Doina Precup
Appointment
Fellow
Canada CIFAR AI Chair
Learning in Machines & Brains
Pan-Canadian AI Strategy
About
Appointed Canada CIFAR AI Chair – 2018
Renewed Canada CIFAR AI Chair – 2023
Doina Precup is a Canada CIFAR AI Chair and a Fellow of the CIFAR Learning in Machines & Brains program at CIFAR. She is also an Associate Professor of Computer Science at McGill University and the Research Team Lead at DeepMind.
Precup leads fundamental research on reinforcement learning, working in particular on AI applications in areas of social impact. Her research interests include Markov decision processes and applications of machine learning and AI. She’s interested in machine decision-making in situations where uncertainty is high.
She is one of the co-founders of the CIFAR-OSMO AI4Good Lab, a seven-week AI training program for undergraduate and graduate students who identify as women.
Awards
- Creative Destruction Lab Ideas Award, 2017
- Outstanding Student Paper Award (2 awards to her students in 2017)
- Google Focused Research Award, 2017
- AAAI Senior Member, 2015
Relevant Publications
Silver, D., Singh, S., Precup, D., & Sutton, R. S. (2021). Reward is enough. Artificial Intelligence, 103535.
Anand, N., & Precup, D. (2021). Preferential Temporal Difference Learning.
Sutton, R. S., Precup, D., & Singh, S. (1999). Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning. Artificial intelligence, 112(1-2), 181-211.
Menze, B. H., Jakab, A., Bauer, S., Kalpathy-Cramer, J., Farahani, K., Kirby, J., Precup, D., Van Leemput, K. (2014). « The multimodal brain tumor image segmentation benchmark (BRATS) », IEEE Transactions on Medical Imaging, 34(10):1993-2024.
Bacon, P. L., Harb, J., & Precup, D. (2017, February). The option-critic architecture. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 31, No. 1).