Keyword: Self-Normalized https://www.math.univ-toulouse.fr/~agarivie/?q=taxonomy/term/16/all en Learning the distribution with largest mean: two bandit frameworks https://www.math.univ-toulouse.fr/~agarivie/?q=node/181 Fri, 27 Jan 2017 08:55:16 +0000 garivier 181 at https://www.math.univ-toulouse.fr/~agarivie On the Complexity of Best Arm Identification in Multi-Armed Bandit Models https://www.math.univ-toulouse.fr/~agarivie/?q=node/131 Fri, 18 Jul 2014 14:45:29 +0000 garivier 131 at https://www.math.univ-toulouse.fr/~agarivie Optimism in Reinforcement Learning and Kullback-Leibler Divergence https://www.math.univ-toulouse.fr/~agarivie/?q=node/146 Mon, 01 Jun 2015 11:36:33 +0000 garivier 146 at https://www.math.univ-toulouse.fr/~agarivie Bandits for Exploration: Best Arm Identification and Discovery with Probabilistic Experts https://www.math.univ-toulouse.fr/~agarivie/?q=node/136 Fri, 17 Oct 2014 14:57:00 +0000 garivier 136 at https://www.math.univ-toulouse.fr/~agarivie Empirical Likelihood Upper Confidence Bounds For Bandit Models https://www.math.univ-toulouse.fr/~agarivie/?q=node/130 Tue, 10 Jun 2014 11:15:27 +0000 garivier 130 at https://www.math.univ-toulouse.fr/~agarivie On the Complexity of A/B Testing https://www.math.univ-toulouse.fr/~agarivie/?q=node/129 Tue, 13 May 2014 11:21:49 +0000 garivier 129 at https://www.math.univ-toulouse.fr/~agarivie Empirical Likelihood for Optimistic Algorithms in Dynamic Resource Allocation https://www.math.univ-toulouse.fr/~agarivie/?q=node/122 Fri, 11 Apr 2014 07:49:54 +0000 garivier 122 at https://www.math.univ-toulouse.fr/~agarivie Informational Confidence Bounds for Self-Normalized Averages and Applications https://www.math.univ-toulouse.fr/~agarivie/?q=node/118 Fri, 13 Sep 2013 06:23:50 +0000 garivier 118 at https://www.math.univ-toulouse.fr/~agarivie Informational Confidence Bounds for Self-Normalized Averages and Applications https://www.math.univ-toulouse.fr/~agarivie/?q=node/117 Fri, 13 Sep 2013 06:19:44 +0000 garivier 117 at https://www.math.univ-toulouse.fr/~agarivie Kullback-Leibler Upper Confidence Bounds for Optimal Sequential Allocation https://www.math.univ-toulouse.fr/~agarivie/?q=node/19 Tue, 30 Jul 2013 13:32:04 +0000 garivier 19 at https://www.math.univ-toulouse.fr/~agarivie Dynamic resource allocation as an estimation problem https://www.math.univ-toulouse.fr/~agarivie/?q=node/111 Thu, 08 Aug 2013 09:31:58 +0000 garivier 111 at https://www.math.univ-toulouse.fr/~agarivie On Bayesian Upper Confidence Bounds for Bandit Problems https://www.math.univ-toulouse.fr/~agarivie/?q=node/30 Tue, 30 Jul 2013 20:38:16 +0000 garivier 30 at https://www.math.univ-toulouse.fr/~agarivie Apprentissage par renforcement et déviations auto-normalisées https://www.math.univ-toulouse.fr/~agarivie/?q=node/105 Thu, 08 Aug 2013 09:16:15 +0000 garivier 105 at https://www.math.univ-toulouse.fr/~agarivie Analyses d'algorithmes pour l'estimation et l'optimisation stochastiques https://www.math.univ-toulouse.fr/~agarivie/?q=node/104 Thu, 08 Aug 2013 08:59:49 +0000 garivier 104 at https://www.math.univ-toulouse.fr/~agarivie Analyse d'algorithmes pour l'estimation et l'optimisation stochastiques https://www.math.univ-toulouse.fr/~agarivie/?q=node/82 Wed, 07 Aug 2013 20:42:20 +0000 garivier 82 at https://www.math.univ-toulouse.fr/~agarivie