Mistake bounds on the noise-free multi-armed bandit game

DOI10.1016/J.IC.2019.104453MaRDI QIDQ2280334zbMATHOpenAlexFDO

Authors Atsuyoshi Nakamura, David P. Helmbold, Manfred K. Warmuth

Publication date 18 December 2019

Published in Information and Computation (Search for Journal in Brave)

Full work available at URL http://hdl.handle.net/2115/83379

zbMATH Keywords

bandit problemonline learningcomputational learning theorymistake bound

Mathematics Subject Classification ID

Computational learning theory (68Q32) Probabilistic games; gambling (91A60)

Recommendations

• Noise free multi-armed bandit game
• The Nonstochastic Multiarmed Bandit Problem
• Bandit regret scaling with the effective loss range
• New bounds on the price of bandit feedback for mistake-bounded online multiclass learning
• New bounds on the price of bandit feedback for mistake-bounded online multiclass learning

Cites work

• Noise free multi-armed bandit game
• Prediction, Learning, and Games
• Regret analysis of stochastic and nonstochastic multi-armed bandit problems
• The Nonstochastic Multiarmed Bandit Problem

Cited in

(3)

• A note on the price of bandit feedback for mistake-bounded online learning
• Special issue: selected papers of the 10th international conference on language and automata theory and applications, LATA 2016
• Noise free multi-armed bandit game

This page was built for publication: Mistake bounds on the noise-free multi-armed bandit game

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2280334)