I am a PhD student at McGill University and Mila in Montreal, Canada. I am fortunately supervised by Marc G. Bellemare and David Meger.

My research interests are primarily concerned with reinforcement learning, and particularly with methods of modeling uncertainty to improve safety and exploration. I am a distributional reinforcement learning enthusiast.

During my Master's, I derived a characterization of the distribution of returns induced by agents whose dynamics are driven by continuous-time Markov processes, which we used to analyze continuous time distributional RL algorithms. My thesis can be seen here.