Since October 2023, I have been a PhD student in the CMAP team at École Polytechnique (Paris), working at the intersection of reinforcement learning and federated learning. I am supervised by Eric Moulines, Alain Durmus, and Karim Abed-Meraim, and I also collaborate closely with Paul Mangold and Daniil Tiapkin.

Before that, I studied at Télécom Paris and completed the MVA Master’s program.

My research interests include

• Federated Reinforcement Learning
• Theory of Reinforcement Learning
• Federated Learning and Personalization

News

• January 2026: Two of my papers as a first-author were accepted at ICLR 2026 and AISTATS 2026, respectively: “Beyond Softmax and Entropy: Convergence Rates of Policy Gradients with f-SoftArgmax Parameterization & Coupled Regularization” and “On Global Convergence Rates for Federated Softmax Policy Gradient under Heterogeneous Environments”! I will attend both conferences to present my work. Feel free to come chat if you’d like to discuss federated learning or policy gradients!
• January 2025: My first paper as a first-author ‘Federated UCBVI: Communication-Efficient Federated Regret Minimization with Heterogeneous Agents’ has been accepted at AISTATS 2025!
• September 2024: My first paper ‘SCAFFLSA: Taming Heterogeneity in Federated Linear Stochastic Approximation and TD Learning’ has been accepted at NeurIPS 2024!
• October 2023: I am starting a PhD at Ecole Polytechnique!