Matthew (Matt) E. Taylor focuses his research on developing intelligent agents, physical or virtual entities that interact with their environments. His main goals are to enable individual agents, and teams of agents, to learn tasks in real-world environments that are not fully known when the agents are designed; to perform multiple tasks, rather than just a single task; and to robustly coordinate with, and reason about, other agents.
Additionally, he is interested in exploring how agents can learn from humans, whether the human is explicitly teaching the agent, the agent is passively observing the human, or the agent is actively cooperating with the human on a task.
Current approaches that his teams are investigating include working on improving reinforcement learning through demonstrations, teaching reinforcement learning systems through action advice, and training agents with discrete human feedback.
Matt is an Associate Professor of Computing Science at the University of Alberta and a Fellow and Fellow-in-Residence at Amii. He is the Director of the Intelligent Robot Learning (IRL) Lab and a Principal Investigator at the Reinforcement Learning & Artificial Intelligence (RLAI) Lab, both at the University of Alberta.
Matt is also Adjunct Professor at Washington State University and was formerly the Principal Researcher at Borealis AI in Edmonton, the artificial intelligence research lab for the Royal Bank of Canada.
He has been a PI or co-PI on over $6M USD in competitively awarded research funding from federal, state, and industrial sources, including the National Science Foundation CAREER award. He has (co-)supervised seven graduated PhD students and six graduated MS students, as well as published over 100 peer-reviewed papers in conferences and journals.
He has delivered invited talks for the Association for the Advancement of Artificial Intelligence (AAAI) and at the International Joint Conference on Artificial Intelligence (IJCAI).