I recently completed my Bachelor's degree in Computer Science at IIT Bombay. I joined the residency program just after finishing my degree to explore various research areas in deep learning. My bachelor's thesis involved building a learning-based Scrabble agent using Evolutionary Strategies and Imitation Learning under the supervision of Prof. Shivaram Kalyanakrishnan. Prior to the residency, I worked at an AI startup on learning realistic driving behaviours using Reinforcement Learning (RL). As an AI Resident, having access to large amounts of compute and collaborating with brilliant researchers have immensely facilitated my research.
My long-term goal is to create robust artificial agents that can meaningfully interact with their environments and I am mainly interested in the field of Deep RL. Applying tabula rasa RL on complex real-world problems is extremely challenging and sample inefficient. One research direction I find interesting is to develop better techniques for incorporating prior information into RL algorithms, which could be in the form of imperfect demonstrations, differentiable physics, priors acquired via meta-learning etc. Another obstacle to applying RL algorithms to real-world tasks is the lack of suitable reward functions. I am also fascinated by the research direction of improving off-policy RL. In general, I believe that deep RL can be improved by inheriting ideas from supervised learning.