Dr. Xianyuan Zhan is a research assistant professor at the Institute for AI Industry Research (AIR), Tsinghua University. He received a dual Master’s degree in Computer Science and Transportation Engineering, and a PhD degree in Transportation Engineering from Purdue University. Before joining AIR, Dr. Zhan was a data scientist at JD Technology and also a researcher at Microsoft Research Asia (MSRA). Dr. Zhan previously led the research and development of AI-driven industrial system optimization products at JD Technology. He has published more than 30 papers in key journals and conferences in the field of Transportation Engineering and Computer Science. He is also a reviewer for many top transportation and computer science journals and conferences. He is currently a committee member of China Computer Federation-Artificial Intelligence & Pattern Recognition (CCF-AI) Committee.
- Offline deep reinforcement learning
- Complex system optimization
- Urban computing
- Big data analytics in transportation
- Complex networks
Recent News and Activities
- Aug. 2021: Interview at “ TalkRL: The Reinforcement Learning Podcast” with Robin Chauhan is now available online. Covering our work of DeepThermal. Apple podcast link is also available here.
- Jul. 2021: Our two papers: “DeepThermal: Combustion Optimization for Thermal Power Generating Units Using Offline Reinforcement Learning” and “Constraints Penalized Q-Learning for Safe Offline Reinforcement Learning” have been accepted in Reinforcement Learning for Real Life Workshop @ ICML 2021. Both papers are selected for the Spotlight Session.
- Jul. 2021: Our latest paper: “CSCAD: Correlation Structure-based Collective Anomaly Detection in Complex System” has been accepted in KDD’21 Workshop on Outlier Detection and Description (OOD).
- May. 2021: Our latest paper: “Network-Wide Traffic States Imputation Using Self-interested Coalitional Learning” has been accepted in KDD 2021.
- Feb. 2021: Our latest paper on optimizing thermal power generating units using offline RL is now on arXiv.
- Jan. 2021: Media coverage of our work on optimizing thermal power plant using AI by South China Morning Post: “JD builds AI control system that can save China’s thermal power plants billions and reduce pollution”.
- Dec. 2020: Our new paper “Robust Spatio-Temporal Purchase Prediction via Deep Meta Learning” has been accepted in AAAI 2021.