Rémi Munos
Also known as Remi Munos
Rémi Munos is a researcher in reinforcement learning, bandit problems, and Monte-Carlo tree search. He defended a doctorate on reinforcement learning in 1997 and was an associate professor at École Polytechnique from 2000 to 2006. His papers include Safe and Efficient Off-Policy Reinforcement Learning and A Distributional Perspective on Reinforcement Learning. In 2018 DeepMind named him to lead its new Paris laboratory, and in 2023 a paper he co-wrote won an ICML Outstanding Paper award. As of October 2026, he directs that laboratory.
Timeline
-
1997
A doctorate on reinforcement learning
He defends a doctorate on reinforcement learning in 1997 at the École des hautes études en sciences sociales.
-
2000–2006
Associate professor at École Polytechnique
At the Centre de Mathématiques Appliquées of École Polytechnique, he works as an associate professor from 2000 to 2006.
-
2014
Bandits and Monte-Carlo tree search
He publishes From Bandits to Monte-Carlo Tree Search in 2014, a study of the optimistic principle for optimization and planning.
-
2016–2017
Off-policy and distributional learning
He co-writes Safe and Efficient Off-Policy Reinforcement Learning in 2016 and A Distributional Perspective on Reinforcement Learning in 2017.
-
2018
Heading DeepMind's Paris lab
DeepMind names him to lead its new Paris laboratory, which the company announces in March 2018.
-
2023
An ICML Outstanding Paper
He co-writes Adapting to game trees in zero-sum imperfect information games, which wins an Outstanding Paper award at ICML 2023.
-
As of October 2026
Directing DeepMind's Paris lab
He directs DeepMind's Paris laboratory, which DeepMind names him to lead in 2018.
Sources and credits
Photo: We have no published photo of Rémi Munos yet. Send us a free-licensed photo.
- Rémi Munos - The Mathematics Genealogy Project
- Rémi Munos — ActuIA
- Rémi Munos - Chess Programming Wiki
- From Bandits to Monte-Carlo Tree Search: The Optimistic Principle Applied to Optimization and Planning | ML Anthology
- [1606.02647] Safe and Efficient Off-Policy Reinforcement Learning
- [1707.06887] A Distributional Perspective on Reinforcement Learning
- DeepMind installe un nouveau laboratoire à Paris qui sera dirigé par Rémi Munos — ActuIA
- Retour à Paris / A return to Paris — Google DeepMind
- ICML 2023 Awards
- Adapting to game trees in zero-sum imperfect information games