I am a Scientist at DeepMind in London. Previously, I was a PhD student at MIT working with Josh Tenenbaum. My long term mission is to build an artificial human mind. My current research goal is to build robots that learn rich mental models of the world for acting and reasoning in them. I take a systems integration approach by combining -- Deep Learning, Probabilistic Programming, Reinforcement Learning, insights from our brains and minds.

My work has led to the development of Deep Inverse Graphics (Picture,DCIGN) , Probabilistic Programming and Inference (Picture, Variational Particle Approximations, Venture), Deep Hierarchical Reinforcement Learning (Hierarchical DQN, Deep Successor RL) and Deep Reinforcement Learning for language understanding.


Talks and Workshops