Biography
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 70 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.
- Group Website: https://air-dream.netlify.app/
- Group Code Repository: https://github.com/AIR-DI
Research Interests
- Offline deep reinforcement learning
- Offline imitation learning
- Foundation models for decision-making
- Complex system optimization
- Autonomous driving
We are hiring!!!
Our team is looking for student interns/postdocs at AIR! If you are interested in the research directions of offline reinforcement learning, offline imitation learning or decision-making in autonomous driving, please feel free to send me an e-mail at zhanxianyuan@air.tsinghua.edu.cn!
Recent News and Activities
- Apr. 2024: Our recent survey paper “A Comprehensive Survey of Cross-Domain Policy Transfer for Embodied Agents” has been accepted in IJCAI 2024.
- Jan. 2024: Our four recent papers “Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient Update”, “Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model”, “Query-Policy Misalignment in Preference-Based Reinforcement Learning”, and “OpenChat: Advancing Open-source Language Models with Mixed-Quality Data” have been accepted in ICLR 2024!
- Oct. 2023: We have released “Data-Driven Control Library (D2C)”, which provides an easy-to-use and comprehensive library for real-world data-driven control & decision-making problems! Project page available at https://github.com/AIR-DI/D2C.
- Sep. 2023: We have released “OpenChat: Advancing Open-source Language Models with Mixed-Quality Data”, which uses ideas from offline RL to fine-tune open-source large language models! Project page is available at https://github.com/imoneoi/openchat.
- Sep. 2023: Our two recent papers “Look Beneath the Surface: Exploiting Fundamental Symmetry for Sample-Efficient Offline RL” and “Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization” have been accepted in NeurIPS 2023!
- Jan. 2023: Our three recent papers “Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization”, “When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learning” and “Mind the Gap: Offline Policy Optimization for Imperfect Rewards” have been accepted in ICLR 2023!
- Jan. 2023: Our paper “Offline Multi-Agent Reinforcement Learning with Coupled Value Factorization” has been accepted in AAMAS 2023.
- Jan. 2023: Our paper “An Efficient Multi-Agent Optimization Approach for Coordinated Massive MIMO Beamforming” on 5G Massive MIMO optimization has been accepted in IEEE ICC 2023.