A bad arm existence checking problem: how to utilize asymmetric problem structure?

DOI10.1007/S10994-019-05854-7MaRDI QIDQ2303673zbMATH OpenOpenAlexFDO

Authors Koji Tabata, Atsuyoshi Nakamura, Junya Honda, Tamiki Komatsuzaki

Publication date 4 March 2020

Published in Machine Learning (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s10994-019-05854-7

zbMATH Keywords

bandit problembest arm identificationonline learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Rationality and learning in game theory (91A26) Probabilistic games; gambling (91A60)

Recommendations

• Good arm identification via bandit feedback
• scientific article; zbMATH DE number 4084786
• scientific article; zbMATH DE number 3976142
• Multi-armed bandits with simple arms
• scientific article; zbMATH DE number 4064878

Cites work

• Action elimination and stopping conditions for the multi-armed bandit and reinforcement learning problems
• Finite-time analysis of the multiarmed bandit problem
• Good arm identification via bandit feedback
• On the complexity of best-arm identification in multi-armed bandit models
• Pure exploration in finitely-armed and continuous-armed bandits
• Some aspects of the sequential design of experiments
• The Nonstochastic Multiarmed Bandit Problem
• The weighted majority algorithm

This page was built for publication: A bad arm existence checking problem: how to utilize asymmetric problem structure?

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2303673)