I am a Research Scientist at Google DeepMind. I did my PhD at MIT while working with Josh Tenenbaum in the Brain and Cognitive Sciences department. I am interested in understanding our minds and brains to create AI. I believe this can be achieved by integrating deep (reinforcement) learning, probabilistic programming and rich simulators. My work has led to the development of - vision as inverse graphics, hierarchical and structured deep reinforcement learning, probabilistic programming and language understanding via interactive text games.

My current research spans three questions:

Highlights

Talks and Workshops