Focused on developing methods that allow robots to provide high-confidence bounds on performance when learning a policy from a limited number of demonstrations, ask risk-aware queries to better resolve ambiguities and perform robust policy optimization from demonstrations, learn more efficiently from informative demonstrations, learn from ranked suboptimal demonstrations even when rankings are unavailable, and perform fast Bayesian reward inference for visual control tasks.
Research Experience
Was a postdoc at UC Berkeley working with Anca Dragan and Ken Goldberg on human-in-the-loop robot learning.
Education
Received his PhD in 2020 from the CS department at UT Austin, advised by Scott Niekum.
Background
Research Interests: Robot learning, reward inference under uncertainty, AI safety. Bio: Assistant Professor in the Robotics Center and School of Computing at the University of Utah, previously a postdoc at UC Berkeley.