Associate Professor
Department of Computing Science
University of Alberta
Affiliations:
Canada CIFAR AI Chair
Alberta Machine Intelligence Institute (Amii)
PI of Vision & Robotics lab, RLAI lab
Email: armahmood@ualberta.ca
Google Scholar Profile
Streaming deep reinforcement learning: Slides Video
Continual robot learning: Video
My research objective is to understand scalable and general learning mechanisms for continually improving agents. To this end, I develop continual reinforcement and representation learning algorithms and real-time learning systems, sometimes for controlling physical robots.
NSERC proposal 2020 (one-page summary)
What's your scientific style? (from a talk by Allen Newell)
You and your research (Richard W. Hamming)