A. Rupam Mahmood

Rupam
Assistant 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

Open office hour

If you are seeking supervision, please fill out this form



Research

Publications

My research objective is to understand scalable and general learning mechanisms for continually improving agents. To this end, I develop reinforcement and representation learning algorithms and real-time learning systems for controlling physical robots. Currently, I am working on the following new research program.

Continual robot learning with onboard computers

A crucial aspect of intelligence is the ability to learn continually and adapt to changes while interacting with the environment. Although natural intelligence innately shows such ability, current approaches to artificial intelligence (AI) only exhibit partial ability. Current AI systems do not learn continually as they first learn from a large stored dataset by replaying samples repeatedly and then are deployed in the real world, where they interact and perform, typically without further learning. Continual learning entails simultaneously interacting and adapting to changes while retaining useful past knowledge. My research program aims to develop approaches, algorithms, and real-time systems that enable continual learning for real-world robots using only onboard computers.

While continual learning represents a forefront challenge in contemporary AI research, achieving it is vital for real-time systems such as robots. This endeavor is distinctly challenging, as it requires learning to occur using the resource-constrained onboard computers of robots. These computers cannot support large-scale computation or provide the memory necessary for storing large datasets, both of which are essential for current approaches. Continual robot learning with onboard computers calls for new learning algorithms and a richer understanding of real-time learning systems. This research program aims to understand the challenges of continual learning in current learning approaches and develop algorithms and real-time systems for physical robots to overcome them. Algorithms developed for this effort are scalable, general, and applicable beyond onboard learning, making them suitable for advancing general intelligence through large-scale computation.

Past and ongoing programs

NSERC proposal 2020 (one-page summary)



Advice for researchers

What's your scientific style? (from a talk by Allen Newell)

You and your research (Richard W. Hamming)



Strong Towns

Blog on free will