Skip to content
Matt Taylor-BW_F

Matt Taylor


  • Canada CIFAR AI Chair
  • Pan-Canadian AI Strategy




Reinforcement learning (RL) is a machine learning technique that has had many successes, but many of them are in video games, and there have been few real-world deployments. Matt Taylor’s primary research goal is to help bring RL out of the lab and into more real-world settings. To accomplish this long-term goal, he has two parallel research tracks. The first research track is to push fundamental research forward so that RL can learn faster, with higher initial performance, primarily by leveraging existing knowledge in other programs, agents, or humans. The second research track is to better adapt RL for real-world settings. This will demand additional fundamental research, but also more practical concerns, such as how explainability influences trust and how to de-risk RL projects for companies.


  • 2018 Early Career Spotlight talk at IJCAI-18
  • 2018 Awarded AAAI Senior Member status
  • 2015 WSU EECS Early Career Award

Relevant Publications

  • Da Silva, F. L., Hernandez-Leal, P., Kartal, B., & Taylor, M. E. (2020). Uncertainty-Aware Action Advising for Deep Reinforcement Learning Agents. In AAAI (pp. 5792-5799).
  • Gabriel, V., Du, Y., & Taylor, M. E. (2019). Pre-training with non-expert human demonstration for deep reinforcement learning. The Knowledge Engineering Review, 34.
  • Wang, Z., & Taylor, M. E. (2018). Interactive Reinforcement Learning with Dynamic Reuse of Prior Knowledge from Human and Agent's Demonstration. arXiv preprint arXiv:1805.04493.
  • Peng, B., MacGlashan, J., Loftin, R., Littman, M. L., Roberts, D. L., & Taylor, M. E. (2018). Curriculum design for machine learners in sequential decision tasks. IEEE Transactions on Emerging Topics in Computational Intelligence, 2(4), 268-277.
  • MacGlashan, J., Ho, M. K., Loftin, R., Peng, B., Roberts, D., Taylor, M. E., & Littman, M. L. (2017). Interactive learning from policy-dependent human feedback. arXiv preprint arXiv:1701.06049.

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