Adam White
Appointment
Canada CIFAR AI Chair
Pan-Canadian AI Strategy
About
Adam is a Canada CIFAR AI Chair at Amii, an assistant professor in the University of Alberta’s Department of Computing Science and a Senior Research Scientist at DeepMind in Edmonton, Canada. At the University of Alberta, he is also a Principal Investigator in the Reinforcement Learning & Artificial Intelligence (RLAI) Lab.
White’s research program focuses on replicating or simulating human-level intelligence in physical and simulated reinforcement learning agents interacting with unknown environments. He seeks to understand knowledge representation and intrinsic motivation.
He is the founder of a language-independent communication protocol and evaluation framework for reinforcement learning experiments, RL-Glue. He is the co-author of the Horde architecture, a scalable real-time architecture for learning knowledge from unsupervised sensorimotor interaction.
Awards
- 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
Linke, C., Ady, N. M., White, M., Degris, T., & White, A. (2020). Adapting behaviour via intrinsic reward: A survey and empirical study. Journal of Artificial Intelligence Research.
Schlegel, M., Jacobsen, A., Zaheer, M., Patterson, A., White, A., & White, M. (2020). General value function networks. Journal of Artificial Intelligence Research.
Ghiassian S., Patterson A., Garg S., Gupta D., White A., White M.(2020). Gradient Temporal-Difference Learning with Regularized Corrections. International Conference on Machine Learning (ICML).
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.
Modayil, J., White, A., Pilarski, P. M., Sutton, R. S. (2012). Acquiring Diverse Predictive Knowledge in Real Time by Temporal-difference Learning. International Workshop on Evolutionary and Reinforcement Learning for Autonomous Robot Systems, Montpellier, France.
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.