Some memoryless bandit policies

DOI10.1239/JAP/1044476838MaRDI QIDQ4408546zbMATH OpenOpenAlexFDO

Authors Erol A. Peköz

Publication date 29 June 2003

Published in Journal of Applied Probability (Search for Journal in Brave)

Full work available at URL https://semanticscholar.org/paper/c8e7da5c00a9671adb52cfb9c0b45fa60dfdb445

zbMATH Keywords

average reward criteriabandit problemmultiarmed bandit problem

Mathematics Subject Classification ID

Sequential statistical design (62L05) Optimal stopping in statistics (62L15) Stochastic scheduling theory in operations research (90B36)

Recommendations

• Policies without Memory for the Infinite-Armed Bernoulli Bandit under the Average-Reward Criterion
• Finite-time analysis of the multiarmed bandit problem
• scientific article; zbMATH DE number 4059270
• Sample mean based index policies by O(log n) regret for the multi-armed bandit problem
• Denumerable-Armed Bandits

Cited in

(8)

• On the evaluation of strategies for branching bandit processes
• Stay-with-a-winner rule for dependent Bernoulli bandits
• On the value of learning for Bernoulli bandits with unknown parameters
• Robustness of stochastic bandit policies
• Memory-Constrained No-Regret Learning in Adversarial Multi-Armed Bandits
• Bandits and Experts in Metric Spaces
• scientific article; zbMATH DE number 6253908 (Why is no real title available?)
• Policies without Memory for the Infinite-Armed Bernoulli Bandit under the Average-Reward Criterion

This page was built for publication: Some memoryless bandit policies

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4408546)