Keyword: Bandit Problems https://www.math.univ-toulouse.fr/~agarivie/?q=taxonomy/term/7/all en Non-Asymptotic Sequential Tests for Overlapping Hypotheses and application to near optimal arm identification in bandit models https://www.math.univ-toulouse.fr/~agarivie/?q=node/230 Thu, 09 May 2019 09:34:57 +0000 garivier 230 at https://www.math.univ-toulouse.fr/~agarivie X-Armed Bandits: Optimizing Quantiles and Other Risks https://www.math.univ-toulouse.fr/~agarivie/?q=node/228 Tue, 23 Apr 2019 07:57:34 +0000 garivier 228 at https://www.math.univ-toulouse.fr/~agarivie Sequential Test for the Lowest Mean: From Thompson to Murphy Sampling https://www.math.univ-toulouse.fr/~agarivie/?q=node/211 Fri, 18 May 2018 20:17:00 +0000 garivier 211 at https://www.math.univ-toulouse.fr/~agarivie Complexity of Sequential Decision Problems https://www.math.univ-toulouse.fr/~agarivie/?q=node/222 Mon, 12 Nov 2018 12:54:37 +0000 garivier 222 at https://www.math.univ-toulouse.fr/~agarivie Profitable Bandits https://www.math.univ-toulouse.fr/~agarivie/?q=node/209 Wed, 09 May 2018 20:49:16 +0000 garivier 209 at https://www.math.univ-toulouse.fr/~agarivie Introduction à certains problèmes de décisions séquentielles https://www.math.univ-toulouse.fr/~agarivie/?q=node/221 Fri, 12 Oct 2018 12:18:52 +0000 garivier 221 at https://www.math.univ-toulouse.fr/~agarivie Comment les maths peuvent-elles aider les machines à apprendre ? https://www.math.univ-toulouse.fr/~agarivie/?q=node/217 Mon, 01 Oct 2018 13:22:03 +0000 garivier 217 at https://www.math.univ-toulouse.fr/~agarivie Explore First, Exploit Next: The True Shape of Regret in Bandit Problems https://www.math.univ-toulouse.fr/~agarivie/?q=node/193 Sat, 16 Dec 2017 16:29:50 +0000 garivier 193 at https://www.math.univ-toulouse.fr/~agarivie Optimization of a SSP's Header Bidding Strategy using Thompson Sampling https://www.math.univ-toulouse.fr/~agarivie/?q=node/206 Mon, 07 May 2018 08:48:54 +0000 garivier 206 at https://www.math.univ-toulouse.fr/~agarivie Missing Mass, and Optimal Discovery https://www.math.univ-toulouse.fr/~agarivie/?q=node/210 Mon, 14 May 2018 13:11:46 +0000 garivier 210 at https://www.math.univ-toulouse.fr/~agarivie KL-UCB-switch: optimal regret bounds for stochastic bandits from both a distribution-dependent and a distribution-free viewpoints https://www.math.univ-toulouse.fr/~agarivie/?q=node/208 Mon, 07 May 2018 09:28:59 +0000 garivier 208 at https://www.math.univ-toulouse.fr/~agarivie Minimisation du regret pour des bandits non-paramétriques grâce à la méthode de la vraisemblance empirique https://www.math.univ-toulouse.fr/~agarivie/?q=node/201 Thu, 26 Apr 2018 19:57:37 +0000 garivier 201 at https://www.math.univ-toulouse.fr/~agarivie 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 Thresholding Bandit for Dose-ranging: The Impact of Monotonicity https://www.math.univ-toulouse.fr/~agarivie/?q=node/195 Sat, 16 Dec 2017 16:35:33 +0000 garivier 195 at https://www.math.univ-toulouse.fr/~agarivie A minimax and asymptotically optimal algorithm for stochastic bandits https://www.math.univ-toulouse.fr/~agarivie/?q=node/183 Thu, 23 Feb 2017 14:37:12 +0000 garivier 183 at https://www.math.univ-toulouse.fr/~agarivie