Algorithms for adversarial bandit problems with multiple plays

DOI10.1007/978-3-642-16108-7_30MaRDI QIDQ4930712zbMATH OpenOpenAlexFDO

Authors Taishi Uchiya, Atsuyoshi Nakamura, Mineichi Kudo

Publication date 1 October 2010

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

Full work available at URL http://hdl.handle.net/2115/47057

zbMATH Keywords

adversarial bandit problemmulti-armed bandit problemonline learning

Mathematics Subject Classification ID

Analysis of algorithms and problem complexity (68Q25) Computational learning theory (68Q32) Online algorithms; streaming algorithms (68W27) Multistage and repeated games (91A20) Probabilistic games; gambling (91A60)

Recommendations

• The Nonstochastic Multiarmed Bandit Problem
• Combinatorial bandits
• Multi-player bandits: the adversarial case
• Better algorithms for benign bandits
• Following the Perturbed Leader to Gamble at Multi-armed Bandits

Cited in

(12)

• Noise free multi-armed bandit game
• Exploration and exploitation of scratch games
• Combinatorial bandits
• Multi-player bandits revisited
• Multi-player bandits: the adversarial case
• Tsallis-INF: an optimal algorithm for stochastic and adversarial bandits
• Dueling bandit problems
• Periodic bandits and wireless network selection
• Nested-Batch-Mode Learning and Stochastic Optimization with An Application to Sequential MultiStage Testing in Materials Science
• Adversarial bandits with knapsacks
• Corruption-tolerant bandit learning
• A unified analysis of nonstochastic delayed feedback for combinatorial semi-bandits, linear bandits, and MDPs

This page was built for publication: Algorithms for adversarial bandit problems with multiple plays

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4930712)