Published a preprint paper titled 'Challenges to Solving Combinatorially Hard Long-Horizon Deep RL Tasks.'
Research Experience
Conducts research in the knowledge representation group at the University of Toronto and is a member of the Canadian Artificial Intelligence Association and the Vector Institute. His PhD thesis is titled 'Reward Machines,' which addresses sample efficiency and partial observability in reinforcement learning.
Education
PhD student at the University of Toronto, supervised by Sheila McIlraith; undergraduate and master's degrees from Pontificia Universidad Católica de Chile, co-supervised by Alvaro Soto and Jorge Baier during his master's.
Background
Research direction is in artificial intelligence, focusing on the core aspects of knowledge, reasoning, and learning to build general-purpose agents with theoretical guarantees and state-of-the-art performance.
Miscellany
Taught the undergraduate course 'Introduction to Computer Programming' at Pontificia Universidad Católica de Chile.