An early interest in machines and mechanisms motivated me to pursue an undergraduate degree in Mechanical Engineering, where I was introduced to control and modeling of dynamic systems. The challenges and limitations of analytical mathematical modeling led me to explore data driven approaches. This exposed me to the world of machine learning and optimization. My interests eventually culminated into a passion for solving arguably the most difficult modeling problem - that of modeling natural intelligence. I currently develop approaches to tackle various aspects of this problem, such as the safe and scalable training of learning agents, incorportation of prior knowledge etc., and typically validate them through theoretical analyses or by deploying them on simulated and/or real-world learning agents. 


My academic network (as of Nov, 2021)


A word-cloud of my Google Scholar page (as of Nov, 2021, generated using https://www.wordclouds.com/ )


Research Interests

Reinforcement Learning

2006 - 2010

National Institute of Technology, Jalandhar, India

Bachelor of Technology, Mechanical Engineering

Optimization and Control

Supervised learning and Neural Networks


National University of Singapore 

Master of Science, Mechatronics

2014 - 2019

Singapore University of Technology and Design

PhD, Reinforcement Learning

Work Experience


Tata Motors Ltd., Pantnagar, India