I'm a phd student in machine learning. I'm particulary interested in reinforcement learning, constrainted problems, and deep-learning. Robotics and dialogue are my favorite applications. I am a member of the team SequeL at INRIA and NADIA team at Orange Labs. My thesis director is Olivier Pietquin (Google DeepMind, INRIA). I'm also supervised by Romain Laroche (Microsoft Maluuba), Tanguy Urvoy (Orange Labs) and Jean-Léon Bouraoui (Orange Labs).
Reinforcement learning for dialog systems optimization with user adaptation.
Automated planning under uncertainty with multiple objectives.
Improvements of a new dynamic neural field model: Randomly Spiking Dynamic Neural Fields (RSDNF).
Predicting user behavior on the web.
Lectures and lab sessions of reinforcement learning for computer science MOCAD master.
Tutor for the computer science part of the 1st year of university.
Apart from artificial intelligence stuff and coding, I'm a Warhammer enthusiast and other tabletop games. I also play poker from time to time. When it's cold outside, I enjoy reading, mostly sci-fi novels but also mangas and fantasy stuff. Otherwise I like mountain biking.