Bio
I have a joint postdoctoral appointment at the University of Michigan and Boston University. Previously, I was at the Technion, Israel Institute of Technology, where I was advised by Prof. Shie Mannor and a member of the Reinforcement Learning Research Lab. I received my PhD from the Indian Institute of Science (IISc), where I was advised by Prof. Anurag Kumar and was a member of the Network Architecture Lab (NetArch), and my Master's in Electrical Engineering from the Indian Institute of Technology (IIT) Madras.
My research interests lie broadly in Reinforcement Learning, Control Theory, and Communication Networks. My research has focused on (a) using stochastic control theory to analyze pricing policies in energy markets and optimize the performance of medium access control (MAC) protocols, and (b) sequential hypothesis testing and multi-armed bandits .
I'M CURRENTLY ON THE JOB MARKET! Please feel free to reach out regarding open positions.
News 📰
I am currently on the job market!
My tutorial on Hyperdimensional Computing has been published in Towards AI. [Link]
Our paper titled "Actor-Critic based Improper Reinforcement Learning," has been accepted to the International Joint Conference on Machine Learning (ICML22) 2022!
Our paper titled "Improved Pure Exploration in Linear Bandits with No-Regret Learning" has been accepted to the International Joint Conference on Artificial Intelligence (IJCAI-ECAI 22) 2022!
Our paper titled "Actor-Critic based Improper Reinforcement Learning," has been accepted to the fifth Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM 2022)!
My article explaining why Thompson Sampling is not good for pure exploration has been published in TDS. [Link]
Research Interests
Stochastic Control
Reinforcement Learning
Stochastic Games (Competitive Markov Decision Processes)
Deregulated Market Design
Communication Network Optimization