Thang D. Chu

I recently completed my M.Sc. in Computing Science at the University of Alberta (August 2026), advised by Prof. Csaba Szepesvári. My thesis was Lower Bound on Policy Gradient with Decreasing Stepsizes, with a focus on lower bounds for policy-gradient methods that use decreasing stepsizes.

My research interests are reinforcement learning theory, stochastic optimization, continual learning, and agentic systems. More broadly, I am interested in rigorously understanding when learning algorithms work, when they fail, and how their optimization dynamics shape their statistical performance.