Étudiant Doctorat, McGill University
I am a PhD student supervised by Prof. Doina Precup at McGill University and Mila. I am particularly interested in scalable human-inspired approaches to intelligence.
Humans are able to learn new skills and adapt to changes in a sample efficiency way, can RL agents do the same? My recent research is currently centered on meta reinforcement learning, together with temporal abstractions and off-policy methods, as a way to answer this question.