Safwan Labbi

Safwan Labbi

Hi! I am a third year PhD student working on Reinforcement Learning/Federated Learning

Publications

A complete and (very likely) more up-to-date list of my articles is available on my Google Scholar profile.

List of Publications

  1. Refined Analysis of Entropy-Regularized Actor-Critic
    Safwan Labbi, Paul Mangold, Daniil Tiapkin, Eric Moulines.
    ICML 2026.

  2. Beyond Softmax and Entropy: Convergence Rates of Policy Gradients with f-SoftArgmax Parameterization & Coupled Regularization
    Safwan Labbi, Daniil Tiapkin, Paul Mangold, Eric Moulines.
    ICLR 2026.

  3. On Global Convergence Rates for Federated Softmax Policy Gradient under Heterogeneous Environments
    Safwan Labbi, Paul Mangold, Daniil Tiapkin, Eric Moulines.
    AISTATS 2026.

  4. Federated UCBVI: Communication-Efficient Federated Regret Minimization with Heterogeneous Agents
    Safwan Labbi, Daniil Tiapkin, Lorenzo Mancini, Paul Mangold, Eric Moulines.
    AISTATS 2025.

  5. Mean-Field Multi-Agent Learning: A Trust Region Approach
    Antonio Ocello, Lorenzo Mancini, Safwan Labbi, Daniil Tiapkin, Adel Belouchrani, Eric Moulines.
    EUSIPCO 2025.

  6. Integrating FedDRL for Efficient Vehicular Communication in Smart Cities
    Lorenzo Mancini, Safwan Labbi, Karim Abed Meraim, Fouzi Boukhalfa, Alain Durmus, Paul Mangold, Eric Moulines.
    Lecture Notes in Intelligent Transportation and Infrastructure. Springer, 2025.

  7. SCAFFLSA: Taming Heterogeneity in Federated Linear Stochastic Approximation and TD Learning
    Paul Mangold, Sergey Samsonov, Safwan Labbi, Ilya Levin, Reda Alami, Alexey Naumov, Eric Moulines.
    NeurIPS 2024.

  8. Joint Channel Selection using FedDRL in V2X
    Lorenzo Mancini, Safwan Labbi, Karim Abed Meraim, Fouzi Boukhalfa, Alain Durmus, Paul Mangold, Eric Moulines.
    IEEE MECOM, 2024.