Scholar
Marc G. Bellemare
Google Scholar ID: uyYPun0AAAAJ
Reliant AI
Citations & Impact
Citations
47,852
H-index
44
i10-index
75
Publications
20
Co-authors
8
list available
Publications
Resume (English only)
Academic Achievements
- Published a book on distributional reinforcement learning (MIT Press, Spring 2023), which surveys the core elements of distributional reinforcement learning. Co-authored with Will Dabney and Mark Rowland. Published 'Autonomous Navigation of Stratospheric Balloons' in Nature (2020). Open-sourced a high-fidelity replica of the original simulator, offering a unique challenge for reinforcement learning algorithms. The Arcade Learning Environment (ALE) is a reinforcement-learning interface that enables artificial agents to play Atari 2600 games.
Research Experience
- Led the reinforcement learning efforts of the Google Brain team in Montréal and worked as a research scientist at DeepMind in the UK. Collaborated with Loon to use deep reinforcement learning to improve the navigation capabilities of stratospheric balloons.
Education
- PhD advisors: Michael Bowling and Joel Veness.
Background
- Chief Scientific Officer at Reliant AI, Adjunct Professor at McGill University and Université de Montréal, Canada CIFAR AI Chair. His PhD research introduced the Atari 2600 as a large-scale benchmark for reinforcement learning research, leading to the emergence of deep reinforcement learning. He and his research group continue to push the frontiers of applied deep reinforcement learning.
Miscellany
- Co-founder of Reliant AI, a generative AI startup based in Montréal, Canada and Berlin, Germany.
