I am a PhD candidate in Mathematics and Artificial Intelligence at Institut Polytechnique de Paris, in the SAMOVAR laboratory, within PEPR Future Networks’ HISEC project. My research focuses on the security of deep reinforcement learning for real-world autonomous cyber-physical systems. My current case study concerns reconfigurable intelligent surfaces (RIS) for physical-layer security in future 6G networks.
Alongside my PhD, I’m building expertise in meta-learning and adaptation methods. My double degree in mathematics and fundamental physics shapes how I connect learning algorithms with physical models and real-world constraints.
I attended EWRL 2026 in Lille, France, on October 5–7, where I presented a poster on our paper “A Survey of Reinforcement Learning for Autonomous Air Combat: Current Progresses and Limitations”.
Read the publicationOur survey of reinforcement learning for autonomous air combat, co-authored with Thibault Lahire, was published in the AAMAS 2026 proceedings !
Read the publicationOur work on fairness-aware B5G physical-layer security received the Best Paper Award at FPS 2025 !
Explore the publicationResearch in practice
RL & Autonomous Systems
A structured survey of reinforcement learning for autonomous air combat, comparing environments, control architectures and the challenges of reproducibility and real-world transfer.
RL & Wireless Security
A reinforcement learning reward strategy for reconfigurable intelligent surfaces that improves fairness among legitimate users while maintaining physical-layer security.
Best Paper Award
A selection of questions, methods and physical systems that shape my research interests.
I enjoy reading about nuclear fusion and quantum algorithms to broaden my scientific understanding. These are personal reading interests and possible long-term directions, outside my current research.