About Me
I am a Ph.D. candidate in the Reinforcement Learning and Artificial Intelligence lab, part of the Alberta Machine Intelligence Institute and the Department of Computing Science at the University of Alberta, advised by Rich Sutton and Martha White.
My research interests centre on Reinforcement Learning (RL) as a way to achieve superhuman algorithmic performance in a wide variety of domains. Recently, I have focused on off-policy learning with the goal of expanding the range of applications of RL, and policy gradient algorithms as a principled approach to improving algorithmic performance beyond human capabilities. That being said, I’m also interested in many other topics and research areas, including representation learning and optimization.
Recent News
- April 2022: I finally updated my website.
- March 2022: RLDM accepted our extended abstract that explains why many off-policy RL algorithms don’t actually do per-decision importance sampling and provides a simple way to reduce variance in off-policy temporal-difference algorithms.
- December 2021: I passed the candidacy exam!
- November 2021: I uploaded our recent paper on off-policy actor-critic algorithms to arXiv.