Cathy Wu

Cathy Wu is interested in developing algorithms which increase the capacity for society to make good decisions, and she focuses on this in the context of urban systems. She studies several important building blocks, including: sample-efficient and scalable reinforcement learning, off-policy learning, scalable simulation, and bridging machine learning and control theory. Her ultimate goal is to leverage machine learning and control theory to build decision support systems (DSSs) which enable stakeholders, in a complex and uncertain societal context, to jointly make better decisions. She draws inspiration from the vast uncertainties in the myriad of decision contexts in vehicle automation, transportation systems, urban planning, economics, and public policy. She is the Gilbert W. Winslow (1937) Career Development Assistant Professor at MIT, where she is part of the Laboratory for Information & Decision Systems (LIDS), the Department of Civil and Environmental Engineering (CEE), and the Institute for Data, Systems, & Society (IDSS). She recently completed a postdoc with the Microsoft Research AI Reinforcement Learning group. She completed her PhD in EECS at UC Berkeley, working at the intersection of machine learning, optimization, and mobility. Her PhD research focused on mixed autonomy systems in mobility, which studies the complex integration of automation such as self-driving cars into existing urban systems. She was advised by Alexandre Bayen, and was part of the Berkeley AI Research Lab (BAIR), California Partners for Advanced Transportation Technology (PATH), the Berkeley Real-time Intelligent Secure Explainable Systems Lab (RISELab), and Berkeley DeepDrive (BDD). Before graduate school, she received a BS and MEng in EECS from MIT, where she worked with Daniela Rus, Seth Teller, and Jim Glass. She has also spent time at OpenAI, Microsoft Research, the Google X Self-Driving Car Team (now Waymo), Dropbox, Facebook, and several startups.