Jalaj Bhandari is a PhD student in operations research at Columbia University, working with Garud Iyengar and Daniel Russo. His thesis work explores the foundations of commonly used reinforcement learning algorithms, like TD learning and policy gradient methods, from an optimization perspective. He has also done research work in approximate Bayesian inference, specifically in designing efficient Markov Chain Monte Carlo (MCMC) methods for posterior sampling. He is interested in pushing the frontiers of reinforcement learning (and more broadly machine learning) theory to design sample efficient and robust algorithms, motivated by applications to real world problems.