I am a 6th year PhD student at Brown University, working on Reinforcement Learning, advised by Professor George Konidaris.

Prior to this I obtained a masters degree from University of Massachusetts, Amherst and had the privilege of working with Professor Phil Thomas. I graduated with a Bachelors of Technology in computer science at IIT Bombay. My research is focused on designing a geometric lense to understand and improve Deep Reinforcement Learning (RL).

High dimensional data has a low dimensional structure to it. For example, a picture of a face might have 2¹⁶ pixels but we can describe a face with far fewer variables: size of the nose, color of the skin, shape of the eyes etc. This is the manifold hypothesis: high-dimensional data lies on (or close to) a low-dimensional manifold. Using this I answer three questions:

1. How do existing deep learning models utilise this low-dimensional structure?
2. How can we exploit this low-dimensional structure to train better models?
3. What is this structure for RL and how do we build agents that can utilise it?

I use theoretical tools from high-dimensional statistics, differential geometry, dynamical systems, and optimal control. I have provided one of the first succesful applications of the theory of infinite width neural networks for continuous RL. My approach is theory-in-practice. Meaning I work with theoretical tools that can help explain the popular practical algorithms in meaningful theoretical settings. I believe theory should move towards practice and practice should move towards theory in Deep RL for true progress. For details see list of my publications.