Alex Lewandowski

About

I am a PhD candidate in computing science at the University of Alberta, part of RLAI and Amii, and supervised by Dale Schuurmans and Marlos C. Machado. Before that, I completed an MSc in statistics at the University of Alberta (supervised by Ivor Cribben and Rohana Karunamuni), and a BMath at the University of Waterloo.

My research explores the computational foundations of adaptive behaviour at the intersection of reinforcement, continual, and meta-learning. I am seeking to understand the problems faced by an agent that uses its experience to efficiently and continually adapt its behaviour. For instance, how should we design learning algorithms that are effective for agents with different computational resources and capabilities, from small and simple agents to larger and more complex ones?

News