Dr. Haoran Wang is a postdoctoral research scientist in the Department of Industrial Engineering and Operations Research and the FDT Center for Intelligent Asset Management at Columbia University. His research interest lies at the interface of reinforcement learning (RL), mathematical finance, and stochastic control and optimization. Previously, together with his collaborators, he has developed a novel theoretical framework for exploratory (relaxed) stochastic control in continuous-time RL setting. In a more recent work, Dr. Wang and Prof. Xunyu Zhou presented an interpretable and efficient RL algorithm for solving the continuos-time mean-variance portfolio allocation problem under the exploratory control framework, with performance exceeding that of the classical econometric method and the deep RL method. He is currently working on scalable RL algorithms for risk-sensitive asset management.
Dr. Wang obtained PhD degree in mathematics from The University of Texas at Austin in 2018, advised by Prof. Thaleia Zariphopoulou. His PhD research focused on forward performance processes and real-time model adaptation with applications ranging from portfolio management, option valuation in incomplete market to optimal execution. He is the holder of the Distinguished Bachelor’s Thesis Award, the IPAM Long Program Award and the SIAM Early Career Travel Award.