Rupam Mahmood
Appointment
Canada CIFAR AI Chair
Pan-Canadian AI Strategy
About
Appointed Canada CIFAR AI Chair – 2020
Renewed Canada CIFAR AI Chair – 2025
Rupam Mahmood is an Assistant Professor in the Department of Computing Science at the University of Alberta, a Canada CIFAR AI Chair, and a Fellow at the Alberta Machine Intelligence Institute (Amii). He is the Director of the Reinforcement and Artificial Intelligence Lab. He is also the scientific advisor for Kindred Inc. and a faculty member of NextAI.
His work intersects reinforcement learning, continual learning, and robot learning. Mahmood focuses on developing deep representation learning algorithms to address issues of continual learning, such as scalability, catastrophic forgetting, and loss of plasticity, with the ultimate goal of building autonomous continual learning systems such as freely-living robots. Before joining UAlberta, Mahmood led the AI Research team at the robotics company Kindred AI, where he developed SenseAct, the first open-source toolkit and benchmark task suite for reproducible real-time learning with various physical robots.
Awards
- Notable Area Chair Award, ICLR, 2023
- Top Reviewer Award, NeurIPS, 2023
- Top Reviewer Award, NeurIPS, 2022
Relevant Publications
- Elsayed, M., & Mahmood, A. R. (2024). Addressing loss of plasticity and catastrophic forgetting in continual learning. In Proceedings of the 12th International Conference on Learning Representations (ICLR).
- Che, F., Xiao, C., Mei, J., Dai, B., Gummadi, R., Ramirez, O. A., Har- ris, C. K., Mahmood, A. R., Schuurmans, D. (2024). Target networks and over-parameterization stabilize off-policy bootstrapping with function approximation. In Proceedings of the 41st International Conference on Machine Learning (ICML spotlight).
- Wang, Y., Vasan, G., & Mahmood, A. R. (2023). Real-time reinforcement learning for vision-based robotics utilizing local and remote computers. In Proceedings of the 2023 International Conference on Robotics and Automation (ICRA).
- Chan, A., Silva, H., Lim, S., Kozuno, T., Mahmood, A. R., & White, M. (2022). Greedification operators for policy optimization: Investigating forward and reverse kl divergences. In the Journal of Machine Learning Research (JMLR).
Mahmood, A. R., Komer, B. J., & Korenkevych, D. (2020). U.S. Patent Application No. 16/560,761.
Mahmood, A. R., Korenkevych, D., Vasan, G., Ma, W., Bergstra, J. (2018). Benchmarking reinforcement learning algorithms on real-world robots. In Proceedings of the 2nd Annual Conference on Robot Learning (CoRL).