Skip to content
Dale Schuurmans-BW_F

Dale Schuurmans


  • Canada CIFAR AI Chair
  • Pan-Canadian AI Strategy


Google Scholar


Dale Shuurman’s research originates and remains rooted in the pursuit of artificial intelligence. His research focuses primarily on the algorithmic foundations of machine learning, motivated by the fact that improving capability autonomously and adapting to novel circumstances are hallmark characteristics of intelligence. Machine learning provides a means to achieving targeted capabilities in sensory interpretation, language interpretation, efficient reasoning, and behavior.

He is currently focusing on developing algorithms that acquire competence through the integration of demonstration-based and experienced-based learning. This recent work has been based on recent advances in:

  1. unifying value and policy-based reinforcement learning;
  2. relating forward and inverse reinforcement learning;
  3. extending on-policy and off-policy reinforcement learning;
  4. exploiting equilibrium concepts from game theory.


  • NeurIPS Best Paper Award, 2018
  • Fellow, Association for the Advancement of Artificial Intelligence (AAAI), 2017
  • Canada Research Chair in Machine Learning, 2008--2018
  • IJCAI Distinguished Paper Award, 2005
  • AAAI Outstanding Paper Award, 2000

Relevant Publications

  • Mei, J., Xiao, C., Dai, B., Li, L., Szepesvári, C., & Schuurmans, D. (2020). Escaping the Gravitational Pull of Softmax. Advances in Neural Information Processing Systems, 33.
  • Yang, M., Nachum, O., Dai, B., Li, L., & Schuurmans, D. (2020). Off-policy evaluation via the regularized lagrangian. arXiv preprint arXiv:2007.03438.
  • Wen, J., Dai, B., Li, L., & Schuurmans, D. (2020). Batch Stationary Distribution Estimation. arXiv preprint arXiv:2003.00722.
  • Chen, M., Gummadi, R., Harris, C., & Schuurmans, D. (2019). Surrogate objectives for batch policy optimization in one-step decision making. In Advances in Neural Information Processing Systems (pp. 8827-8837).
  • Lu, T., Schuurmans, D., & Boutilier, C. (2018). Non-delusional Q-learning and value-iteration. Advances in neural information processing systems, 31, 9949-9959.

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.

MaRS Centre, West Tower
661 University Ave., Suite 505
Toronto, ON M5G 1M1 Canada