Adam White
Appointment
Canada CIFAR AI Chair
Pan-Canadian AI Strategy
About
Appointed Canada CIFAR AI Chair – 2020
Adam is a Canada CIFAR AI Chair and Director of Scientific Operations at Amii and an assistant professor in the University of Alberta’s Department of Computing Science. At the University of Alberta, he is also a Principal Investigator in the Reinforcement Learning & Artificial Intelligence (RLAI) Lab.
White’s research is focused on understanding the fundamental principles of learning in continual learning settings, both simulated worlds and real-world industrial-control applications. His group is deeply passionate about good empirical practices and new methodologies to help determine if our algorithms are ready for deployment in the real world.
He co-created the Reinforcement Learning Specialization, taken by over 85,000 students on Coursera. He developed general value functions and the Horde architecture, a scalable real-time architecture for learning knowledge from unsupervised sensorimotor interaction.
Awards
- Highlighted Area Chair, ICLR, 2022
- Paper of Distinction at the 2012 IEEE International Conference on Developmental Robotics and Epigenetic Robotics.
- Best Paper Award at the International Workshop on Evolutionary and Reinforcement Learning for Autonomous Robot Systems in 2013.
- Numerous top reviewer awards for the International Conferences (2015, 2017, 2018, 2019).
Relevant Publications
- Wang, H., Miahi, E., White, M., Machado, M. C., Abbas, Z., Kumaraswamy, R., Liu, V., & White, A. (2024). Investigating the Properties of Neural Network Representations in Reinforcement Learning. AI Journal.
- Sutton, R. S., Machado, M. C., Holland, G. Z., Timbers, D. S. F., Tanner, B., & White, A. (2023). Reward-respecting subtasks for model-based reinforcement learning. AI Journal
- Abbas, Z., Zhao, R. Modayil, J., White, A., & Machado MC. (2023). Loss of plasticity in continual deep reinforcement learning. Conference on Lifelong Learning Agents (pp. 620-636).
White, A., Modayil, J., & Sutton, R. S. (2012). Scaling life-long off-policy learning. In the IEEE International Conference on Development and Learning and Epigenetic Robotics, 1–6.
- Sutton, RS., Modayil J., Delp, M., Degris, T., Pilarski, PM., White, A., & Precup D. (2011). Horde: A scalable real-time architecture for learning knowledge from unsupervised sensorimotor interaction. In the 10th International Conference on Autonomous Agents and Multiagent Systems - Volume 2 (pp. 761-768).
- Tanner, B., & White, A. (2009). RL-Glue: Language-independent software for reinforcement-learning experiments. In the Journal of Machine Learning Research, Volume 10 (pp.2133-2136).