Publications

In this Ph.D. thesis, we study how autonomous vehicles can learn to act safely and avoid accidents, despite sharing the road with human …

We consider the problem of robust and adaptive model predictive control (MPC) of a linear system, with unknown parameters that are …

We propose MDP-GapE, a new trajectory-based Monte-Carlo Tree Search algorithm for planning in a Markov Decision Process in which …

We consider the problem of planning in a Markov Decision Process (MDP) with a generative model and limited computational budget. …

Realistic environments often provide agents with very limited feedback. When the environment is initially unknown, the feedback, in the …

Robust and adaptive stabilisation and constraint satisfaction for linear systems.

Reward-free exploration is a reinforcement learning setting recently studied by Jin et al., who address it by running several …

An attention architecture for behavioural planning with multiple agents.

Projects

Prescription

Determine the statute of limitations for sexual offences in French criminal law

twitter-graph

Fetch and visualize the graph of your Twitter friends

Sisyphe

Learn poetry by progressively hiding words

IGNite

Georeferenced IGN maps of any area

AI tweets

I’m sorry Dave, I’m afraid I can’t do that.

Academia tweets

Witty academics on Twitter

Rl Agents

A collection of Reinforcement Learning agents

Highway Env

A collection of environments for behavioral planning tasks in autonomous driving

PhD Bibliography

References on Optimal Control, Reinforcement Learning and Motion Planning

Mozaic

Automatic reproduction of images with simple primitives

Kestrel Fpv

Quadcopter FPV Racing simulator

Melodic Dictation

Signal processing tool to recover the music score from an audio file

Icarus

Design and construction of a DIY quadcopter running on Arduino Mega

Spelling

Detection of language and spelling correction using a Naive Bayes classifier

Hacktamine

Coding battle webapp

Students Website

Website for the students of Mines ParisTech, powered by django

Talks

Communication at a science popularization event (in French)

Invited Speaker

Safe Reinforcement Learning for Autonomous Driving

Organizing Committee, Teaching Assistant.

Accomplish­ments

Abertis Prize, Best Doctoral Thesis

Recognizes the best research work on Road Safety
See certificate

Best PhD Award

Recognizes the best research work on Modelling, Analysis and Control of Dynamical Systems. Award tied with Eva Petitdemange.
See certificate

Experience

 
 
 
 
 

Research Scientist, Applied

DeepMind

Oct 2021 – Present London
Research on applying Machine Learning to optimize Google products and infrastructure.
 
 
 
 
 

PhD Student, Autonomous Driving department

Renault

Oct 2017 – Oct 2020 Paris
Research on Safe Reinforcement Learning applied to Decision-Making and Motion Planning in Autonomous Driving.
 
 
 
 
 

Control Systems Lead Engineer

Parrot

May 2014 – Sep 2017 Paris
Developement of Guidance, Navigation and Control algorithms running on the flight controller of consumer drones.
 
 
 
 
 

Software Engineering Intern

Twitter

Jun 2013 – Sep 2013 San Francisco
Front-end development and performance optimization in the iOS Mobile team.