Marc G. Bellemare
Appointment
Associate Fellow
Canada CIFAR AI Chair
Learning in Machines & Brains
Pan-Canadian AI Strategy
About
Marc G. Bellemare is a Canada CIFAR AI Chair at Mila, a CIFAR associate fellow of the Learning in Machines & Brains program, an adjunct professor at the School of Computer Science at McGill University, and a research scientist at Google Brain in Montréal.
Bellemare’s research lies at the intersection of reinforcement learning and statistical prediction. His work spans both theoretical and practical contributions, including a novel distributional treatment of reinforcement learning, a theory of exploration in high-dimensional state spaces, the development of the highly-successful Arcade Learning Environment for evaluating artificial agents, and deep reinforcement learning. His long-term goal is the design of generally competent agents: agents that can successfully operate in a wide range of environments and eventually exhibit the gamut of behaviour that we attribute to humans: curiosity, boredom, competence, and emergent communication.
Awards
- Best Paper Award, ICML Exploration in Reinforcement Learning Workshop, 2019
- Best Paper Award, Reinforcement Learning and Decision-Making Symposium (RLDM), 2019
Relevant Publications
François-Lavet, V., Henderson, P., Islam, R., Bellemare, M. G., & Pineau, J. (2018). An introduction to deep reinforcement learning.
Bellemare, M. G., Dabney, W., & Munos, R. (2017). A distributional perspective on reinforcement learning. In International Conference on Machine Learning (pp. 449-458). PMLR.
Bellemare, M., Srinivasan, S., Ostrovski, G., Schaul, T., Saxton, D., & Munos, R. (2016). Unifying count-based exploration and intrinsic motivation. Advances in neural information processing systems, 29, 1471-1479.
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Hassabis, D., et. al. (2015). Human-level control through deep reinforcement learning. nature, 518(7540), 529-533.
Bellemare, M. G., Naddaf, Y., Veness, J., & Bowling, M. (2013). The arcade learning environment: An evaluation platform for general agents. Journal of Artificial Intelligence Research, 47, 253-279.
Support Us
CIFAR is a registered charitable organization supported by the governments of Canada, Alberta and Quebec, as well as foundations, individuals, corporations and Canadian and international partner organizations.