Multi-armed bandit with sub-exponential rewards

DOI10.1016/J.ORL.2021.08.004MaRDI QIDQ2060366zbMATH OpenOpenAlexWikidataFDO

Authors Huiwen Jia, Cong Shi, Siqian Shen

Publication date 13 December 2021

Published in Operations Research Letters (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.orl.2021.08.004

zbMATH Keywords

multi-armed banditupper confidence boundunbounded rewardsub-exponential reward

Mathematics Subject Classification ID

Operations research, mathematical programming (90-XX)

Recommendations

• Optimal exploration-exploitation in a multi-armed bandit problem with non-stationary rewards
• Multi-armed bandits in discrete and continuous time
• Independently Expiring Multiarmed Bandits
• Multi-armed bandit problem revisited
• scientific article; zbMATH DE number 4084786
• The Multi-Armed Bandit With Stochastic Plays
• The Nonstochastic Multiarmed Bandit Problem

Cites work

• An Introduction to Heavy-Tailed and Subexponential Distributions
• Bandit algorithms
• Bandits With Heavy Tail
• Concentration inequalities. A nonasymptotic theory of independence
• Introduction to multi-armed bandits
• Inventory rebalancing and vehicle routing in bike sharing systems
• Learning to optimize via posterior sampling
• Online learning and online convex optimization
• Pricing of reusable resources under ambiguous distributions of demand and service time with emerging applications
• Regret analysis of stochastic and nonstochastic multi-armed bandit problems
• Some aspects of the sequential design of experiments
• The concentration of measure phenomenon

Cited in

(3)

• An incentive-compatible multi-armed bandit mechanism
• scientific article; zbMATH DE number 3867090 (Why is no real title available?)
• Multi-armed bandits with episode context

This page was built for publication: Multi-armed bandit with sub-exponential rewards

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2060366)