optimal sampling strategy

Cited in

(7)

• Optimal Bayesian strategies for the infinite-armed Bernoulli bandit
• Finding optimal memoryless policies of POMDPs under the expected average reward criterion
• A note on infinite-armed Bernoulli bandit problems with generalized beta prior distributions
• Some memoryless bandit policies
• A note on strategies for bandit problems with infinitely many arms
• Bandit and covariate processes, with finite or non-denumerable set of arms
• Topp-Leone distribution with an application to binomial sampling

This page was built for publication: Policies without Memory for the Infinite-Armed Bernoulli Bandit under the Average-Reward Criterion

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5485352)