Hi! My name is Ashish.

I am a recent Ph.D. (CS) graduate from the University of Waterloo.

My Ph.D. research focused on developing methods for inverse reinforcement learning (IRL), particularly in the constrained MDP setting, i.e. learning a constraint instead of a reward. This involved designing inverse constraint learning (ICL) algorithms that learned different types of constraints from expert demonstrations. These algorithms were then applied to real world domains like robotics and highway driving.

Previously, as a Master’s student, I was a part of the Waterloo Intelligent Systems Engineering (WISE) lab. I was also a part of the behavior planning team for autonomoose, Waterloo’s self driving car project. My research focused on safe reinforcement learning and continual learning.

These days, I design agentic and AI architectures at Kodem Legal.