Supaero Reinforcement Learning Initiative
Professors, researchers, engineers, students, researching open questions in Reinforcement Learning. Most of us are affiliated with ISAE-SUPAERO, where the team is hosted.
We work on state of the art algorithms, study their properties mathematically and empirically, and apply them to challenging problems to bridge a gap between theory and real applications. We focus on Reinforcement Learning for sequential decision making problems and its links with other disciplines (e.g. Operations Research, Evolutionary Computation, Planning, Optimization).
Autonomous vehicles, control of optimization processes, rehabilitation exoskeleton control, video games, aircraft landing scheduling, satellite resources planning, sailboat and UAV planning and control, mobile robot mission planning, computer bug tracking, fluid flows control.
Current Post-docs (), PhD students (
) and interns (
):
Guillaume Levy (intern 2025, E. Rachelson) — Model-based RL
Thomas Delliaux (PhD 2023-, E. Rachelson) — Representations in RL
Alexandre Bertin (PhD 2023-, V. Pancaldi) — Dynamic treatment regimes for tumor micro-environments
Paul Strang (PhD 2022-, S. Kedad-Sidhoum, Z. Ales, E. Rachelson) — Solving repeated combinatorial optimization problems with machine learning
Hedwin Bonnavaud (PhD 2021-, C. Chanel, C. Lesire, A. Albore, E. Rachelson) — Planning and RL for robot tasks
Paul-Antoine Le Tolguenec (PhD 2021-, D. Wilson, E. Rachelson) — Autopilot testing with RL
Adil Zoutine (PhD 2021-, E. Rachelson) — Robustness to model uncertainties in RL
Mehdi Zouitine (PhD 2021-, A. Lagnoux, C. Pellegrini, E. Rachelson), RL for heterogeneous space observation missions planning
The “former members” list has grown quite long over time and can be found here.
Don’t hesitate to contact us.
For prospective students. We often offer student projects, “parcours recherche” (ISAE-SUPAERO), or internships. Get in touch with us!