CV
See also the pdf version here (Last update: 2024-10-24).
Education
2023 – 2024 : Master degree “Mathematics, Vision, Learning” (MVA) at École Normale Supérieure Paris-Saclay.
2022 – 2023 : Diploma “Research Year in Artificial Intelligence” (ARIA) at École Normale Supérieure Paris-Saclay.
2021 – 2022 : First year of a Master’s degree in computer science at École Normale Supérieure Paris-Saclay.
2020 – 2021 : Bachelor’s degree in Computer Science at École Normale Supérieure Paris-Saclay.
2018 – 2020 : Preparatory classes at Lycée Thiers, Marseille: two-year undergraduate intensive courses in mathematics and physics preparing for the national competitive exam for entry to top french engineering schools.
Work experience
PhD Student at Inria Lille. Supervised by Émilie Kaufmann and Debabrota Basu in the Scool team. Research Topic : Responsible Reinforcement Learning: Robustness and Privacy for & by Sequential Decision Making
Research internship with Flowers team at INRIA Bordeaux supervised by Clément Moulin-Frier and Pierre-Yves Oudeyer. Topic: Emergence, control and open-ended evolution in cellular automata (April – September 2024).
Research internship with Scool team at INRIA Lille supervised by Odalric-Ambrym Maillard and Debabrota Basu. Topic: Developing Three-Risk-Proof Sequential Decision Making for Agricultural Decisions under Environmental Risks (February – July 2023)
Research internship at Centre Borelli laboratory in ENS Paris-Saclay supervised by Thibaud Ehret. Topic: Image restoration through real noise modeling (September 2022 – January 2023)
Research internship at the Chair of Information Technology of the University of Leoben under the supervision of Ronald Ortner. Topic : Algorithms for satisficing in reinforcement learning (February – July 2022)
Research internship with team FLOWERS at INRIA Laboratory in Bordeaux supervised by Masataka Sawayama. Topic : Computational models for human multiple object tracking (June – July 2021).
Skills
Programming languages: Python, C++, OCamL, Rust
Machine Learning : Reinforcement Learning, Sequential Learning, Computer Vision, Deep Learning
Publications
Regret Bounds for Satisficing in Multi-Armed Bandit Problems
Michel, T., Hajiabolhassan, H., & Ortner, R. (2023). "Regret Bounds for Satisficing in Multi-Armed Bandit Problems." Transactions on Machine Learning Research.