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. My research explores the computational foundations of adaptive behaviour at the intersection of reinforcement learning, continual learning, and meta-learning. Previously, 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.

I am seeking to understand the problems faced by an agent that uses its experience to efficiently and continually adapt its behaviour. A central problem that I have studied is loss of plasticity in neural networks, a phenomenon in which performance degrades over the course of continual gradient-based optimization. More recently, I have been interested in a big world problem setting, where (1) it is suboptimal to stop learning, and (2) this need for continual learning cannot be outscaled. With this perspective, I am developing 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

© Alex Lewandowski. Last modified: February 15, 2026. Website built with Franklin.jl and the Julia programming language.