Xinjie Liu

Hello and welcome! I am a third-year Ph.D. student in the Department of Electrical and Computer Engineering, Cockrell School of Engineering at The University of Texas at Austin. I am very fortunate to be co-advised by Prof. Ufuk Topcu and Prof. David Fridovich-Keil. My research focuses on developing scalable algorithms and theory behind them for reliable, sample-efficient learning and decision-making in autonomous systems such as robots. I am particularly interested in realistic settings where convenient assumptions break down—for example, when high-fidelity training data are scarce, simulators mismatch reality, other agents’ intentions are only partially observable, or communication and sensing resources are constrained. The majority of my work draws on reinforcement learning, numerical optimization, game theory, and statistical estimation and inference.

I obtained a master’s degree (the highest cum laude distinction) in Robotics from the Department of Cognitive Robotics (CoR) at the Delft University of Technology, Netherlands, where I was very fortunate to be advised by Prof. Javier Alonso-Mora. My master’s thesis was on game-theoretic motion planning for multi-agent systems. Before that, I received my bachelor’s degree in Automotive Engineering from Tongji University, Shanghai. During my senior year, I studied as a visiting undergraduate student at the Graz Univerisity of Technology, Austria.