Johan Ferret
Research Scientist at Google DeepMind
Paris, Ile-de-France
Summary
👤
Senior🎓
Top SchoolJohan Ferret is a Research Scientist at Google DeepMind with a decade of experience at the intersection of deep reinforcement learning, large language models, and model alignment. Trained at École Polytechnique and Télécom Paris, he progressed from applied ML roles and a PhD at Inria to production-focused RL engineering and research at DeepMind, contributing core improvements to the widely used Acme RL library (R2D2, IMPALA, replay and logging enhancements). He blends rigorous academic grounding with hands-on engineering—shipping algorithmic refinements, learning-rate annealing options, and robust replay mechanisms—while exploring creative outlets like algorithmic art. Based in Paris, he brings a pragmatic curiosity that bridges foundational research and useful tooling for scalable RL systems.
10 years of coding experience
6 years of employment as a software developer
M.Sc - Applied Mathematics, Computer Science, M.Sc - Applied Mathematics, Computer Science at Télécom ParisM.Sc - Data Science, M.Sc - Data Science at Ecole polytechnique
French, English, Spanish
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (9)
agent10
jax10
python10
reinforcement-learning10
machine-learning9
algorithms8
tensorflow8
data-structure7
data-structures7
Programming languages (2)
Github contributions (5)
google-deepmind/acme
Feb 2022 - Nov 2022
A library of reinforcement learning components and agents
Role in this project:
ML Engineer
ML EngineerContributions:5 commits in 9 months
Contributions summary:Johan contributed to the reinforcement learning library by implementing and modifying core components. They refactored replay mechanisms and added functionalities to existing modules like R2D2, IMPALA. The changes included adding options for controlling the number of steps and integrating learning rate annealing. The user also worked on logging improvements within the IMPALA framework.
reinforcement-learningagents
ferretj/papers
Sep 2017 - Jul 2018
Contributions:67 commits, 58 pushes, 1 branch in 10 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.