I am a tenured Associate Professor in the School of Computer Science at Peking University (PKU).
I also lead the Multimodal Interaction Research Center at Beijing Academy of Artificial Intelligence (BAAI).
My current research focuses on
with the aim of endowing agents with the ability to autonomously acquire skills to accomplish tasks, cooperate, and communicate in the open world, towards artificial general intelligence.
Short Bio
I joined Peking University as an Assistant Professor at the School of Computer Science in Fall 2017 and have been a tenured Associate Professor since January 2024. Before that, I was a postdoc in the Department of Computer Science and Engineering, Pennsylvania State University. I received the PhD degree from the School of Computer Science and Engineering, Nanyang Technological University in 2014, master and bachelor degrees from Southeast University.
I am looking for self-motivated undergraduate students for research internships. I am recruiting PhD students (Fall 2026), RAs and postdocs at PKU, and interns at BAAI. If you are interested, drop me an email.
Six papers on reinforcement learning were accepted at NeurIPS’24. Congratulations to all.
Four papers on multimodal models, learning from videos, and generalization in RL were accepted at ECCV’24.
Recently developed foundation models, such as large language models and multi-modal models, open great opportunities to build generally capable agents, combined with reinforcement learning. This project focuses on learning skills and foundation models and connecting them to build generalist agents. In the following, we introduce some of our studies. For more details, please refer to the papers. Plan4MC We study building a multi-task agent in Minecraft. Without human demonstrations, solving long-horizon tasks in this open-ended environment with reinforcement learning (RL) is extremely sample inefficient. [Read More…]
Multi-Agent Reinforcement Learning (MARL) has recently attracted much attention from the communities of machine learning, artificial intelligence, and multi-agent systems. As an interdisciplinary research field, there are so many unsolved problems, from cooperation to competition, from agent communication to agent modeling, from centralized learning to decentralized learning. MARL has been the main research focus of our lab. We are investigating the field from many perspectives. In the following, we introduce some of our studies. [Read More…]
Area Chair, ICLR 2024 2025, ICML 2024, NeurIPS 2024, AAMAS 2025
Associate Editor, ACM Journal on Autonomous Transportation Systems, 2022 -
Guest Editor, Machine Learning Special Issue on RL for Real Life, 2023
NeurIPS 2024 Large-Scale Auction Challenge, Co-Organizer
IEEE Conference on Games 2022, Keynote Co-Chair
ICML 2021 Workshop on Reinforcement Learning for Real Life, General Co-Chair
INFOCOM 2020 Worksop on Network Intelligence, General Co-Chair
ACM TURC 2018, Award Co-Chair