CAREER: Principled Deep Reinforcement Learning for Societal Systems

The goal of this project is to develop a new generation of data-driven decision-making algorithms, theory, and software to address pressing challenges in societal systems. (i) Specifically, it aims to break various barriers that prohibit principled applications of deep reinforcement learning (RL) in critical domains, e.g., healthcare, transportation, power grid, financial network, and supply chain. (ii) Also, it aims to initiate a new subfield, namely societal deep RL, by connecting deep RL with multiple fields, e.g., nonconvex optimization, nonparametric statistics, causal inference, stochastic game, and social science. (iii) Meanwhile, it aims to train future leaders of academia, industry, and government by equipping them with fundamental skills in data science and artificial intelligence, which are needed to make accountable decisions with positive and progressive social impacts.