Optimal Best Arm Identification with Fixed Confidence
Year: 2016
Type: preprint
Abstract: We give a complete characterization of the complexity of best-arm identification in one-parameter bandit problems. We prove a new, tight lower bound on the sample complexity. We propose the `Track-and-Stop' strategy, which we prove to be asymptotically optimal. It consists in a new sampling rule (which tracks the optimal proportions of arm draws highlighted by the lower bound) and in a stopping rule named after Chernoff, for which we give a new analysis.
Source: arXiv (Cornell University)
Authors: Garivier, Aurélien, Kaufmann, Emilie
Institutions: Centre National de la Recherche Scientifique, Institut national de recherche en sciences et technologies du numérique, Université Toulouse III - Paul Sabatier, Université de Lille, Centre de Recherche en Informatique, Signal et Automatique de Lille, Université de Toulouse, Institut de Mathématiques de Toulouse
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W2963486287