KL-UCB-switch: optimal regret bounds for stochastic bandits from both a distribution-dependent and a distribution-free viewpoints

From MaRDI portal
Publication:6301530

arXiv1805.05071MaRDI QIDQ6301530

Pierre Menard, Hédi Hadiji, Gilles Stoltz, Aurélien Garivier

Publication date: 14 May 2018




Has companion code repository: https://github.com/SMPyBandits/SMPyBandits









This page was built for publication: KL-UCB-switch: optimal regret bounds for stochastic bandits from both a distribution-dependent and a distribution-free viewpoints