I am interested in cognitive flexibility and generalization, and how these abilities are enabled by factors like language, memory, and embodiment. I consider these issues from both the perspective of human cognition and artificial intelligence. My work often draws inspiration from cognitive science to build better AI; for example improving RL agent memory using the idea of mental time-travel, using task relationships to adapt to novel tasks on the first try, and learning from explanations. I am also interested in broader issues such as how we should think about symbols in AI and how publishing fast and slow could improve the generalizability of research.
I am a Senior Research Scientist at DeepMind. I completed my PhD in Cognitive Psychology at Stanford University. Prior to that, my background is in mathematics, physics, and machine learning. In my spare time, I enjoy climbing.