Hi, I'm Pranav.

I’m a soon-to-graduate PhD student and a Neuro-AI researcher at the University of Oxford, looking for postdoctoral research opportunities. My background is in engineering. I study minds as computational systems—entities that adapt and act purposefully in uncertain, non-stationary, open-ended environments. 

I’m interested in a broad range of problems such as continual lifelong learning, hierarchical planning and reasoning, long-range credit assignment, survival-critical computations, adaptive behaviour and homeostasis.  I'm curious about questions such as how the brain does so much with so little! And why do we sometimes cope well with adverse and stressful events, while sometimes we don't? 

I draw inspiration from AI research to (1) better understand cognition from a normative perspective and to (2) view mental health disorders and chronic pain as disruptions in continual learning, opening paths for new treatments.  On the flip side, by drawing on neuroscience, I aim to (3) advance fundamental AI research and (4) develop tools to mechanistically interpret and characterise behaviours and learning in complex AI systems. 

I did my PhD on safe learning in humans and machines, where I studied safe exploration using multi-objective RL and self-preservation/homeostasis using POMDPs. I’ve had the privilege of working with Peter Dayan, Boris Gutkin, Flavia Mancini, Sang Wan Lee, and my advisors Ben Seymour and Ioannis Havoutis. Previously, I briefly worked on scalable distributed deep learning at Nvidia.