Finite-time lower bounds for the two-armed bandit problem

DOI10.1109/9.847107MaRDI QIDQ4507101zbMATH OpenOpenAlexFDO

Authors Sanjeev R. Kulkarni, Gábor Lugosi

Publication date 17 October 2000

Published in IEEE Transactions on Automatic Control (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1109/9.847107

Mathematics Subject Classification ID

Sequential statistical design (62L05) Minimax procedures in statistical decision theory (62C20)

Recommendations

• scientific article; zbMATH DE number 3846699
• Lower bounds on the sample complexity of exploration in the multi-armed bandit problem.
• Nonparametric bandit methods
• Sample mean based index policies by O(log n) regret for the multi-armed bandit problem
• The sample complexity of exploration in the multi-armed bandit problem

Cited in

(12)

• Bounded Regret for Finitely Parameterized Multi-Armed Bandits
• On ergodic two-armed bandits
• Finite-time analysis of the multiarmed bandit problem
• Non-asymptotic analysis of a new bandit algorithm for semi-bounded rewards
• Arbitrary side observations in bandit problems
• Explore first, exploit next: the true shape of regret in bandit problems
• On optimal prior learning time in the two-armed bandit problem
• scientific article; zbMATH DE number 3967731 (Why is no real title available?)
• scientific article; zbMATH DE number 3846699 (Why is no real title available?)
• A Note on Performance Limitations in Bandit Problems With Side Information
• scientific article; zbMATH DE number 6982311 (Why is no real title available?)
• Adaptive policies for sequential sampling under incomplete information and a cost constraint

This page was built for publication: Finite-time lower bounds for the two-armed bandit problem

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4507101)