Optimal Best-Arm Identification Methods for Tail-Risk Measures

v1v2v3 (latest)

Optimal Best-Arm Identification Methods for Tail-Risk Measures

17 August 2020

Shubhada Agrawal

Wouter M. Koolen

ArXiv (abs)PDF HTML

Papers citing "Optimal Best-Arm Identification Methods for Tail-Risk Measures"

5 / 5 papers shown

Title
Sequential Learning of the Pareto Front for Multi-objective Bandits Elise Crépon Aurélien Garivier Wouter M. Koolen 87 5 0 29 Jan 2025
Top Two Algorithms Revisited Marc Jourdan Rémy Degenne Dorian Baudry R. D. Heide E. Kaufmann 72 42 0 13 Jun 2022
From Optimality to Robustness: Dirichlet Sampling Strategies in Stochastic Bandits Dorian Baudry Patrick Saux Odalric-Ambrym Maillard 57 7 0 18 Nov 2021
A Unifying Theory of Thompson Sampling for Continuous Risk-Averse Bandits Joel Q. L. Chang Vincent Y. F. Tan 97 14 0 25 Aug 2021
Optimal Thompson Sampling strategies for support-aware CVaR bandits Dorian Baudry Romain Gautron E. Kaufmann Odalric-Ambrym Maillard 49 33 0 10 Dec 2020