McGill University
University of Alberta
Joëlle PineauChief AI Officer · CohereResearcher↗
Researcher
Marc G. Bellemare
CohereVP Modeling
Bellemare created a standard Atari testbed that helped researchers compare game-playing AI and accelerate deep reinforcement learning. He later developed methods that let agents consider the range of possible rewards, not just the average. After co-founding Reliant AI, he joined Cohere as VP of Modelling in 2026.
Career & education
Current roleCohere2026-presentVP Modeling
Cohere2026-presentPreviously
Reliant AI2023-2026Chief Scientific Officer and Co-founder
Google2017-2023Research Scientist
Reliant AI2023-2026Google2017-2023Work and education history is primarily focused on AI-relevant roles and may not be comprehensive.
Citation Trend
Total citations to scholarly work, including research papers, technical reports, books and theses, as recorded by Google Scholar. Each point is a dated snapshot.
citations68,577As of Jun 15, '26
citations0Since last snapshot, Jun 14, '26
Selected contributions
Human-level control through deep reinforcement learning
With Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, Alex Graves, Martin Riedmiller and others ·Presented DQN, learning to play 49 Atari games from screen images and game scores.
Based on public sources. If accuracy is important, verify details using the links or references.
For corrections, updates, or requests to remove information, contact us.
Reviewed August 22, 2026 · Checked for accuracy and new information.
