I am a PhD student at Columbia Business School in the Decision, Risk, and Operations division. I am advised by Jing Dong and Hongseok Namkoong.
My research is on scalable planning and policy optimization for operations research problems. I'm interested in developing
differentiable and sample-based models for these problems, which enable the application of sample-efficient
methods from reinforcement learning (RL), approximate dynamic programming (ADP), and optimal control.
In particular, I am interested in the applications in adaptive experimentation, policy learning, and
routing control in queuing systems and discrete-event systems.
I've also done research in mechanism design.