← Team

Mahdi Kallel

Ph.D. student

M.Sc. Mahdi Kallel

Reinforcement Learning and Computational Decision-Making
Julius-Maximilians-Universität Würzburg
John-Skilton-Straße 8a, 97074 Würzburg
Building JS8 · Room 04.017

mahdi.kallel@uni-wuerzburg.de

About

I joined the LiteRL group at JMU Würzburg in April 2023 as a Ph.D. candidate. Before joining the group, I graduated from Télécom Paris with a major in Machine Learning and Operations Research.

I wrote my thesis, “Deterministic Exploration in Reinforcement Learning”, while working in the Scool group at INRIA Lille as a visiting student under the supervision of Prof. Riad Akrour. In this work, we built a bridge between direct policy search methods, which are oblivious to the sequential nature of MDPs, and value-based reinforcement learning algorithms, which suffer under sparse rewards.

I am passionate about model-based reinforcement learning, Bayesian optimization, explainability, and incorporating human feedback into the learning loop.

Publications with LiteRL (13)

  1. Journal

    TMLR 2026

    Do Not Imitate, Reinforce: Iterative Classification via Belief Refinement

    M. Kallel, J. Tölle, A. Hendawy, C. D’Eramo

    Transactions on Machine Learning Research (TMLR)

  2. Journal

    RLJ 2026

    PPO+: Enhancing Proximal Policy Optimization

    M. Kallel, J. L. Holgado-Alvarez, S. Tosatto, C. D’Eramo

    Reinforcement Learning Journal (RLJ)

  3. Conference

    ICLR 2026

    Use the Online Network If You Can: Towards Fast and Stable Reinforcement Learning

    A. Hendawy, H. Metternich, T. Vincent, M. Kallel, J. Peters, C. D’Eramo

    International Conference on Learning Representations (ICLR)

  4. Workshop

    NeurIPS 2026

    AXIOM: Foundations of Efficient Deep Learning

    M. Kallel, N. Jamoussi, J. Tölle, M. Kountouris, C. D’Eramo

    Workshop at Advances in Neural Information Processing Systems (NeurIPS)

  5. Workshop

    EWRL 2026

    Use the Online Network If You Can: Towards Fast and Stable Reinforcement Learning

    A. Hendawy, H. Metternich, T. Vincent, M. Kallel, J. Peters, C. D’Eramo

    European Workshop on Reinforcement Learning (EWRL)

  6. Workshop

    EWRL 2026

    Do Not Imitate, Reinforce: Iterative Classification via Belief Refinement

    M. Kallel, J. Tölle, A. Hendawy, C. D’Eramo

    European Workshop on Reinforcement Learning (EWRL)

  7. Workshop

    RLC 2026

    Do Not Imitate, Reinforce: Iterative Classification via Belief Refinement

    M. Kallel, J. Tölle, A. Hendawy, C. D’Eramo

    Finding the Frame Workshop, Reinforcement Learning Conference (RLC)

  8. Workshop

    EWRL 2025

    Revisiting Proximal Policy Optimization

    M. Kallel, J. L. Holgado-Alvarez, S. Tosatto, C. D’Eramo

    European Workshop on Reinforcement Learning (EWRL)

  9. Journal

    RLJ 2024

    Cyclicity-Regularized Coordination Graphs

    O. Järnefelt, M. Kallel, C. D’Eramo

    Reinforcement Learning Journal (RLJ)

  10. Conference

    ICLR 2024

    Augmented Bayesian Policy Search

    M. Kallel, D. Basu, R. Akrour, C. D’Eramo

    International Conference on Learning Representations (ICLR)

  11. Workshop

    EWRL 2024

    Augmented Bayesian Policy Search

    M. Kallel, D. Basu, R. Akrour, C. D’Eramo

    European Workshop on Reinforcement Learning (EWRL)

  12. Workshop

    EWRL 2024

    Cyclicity-Regularized Coordination Graphs

    O. Järnefelt, M. Kallel, C. D’Eramo

    European Workshop on Reinforcement Learning (EWRL)

  13. Workshop

    EWRL 2024

    Revisiting On-Policy Deep Reinforcement Learning

    M. Kallel, S. Tosatto, C. D’Eramo

    European Workshop on Reinforcement Learning (EWRL)