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

v1v2v3 (latest)

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

14 May 2018

Aurélien Garivier

Pierre Menard

ArXiv (abs)PDF HTML

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

10 / 10 papers shown

Title
Tsallis-INF: An Optimal Algorithm for Stochastic and Adversarial Bandits Julian Zimmert Yevgeny Seldin AAML 184 182 0 19 Jul 2018
A minimax and asymptotically optimal algorithm for stochastic bandits Pierre Ménard Aurélien Garivier 80 60 0 23 Feb 2017
Regret Analysis of the Anytime Optimally Confident UCB Algorithm Tor Lattimore 82 26 0 29 Mar 2016
Explore First, Exploit Next: The True Shape of Regret in Bandit Problems Aurélien Garivier Pierre Ménard Gilles Stoltz 77 214 0 23 Feb 2016
Thompson Sampling for 1-Dimensional Exponential Family Bandits N. Korda E. Kaufmann Rémi Munos 76 155 0 12 Jul 2013
Prior-free and prior-dependent regret bounds for Thompson Sampling Sébastien Bubeck Che-Yu Liu 122 96 0 21 Apr 2013
Kullback-Leibler upper confidence bounds for optimal sequential allocation Olivier Cappé Aurélien Garivier Odalric-Ambrym Maillard Rémi Munos Gilles Stoltz 134 395 0 03 Oct 2012
A Finite-Time Analysis of Multi-armed Bandits Problems with Kullback-Leibler Divergences Odalric-Ambrym Maillard Rémi Munos Gilles Stoltz 99 146 0 29 May 2011
Minimax Policies for Combinatorial Prediction Games Jean-Yves Audibert Sébastien Bubeck Gabor Lugosi OffRL 195 82 0 24 May 2011
The KL-UCB Algorithm for Bounded Stochastic Bandits and Beyond Aurélien Garivier Olivier Cappé 201 615 0 12 Feb 2011

We use cookies and other tracking technologies to improve your browsing experience on our website, to show you personalized content and targeted ads, to analyze our website traffic, and to understand where our visitors are coming from. See our policy.