About Me

I’m a reinforcement learning researcher. Currently, I am primarily working on Inverse Reinforcement Learning. In the long run, I want to focus on using principles from the human cognition and psychology to build better reinforcement learning agents.

I’m associated with Machine Teaching Group at the Max Planck Institute for Software Systems, Saarbrücken, Germany. I am being advised by Dr. Adish Singla.

Previosly, I had completed MS (Research) in Computational Science from IIT Madras, India. I was advised by Dr. Balaraman Ravindran and Dr. Radha Krishna Ganti. My MS thesis is titled ‘On Learning Smooth Policies in Imitation Learning’.