Sotabase

Career

· Chief Scientific Officer & Co-founder, Reliant AI2023–
· Research Scientist / RL Team Lead, Google Brain2017–2023
· Research Scientist, DeepMind2013–2017
· PhD in Computer Science, University of Alberta2007–2013
· MS in Computer Science, McGill University2005–2007
· BSc in Computer Science, McGill University2002–2005

Publications (173)

Human-level control through deep reinforcement learning
Nature · 2015
30,344
cited
The Arcade Learning Environment: An Evaluation Platform for General Agents
Journal of Artificial Intelligence Research · 2012
3,209
cited
A Distributional Perspective on Reinforcement Learning
International Conference on Machine Learning · 2017
1,723
cited
Unifying Count-Based Exploration and Intrinsic Motivation
Neural Information Processing Systems · 2016
1,597
cited
An Introduction to Deep Reinforcement Learning
Found. Trends Mach. Learn. · 2018
1,419
cited
Distributional Reinforcement Learning with Quantile Regression
AAAI Conference on Artificial Intelligence · 2017
901
cited
Deep Reinforcement Learning at the Edge of the Statistical Precipice
Neural Information Processing Systems · 2021
804
cited
Count-Based Exploration with Neural Density Models
International Conference on Machine Learning · 2017
665
cited
Safe and Efficient Off-Policy Reinforcement Learning
Neural Information Processing Systems · 2016
658
cited
Automated Curriculum Learning for Neural Networks
International Conference on Machine Learning · 2017
595
cited
Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents
Journal of Artificial Intelligence Research · 2017
591
cited
The Hanabi Challenge: A New Frontier for AI Research
Artificial Intelligence · 2019
397
cited
Autonomous navigation of stratospheric balloons using reinforcement learning
Nature · 2020
383
cited
The Cramer Distance as a Solution to Biased Wasserstein Gradients
arXiv.org · 2017
376
cited
DeepMDP: Learning Continuous Latent Space Models for Representation Learning
International Conference on Machine Learning · 2019
324
cited
Dopamine: A Research Framework for Deep Reinforcement Learning
arXiv.org · 2018
290
cited
A Laplacian Framework for Option Discovery in Reinforcement Learning
International Conference on Machine Learning · 2017
276
cited
Count-Based Exploration with the Successor Representation
AAAI Conference on Artificial Intelligence · 2018
198
cited
Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning
International Conference on Learning Representations · 2021
184
cited
Increasing the Action Gap: New Operators for Reinforcement Learning
AAAI Conference on Artificial Intelligence · 2015
159
cited
Sotabase