Pierre Ménard

A minimax and asymptotically optimal algorithm for stochastic bandits

Pierre Ménard, Aurélien Garivier · arXiv (Cornell University) · 2017 · 72 citations · Full text

Business, Decision Sciences, Decision Theory +9

Fast active learning for pure exploration in reinforcement learning

Pierre Ménard, Omar Darwiche Domingues, Anders Jönsson et al. · Repositori digital de la UPF (Universitat Pompeu Fabra) · 2020 · 29 citations · Full text

Computing, Computer Science, Artificial Intelligence +16

Gamification of Pure Exploration for Linear Bandits

Rémy Degenne, Pierre Ménard, Xuedong Shang et al. · arXiv (Cornell University) · 2020 · 23 citations · Full text

Business, Decision Sciences, Algorithms +12

Explore First, Exploit Next: The True Shape of Regret in Bandit Problems

Aurélien Garivier, Pierre Ménard, Gilles Stoltz · Mathematics of Operations Research · 2018 · 17 citations · Full text

Business, Decision Sciences, Mathematics +13

Regret bounds for kernel-based reinforcement learning

Omar Darwiche Domingues, Pierre Ménard, Matteo Pirotta et al. · LillOA (Université de Lille (University Of Lille)) · 2020 · 16 citations · Full text

Computing, Computer Science, Algorithms +13