A Non-Asymptotic Approach to Best-Arm Identification for Gaussian Bandits Antoine BARRIER, Aurélien GARIVIER, Tomáš KOCÁK 1 April 2022 PDF Poster Slides Video PMLR HAL arXiv BibTeX BAI fixed confidence Antoine BARRIER PhD student in Sequential Learning I’m interested in Optimization Algorithms in Sequential Learning. Aurélien GARIVIER Tomáš KOCÁK
