Arbitrary side observations in bandit problems

DOI10.1016/J.AAM.2004.10.004MaRDI QIDQ2483920zbMATH OpenOpenAlexFDO

Authors Sanjeev R. Kulkarni, H. Vincent Poor, Chih-Chun Wang

Publication date 1 August 2005

Published in Advances in Applied Mathematics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.aam.2004.10.004

zbMATH Keywords

AdaptiveAllocation ruleArbitraryAsymptoticEfficientEvenly distributedRegretSide informationTwo-armed bandit

Mathematics Subject Classification ID

Stopping times; optimal stopping problems; gambling theory (60G40) Probabilistic games; gambling (91A60)

Recommendations

• Generalized Bandit Problems
• Partial monitoring with side information
• Reward maximization under uncertainty: leveraging side-observations on networks
• The multi-armed bandit problem with covariates
• A Two-Armed Bandit Problem with possibility of no Information

Cites work

• A Bernoulli Two-armed Bandit
• A One-Armed Bandit Problem with a Concomitant Variable
• Asymptotically efficient adaptive allocation rules
• Asymptotically efficient adaptive allocation rules for the multiarmed bandit problem with switching cost
• Asymptotically efficient adaptive allocation schemes for controlled i.i.d. processes: finite parameter space
• Asymptotically efficient adaptive allocation schemes for controlled Markov chains: finite parameter space
• Asymptotically efficient allocation rules for the multiarmed bandit problem with multiple plays-Part I: I.I.D. rewards
• Asymptotically efficient allocation rules for the multiarmed bandit problem with multiple plays-Part II: Markovian rewards
• Bandit problems with side observations
• Covariate models for bernoulli bandits
• Finite-time lower bounds for the two-armed bandit problem
• scientific article; zbMATH DE number 3947447 (Why is no real title available?)
• scientific article; zbMATH DE number 51379 (Why is no real title available?)
• scientific article; zbMATH DE number 3638998 (Why is no real title available?)
• scientific article; zbMATH DE number 3418509 (Why is no real title available?)
• Large deviations techniques and applications.
• Learning while searching for the best alternative
• Machine learning and nonparametric bandit theory
• One-armed bandit problems with covariates
• Optimal allocations in sequential tests involving two populations with covariates
• Some aspects of the sequential design of experiments

Cited in

(6)

• Reward maximization under uncertainty: leveraging side-observations on networks
• Nonstochastic Multi-Armed Bandits with Graph-Structured Feedback
• A linear response bandit problem
• A Note on Performance Limitations in Bandit Problems With Side Information
• Modeling item-item similarities for personalized recommendations on Yahoo! front page
• Woodroofe's one-armed bandit problem revisited

This page was built for publication: Arbitrary side observations in bandit problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2483920)