About Me

I am a PhD student at the University of Alberta supervised by Prof. Dale Schuurmans, where I mainly focus on in-context learning and reinforcement learning. My goal is to understand how to efficiently train and deploy scalable agents that can act under non-stationary environments.

Before this, I was a researcher at Kindred AI (acquired by Ocado Technology) developing reinforcement-learning and imitation-learning methods for robotic manipulation. I completed my MSc in Applied Computing and HBSc in Computer Science at the University of Toronto.

Updates

May. 9, 2025: Our paper on estimating stationary distribution for off-policy evaluation has been accepted to RLC 2025!