Jesse Farebrother

I am currently a graduate student at Mila / McGill University supervised by Marc G. Bellemare. I also share my time as a student researcher at Google Brain Montréal. Previously, I completed my undergraduate degree in Computer Science at the University of Alberta and the Alberta Machine Intelligence Institute (Amii) working with Marlos C. Machado and Michael Bowling. I’m also the current maintainer and lead developer of the Arcade Learning Environment a popular benchmark for Reinforcement Learning (RL) agents.

My research interests lie broadly at the intersection of Reinforcement Learning (RL) and Deep Learning. More specifically, understanding representation learning in RL when using neural networks as function approximators.