A minimax and asymptotically optimal algorithm for stochastic bandits

zbMath1407.62046arXiv1702.07211MaRDI QIDQ4645646

Pierre Ménard, Aurélien Garivier

Publication date: 10 January 2019

Full work available at URL: https://arxiv.org/abs/1702.07211

zbMATH Keywords

asymptotic optimalityminimax optimalitystochastic multi-armed banditsregret analysisupper confidence bound (UCB)

Mathematics Subject Classification ID

Minimax procedures in statistical decision theory (62C20)

Related Items (3)

Empirical Gittins index strategies with \(\varepsilon\)-explorations for multi-armed bandit problems ⋮ Learning the distribution with largest mean: two bandit frameworks ⋮ Ballooning multi-armed bandits

This page was built for publication: A minimax and asymptotically optimal algorithm for stochastic bandits