Robbing the bandit

DOI10.1145/1109557.1109660MaRDI QIDQ3581558zbMATH OpenOpenAlexFDO

Authors Varsha Dani, Thomas P. Hayes

Publication date 16 August 2010

Published in Proceedings of the seventeenth annual ACM-SIAM symposium on Discrete algorithm - SODA '06 (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1145/1109557.1109660

Mathematics Subject Classification ID

Combinatorial optimization (90C27)

Cited in

(7)

• General bounds for incremental maximization
• Regret bounded by gradual variation for online convex optimization
• Online linear optimization and adaptive routing
• Following the Perturbed Leader to Gamble at Multi-armed Bandits
• Combinatorial bandits
• A unified analysis of nonstochastic delayed feedback for combinatorial semi-bandits, linear bandits, and MDPs
• Online learning for traffic navigation in congested networks

This page was built for publication: Robbing the bandit

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3581558)