Arthur Guez
Arthur Guez co-authored Nature papers on game-playing AI at Google DeepMind, including AlphaGo Zero and MuZero. As of October 2026, he is a member of technical staff at Periodic Labs. At McGill University, his 2010 M.Sc. thesis used reinforcement learning to control epileptic seizures. His PhD at UCL's Gatsby Computational Neuroscience Unit, completed in 2015, was supervised by Peter Dayan and David Silver.
Timeline
-
2010
Seizure control with reinforcement learning
He completes an M.Sc. thesis at McGill University in 2010, on adaptive control of epileptic seizures using reinforcement learning.
-
2014–2025
A research scientist at DeepMind
At Google DeepMind, he works as a research scientist from 2014 to 2025.
-
2015
A PhD on Bayes-adaptive planning
In 2015 he completes a PhD at UCL's Gatsby Computational Neuroscience Unit, under Peter Dayan and David Silver. His thesis is titled Sample-based Search Methods for Bayes-Adaptive Planning.
-
2016
A Nature paper on Go
The 2016 Nature paper 'Mastering the game of Go with deep neural networks and tree search' lists him as a co-author.
-
2017
Co-authoring AlphaGo Zero
He co-authors AlphaGo Zero, whose 2017 Nature paper is 'Mastering the Game of Go without Human Knowledge'.
-
2020
The MuZero paper in Nature
The 2020 Nature paper 'Mastering Atari, Go, chess and shogi by planning with a learned model' lists him as a co-author and presents the MuZero algorithm.
-
As of October 2026
Technical staff at Periodic Labs
At Periodic Labs, he is a member of technical staff, after a Google DeepMind role that ended in 2025.
Sources and credits
Photo: acguez.github.io; Arthur Guez's Homepage; creator not stated. License: Not stated by source. Source: acguez.github.io. Cropped to a square and resized. Ask us to remove or replace this photo.