Zongzhang ZhangPh.D., Associate ProfessorLAMDA Group School of Artificial Intelligence National Key Laboratory for Novel Software Technology Nanjing University, P. R. China Office: Room A503, Yi Fu Building, Xianlin Campus Email: zzzhang@nju.edu.cn, zhangzongzhang@gmail.com |
|
I am now an associate professor at the School of Artificial Intelligence, Nanjing University. I am also a member of the LAMDA group, led by Prof. Zhi-Hua Zhou. From July 2014 to June 2019, I worked as an associate professor at the School of Computer Science and Technology, Soochow University. I received my Ph.D. degree from the School of Computer Science and Technology, University of Science and Technology of China, advised by Prof. Xiaoping Chen, in 2012. I worked with Prof. Mykel J. Kochenderfer as a visiting scholar at the Stanford Intelligent Systems Laboratory (SISL) from September 2018 to March 2019 and worked as a research fellow at the School of Computing, National University of Singapore, from November 2012 to June 2014, under Prof. David Hsu and Prof. Wee Sun Lee. Before that, I visited the Rutgers Laboratory for Real-Life Reinforcement Learning (RL3), directed by Prof. Michael L. Littman, as a research visiting student, from October 2010 to October 2011. I also briefly worked as a research engineer at the Noah's Ark Lab in the Huawei Company in 2012.
Debiased Offline Representation Learning for Fast Online Adaptation in Non-stationary Dynamics [Paper] [Code]
Xinyu Zhang, Wenjie Qiu, Yi-Chen Li, Lei Yuan, Chengxing Jia, Zongzhang Zhang*, and Yang Yu
In: Proceedings of the 41st International Conference on Machine Learning (ICML-2024), pages 59741-59758, Vienna, Austria, 2024.
Efficient and Stable Offline-to-online Reinforcement Learning via Continual Policy Revitalization [Paper] [Appendix] [Code]
Rui Kong, Chenyang Wu, Chen-Xiao Gao, Zongzhang Zhang*, and Ming Li
In: Proceedings of the 33rd International Joint Conference on Artificial Intelligence (IJCAI-2024), pages 4317-4325, Jeju Island, South Korea, 2024.
Focus-Then-Decide: Segmentation-Assisted Reinforcement Learning [Paper] [Appendix] [Code] [Project Page]
Chao Chen, Jiacheng Xu, Weijian Liao, Hao Ding, Zongzhang Zhang*, Yang Yu, and Rui Zhao
In: Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI-2024), pages 11240–11248, Vancouver, Canada, 2024.
ACT: Empowering Decision Transformer with Dynamic Programming via Advantage Conditioning [Paper] [Appendix] [Code]
Chen-Xiao Gao, Chenyang Wu, Mingjun Cao, Rui Kong, Zongzhang Zhang*, and Yang Yu
In: Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI-2024), pages 12127–12135, Vancouver, Canada, 2024.
Generalizable Task Representation Learning for Offline Meta-Reinforcement Learning with Data Limitations [Paper] [Appendix] [Code]
Renzhe Zhou, Chen-Xiao Gao, Zongzhang Zhang*, and Yang Yu
In: Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI-2024), pages 17132-17140, Vancouver, Canada, 2024.
Deep Anomaly Detection via Active Anomaly Search [Paper] [Appendix] [Code]
Chao Chen, Dawei Wang, Feng Mao, Jiacheng Xu, Zongzhang Zhang*, and Yang Yu
In: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems (AAMAS-2024), pages 308–316, Auckland, New Zealand, 2024.
Surfing Information: The Challenge of Intelligent Decision-Making [Paper]
Chenyang Wu and Zongzhang Zhang*
Intelligent Computing, 2023, 2: Article 0041.
Policy Regularization with Dataset Constraint for Offline Reinforcement Learning [Paper] [Code]
Yuhang Ran, Yi-Chen Li, Fuxiang Zhang, Zongzhang Zhang*, and Yang Yu
In: Proceedings of the 40th International Conference on Machine Learning (ICML-2023), pages 28701-28717, Honolulu, Hawaii, USA, 2023.
Discovering Generalizable Multi-agent Coordination Skills from Multi-task Offline Data [Paper] [Code]
Fuxiang Zhang, Chengxing Jia, Yi-Chen Li, Lei Yuan, Yang Yu, and Zongzhang Zhang*
In: Proceedings of the 11th International Conference on Learning Representations (ICLR-2023), Kigali, Rwanda, 2023.
Internal Logical Induction for Pixel-Symbolic Reinforcement Learning [Paper] [Code]
Jiacheng Xu, Chao Chen, Fuxiang Zhang, Lei Yuan, Zongzhang Zhang*, and Yang Yu
In: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD-2023), pages 2825–2837, Long Beach, CA, USA, 2023.
Policy-Independent Behavioral Metric-Based Representation for Deep Reinforcement Learning [Paper] [Appendix]
Weijian Liao, Zongzhang Zhang*, and Yang Yu
In: Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI-2023), pages 8746-8754, Washington, DC, USA, 2023.
Bayesian Optimistic Optimization: Optimistic Exploration for Model-based Reinforcement Learning [Paper] [Appendix]
Chenyang Wu, Tianci Li, Zongzhang Zhang*, and Yang Yu
In: Advances in Neural Information Processing Systems 35 (NeurIPS-2022), pages 14210-14223, New Orleans, USA, 2022.
Efficient Multi-Agent Communication via Shapley Message Value [Paper] [Code] [Demo]
Di Xue, Lei Yuan, Zongzhang Zhang*, and Yang Yu
In: Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI-2022), pages 578-584, Vienna, Austria, 2022.
Multi-Agent Incentive Communication via Decentralized Teammate Modeling [Paper] [Code] [Demo]
Lei Yuan, Jianhao Wang, Fuxiang Zhang, Chenghe Wang, Zongzhang Zhang*, Yang Yu, and Chongjie Zhang*
In: Proceedings of the 36th AAAI Conference on Artificial Intelligence (AAAI-2022), pages 9466-9474, Virtual Conference, 2022.
Adaptive Online Packing-guided Search for POMDPs [Paper] [Appendix] [Code]
Chenyang Wu, Guoyu Yang, Zongzhang Zhang*, Yang Yu, Dong Li, Wulong Liu, and Jianye Hao
In: Advances in Neural Information Processing Systems 34 (NeurIPS-2021), pages 28419-28430, Virtual Conference, 2021.
Cross-Modal Domain Adaptation for Cost-Efficient Visual Reinforcement Learning [Paper] [Appendix] [Code]
Xiong-Hui Chen, Shengyi Jiang, Feng Xu, Zongzhang Zhang*, and Yang Yu
In: Advances in Neural Information Processing Systems 34 (NeurIPS-2021), pages 12520-12532, Virtual Conference, 2021.
[Full List of Publications] [DBLP] [Google Scholar] [Code Repositories]
Ph.D. Students:
Master Students:
[More Information on Current Students and Alumni]
To prospective students:
I am in a LAMDA's reinforcement learning team (LAMDA RL Lab) with Prof. Yang Yu.
I am looking for self-driven, diligent, adaptable, and resourceful students to work on exciting research in machine learning, including topics of reinforcement learning, multi-agent systems, probabilistic planning, imitation learning, etc. If you are passionate about research, you are welcome to contact me.