Students
I supervise PhD students and research interns in reinforcement learning and online learning.
Current PhD students
Pako Maxence TekouSince October 2026
Theory of policy gradient methods.
Djamel Rassem LamouriSince October 2025
Stochastic approximation theory and its connections to machine learning.
Past research internships
M1 and M2 refer to the first and second years of a master's degree, respectively.
Amine OulumSummer 2026
Exploration in policy gradient methods (ongoing project).
Bastien JacquesSummer 2026
Exploration in policy gradient methods (ongoing project).
Nathan BoyerSummer 2025
Best-of-Both-Worlds for linear bandits.
Paper and preprintNathan Van AsscheSummer 2024
Reinforcement learning with predictions.