The \(K\)-armed dueling bandits problem

DOI10.1016/J.JCSS.2011.12.028zbMath1283.68181DBLPjournals/jcss/YueBKJ12OpenAlexW2044493620WikidataQ29300682 ScholiaQ29300682MaRDI QIDQ440003

Thorsten Joachims, Yisong Yue, Josef Broder, Robert D. Kleinberg

Publication date: 17 August 2012

Published in: Journal of Computer and System Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.jcss.2011.12.028

zbMATH Keywords

online learningmulti-armed banditspreference elicitation

Mathematics Subject Classification ID

Computational learning theory (68Q32) Learning and adaptive systems in artificial intelligence (68T05) Probabilistic games; gambling (91A60) Online algorithms; streaming algorithms (68W27)

Related Items (13)

Top-\(\kappa\) selection with pairwise comparisons ⋮ Parallel distributed block coordinate descent methods based on pairwise comparison oracle ⋮ Unnamed Item ⋮ Unnamed Item ⋮ The \(K\)-armed dueling bandits problem ⋮ Lexicographic refinements in stationary possibilistic Markov decision processes ⋮ How good is a two-party election game? ⋮ Active ranking from pairwise comparisons and when parametric assumptions do not help ⋮ Preference-based reinforcement learning: evolutionary direct policy search using a preference-based racing algorithm ⋮ Global optimization based on active preference learning with radial basis functions ⋮ On testing transitivity in online preference learning ⋮ Lexicographic refinements in possibilistic decision trees and finite-horizon Markov decision processes ⋮ Unnamed Item

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• The \(K\)-armed dueling bandits problem
• Asymptotically efficient adaptive allocation rules
• Regret bounds for sleeping experts and bandits
• Computing with Noisy Information
• A PAC-Bayesian margin bound for linear classifiers
• The Nonstochastic Multiarmed Bandit Problem
• 10.1162/153244303321897663
• 10.1162/1532443041827916
• Probability Inequalities for Sums of Bounded Random Variables
• Regret Minimization Under Partial Monitoring
• Robust Reductions from Ranking to Classification
• Some aspects of the sequential design of experiments
• Finite-time analysis of the multiarmed bandit problem

This page was built for publication: The \(K\)-armed dueling bandits problem