Active Learning in Multi-armed Bandits

DOI10.1007/978-3-540-87987-9_25MaRDI QIDQ3529929zbMATH OpenOpenAlexFDO

Authors András Antos, Varun Grover, Csaba Szepesvári

Publication date 14 October 2008

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/978-3-540-87987-9_25

Mathematics Subject Classification ID

Computational learning theory (68Q32) Learning and adaptive systems in artificial intelligence (68T05) Reliability, availability, maintenance, inspection in operations research (90B25)

Recommendations

• Upper-Confidence-Bound Algorithms for Active Learning in Multi-armed Bandits
• Active learning in heteroscedastic noise
• Optimal learning and experimentation in bandit problems.
• Learning the distribution with largest mean: two bandit frameworks
• The Continuum-Armed Bandit Problem

Cites work

• Adaptive optimal allocation in stratified sampling methods
• Asymptotically efficient adaptive allocation rules
• Finite-time analysis of the multiarmed bandit problem
• scientific article; zbMATH DE number 893887 (Why is no real title available?)
• Measure Theory and Probability Theory
• Probability Inequalities for Sums of Bounded Random Variables

Cited in

(14)

• Upper-Confidence-Bound Algorithms for Active Learning in Multi-armed Bandits
• V-optimal designs for heteroscedastic regression
• Active Learning of Multiple Source Multiple Destination Topologies
• Learning the distribution with largest mean: two bandit frameworks
• scientific article; zbMATH DE number 7387623 (Why is no real title available?)
• On the bias, risk, and consistency of sample means in multi-armed bandits
• Efficient Algorithms for General Active Learning
• scientific article; zbMATH DE number 6542809 (Why is no real title available?)
• Incentive Compatible Active Learning.
• Optimal activation of halting multi‐armed bandit models
• Multinomial Thompson sampling for rating scales and prior considerations for calibrating uncertainty
• Active learning with multi-criteria decision making systems
• Models of active learning in group-structured state spaces
• Active learning in heteroscedastic noise

This page was built for publication: Active Learning in Multi-armed Bandits

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3529929)