About me

I’m a research scientist at Google DeepMind where I work on sequential decision making problems and reinforcement learning. Most recently I’ve been working on general RL for large language models, or RLHF more colloquially. However I’ve been known to work on meta-learning, Bayesian optimization, and a whole host of other problems. Check out my recent publications if you’re interested to know more!

Previously, I was a postdoc working with Carl Rasmussen and Zoubin Ghahramani in the machine learning group at the University of Cambridge. Before that I was a graduate student in the CS department at UBC, supervised by Nando de Freitas and Arnaud Doucet. My research there focused on using inference-based approaches to solve problems in sequential decision making.

I’ve also written software for reinforcement learning and Bayesian optimization that may be useful.

In the far distant past I was an undergraduate in the CS and Math departments at the University of Washington. While there I worked with Rajesh Rao as part of the Neural Systems Group, and I focused primarily on problems of gaze-imitation and imitation-learning utilizing shared-attention.