Lei Yuan @ LAMDA, NJU-AI

袁雷 Lei Yuan Assistant researcher, LAMDA Group School of Artificial Intelligence National Key Laboratory for Novel Software Technology Nanjing University, Nanjing 210023, China Email: yuanl {AT} lamda.nju.edu.cn OR yuanleiml {AT} gmail.com Laboratory: Shaoyifu Building, Xianlin Campus of Nanjing University Google Scholar

Biography

Currently I am an assistant researcher in School of Artificial Intelligence at Nanjing University, and I am also a member of LAMDA Group.

I obtained my Ph.D. degree from Department of Computer Science and Technology in Nanjing University in December 2023, where I was very fortunate to be advised by Prof. Yang Yu. I obtained my M.Sc. degree of Software Engineering from CAE in June 2019, and received my B.Sc. degree in Department Of Electronic Engineering in June 2016 from Tsinghua University

Research Interests

Currently my research interest is Reinforcement Learning. Especially in

• Reinforcement Learning

• Multi-agent Reinforcement Learning

• Open-environment RL and MARL

• Cooperation and Coordination

• Human-AI Coordination

• Large Languag Model and It's Application

• Large Decision Model for Coordination

Publication

Survey:

• Lei Yuan, Ziqian zhang, Lihe Li, Cong Guan, and Yang Yu. A Survey of Progress on Cooperative Multi-agent Reinforcement Learning in Open Environment (In English) (中文版本)

Conference Papers:

2024

• Ruiqi Xue, Ziqian Zhang, Lihe Li, Feng Chen,Yi-Chen Li,Yang Yu, and Lei Yuan. Dynamics Adaptive Safe Reinforcement Learning with a Misspecified Simulator. European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD-2024). 2024.

• Xinyu Zhang, Wenjie Qiu, Yi-Chen Li, Lei Yuan, Chengxing Jia, Zongzhang Zhang, and Yang Yu, Debiased Offline Representation Learning for Fast Online Adaptation in Non-stationary Dynamics. International Conference on Machine Learning (ICML-2024). 2024.

• Lihe Li, Ruotong Chen, Ziqian Zhang, Zhichao Wu, Yi-Chen Li, Cong Guan, Yang Yu, and Lei Yuan. Continual Multi-Objective Reinforcement Learning via Reward Model Rehearsal. Proceedings of the 33rd International Joint Conference on Artificial Intelligence (IJCAI-24) , 2024.

• Cong Guan, Feng Chen, Ke Xue, Chunpeng Fan, Lichao Zhang, Ziqian Zhang, Pengyao Zhao, Zongzhang Zhang, Chao Qian, Lei Yuan, Yang Yu. One by One, Continual Coordinating with Humans via Hyper-Teammate Identification. ICLR 2024 Workshop GenAI4DM , 2024.

• Feng Chen, Fuguang Han, Cong Guan, Lei Yuan, Zhilong Zhang, Yang Yu, Zongzhang Zhang. Stable Continual Reinforcement Learning via Diffusion-based Trajectory Replay. ICLR 2024 Workshop GenAI4DM, 2024.

• Cong Guan, Lichao Zhang, Chunpeng Fan, Yi-Chen Li, Feng Chen, Lihe Li, Yunjia Tian, Lei Yuan, and Yang Yu. Efficient Human-AI Coordination via Preparatory Language-based Convention. LLMAgents @ ICLR 2024, 2024. arXiv preprint arXiv:2311.00416.

• Chengxing Jia, Chenxiao Gao, Hao Yin, Fuxiang Zhang, Xiong-Hui Chen, Tian Xu, Lei Yuan, Zongzhang Zhang, Yang Yu, and Zhi-Hua Zhou. Policy Rehearsing: Training Generalizable Policies for Reinforcement Learning. The Twelfth International Conference on Learning Representations (ICLR2024), 2024. arXiv preprint arXiv:2311.00416.

• Cong Guan, Ruiqi Xue, Ziqian Zhang, Lihe Li, Yichen Li, Lei Yuan and Yang Yu. Cost-aware Offline Safe Meta Reinforcement Learning with Robust In-Distribution Online Task Adaptation. Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2024), 2024.

• Chengxing Jia, Fuxiang Zhang, Yi-Chen Li, Chenxiao Gao, Xu-Hui Liu, Lei Yuan, Zongzhang Zhang and Yang Yu. Disentangling Policy from Offline Task Representation Learning via Adversarial Data Augmentation. Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2024), 2024.

  2023

• Lei Yuan, Lihe Li, Ziqian Zhang, Feng Chen, Tianyi Zhang, Cong Guan, Yang Yu, Zhi-Hua Zhou. Learning to Coordinate with Anyone. Proceedings of the Distributed Artificial Intelligence (DAI 2023, Best Paper Award), 2023. arXiv:2309.12633.

• Jiacheng Xu, Chao Chen, Fuxiang Zhang, Lei Yuan, Zongzhang Zhang, Yang Yu. Internal Logical Induction for Pixel-Symbolic Reinforcement Learning. Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2023), 2023.

• Zi-Qian Zhang, Lei Yuan, Li-He Li, Ke Xue, Chengxing Jia, Cong Guan, Chao Qian, Yang Yu. Fast Teammate Adaptation in the Presence of Sudden Policy Change. Proceedings of the 39th Conference on Uncertainty in Artificial Intelligence (UAI 2023), 2023. arXiv:2305.05911.

• Fuxiang Zhang, Chengxing Jia, Yi-Chen Li, Lei Yuan, Yang Yu, Zongzhang Zhang. Discovering Generalizable Multi-agent Coordination Skills from Multi-task Offline Data. The Eleventh International Conference on Learning Representations (ICLR2023), 2023.

• Shaowei Zhang, Jiahan Cao, Lei Yuan, Yang Yu and De-Chuan Zhan. Self-Motivated Multi-Agent Exploration. Proceedings of the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2023), 2023. arXiv:2301.02083.

• Lei Yuan, Zi-Qian Zhang, Ke Xue, Hao Yin, Feng Chen, Cong Guan, Li-He Li, Chao Qian, Yang Yu. Robust multi-agent coordination via evolutionary generation of auxiliary adversarial attackers. Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI-23, Oral Presentation), 2023. arXiv:2305.05909.

  2022

• Ke Xue, Jiacheng Xu, Lei Yuan, Miqing Li, Chao Qian, Zongzhang Zhang, Yang Yu. Multi-agent Dynamic Algorithm Configuration. Advances in Neural Information Processing Systems 35 (NeurIPS'22, Spotlight), New Orleans, LA, 2022.

• Cong Guan, Feng Chen, Lei Yuan, Chenghe Wang, Hao Yin, Zongzhang Zhang, Yang Yu. Efficient Multi-agent Communication via Self-supervised Information Aggregation. Advances in Neural Information Processing Systems 35 (NeurIPS'22), New Orleans, LA, 2022.

• Lei Yuan, Jianhao Wang, Fuxiang Zhang*, Chenghe Wang, Zongzhang Zhang, Yang Yu, and Chongjie Zhang. Multi-Agent Incentive Communication via Decentralized Teammate Modeling. Proceedings of the 36th Conference on Artificial Intelligence (AAAI-2022), Vancouver, Canada, 2022.

• Lei Yuan, Chenghe Wang, Jianhao Wang, Fuxiang Zhang, Feng Chen, Cong Guan, Zongzhang Zhang, Yang Yu, and Chongjie Zhang. Multi-Agent Concentrative Coordination with Decentralized Task Representation. Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI-2022), Vienna, Austria, 2022

• Di Xue, Lei Yuan, Zongzhang Zhang, and Yang Yu. Efficient Multi-Agent Communication via Shapley Message Value. Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI-2022, Long Oral Presentation), Vienna, Austria, 2022

2021

• Weijie Shen, Lei Yuan, Junfu Huang, Songyi Gao, Yuyang Huang, and Yang Yu. Sequential and Dynamic constraint Contrastive Learning for Reinforcement Learning. IJCNN2021.

Journal Papers:

• Cong Guan, Feng Chen, Lei Yuan, Zongzhang Zhang, Yang Yu. Efficient Communication via Self-supervised Information Aggregation for Online and Offline Multi-agent Reinforcement Learning. arXiv preprint arXiv:2302.09605. IEEE Transactions on Neural Networks and Learning Systems (TNNLS). 2024.

• Lei Yuan, Lihe Li, Ziqian Zhang, Fuxiang Zhang, Cong Guan, Yang Yu. Multi-agent Continual Coordination via Progressive Task Contextualization. arXiv preprint arXiv:2305.13937. IEEE Transactions on Neural Networks and Learning Systems (TNNLS). 2024.

• Cong Guan, Ke Xue, Chunpeng Fan, Feng Chen, Lichao Zhang, Lei Yuan, Chao Qian , Yang Yu. Open and Real-World Human-AI Coordination by Heterogeneous Training with Communication. FCS (Frontiers of Computer Science). 2024.

• Lei Yuan, Tao Jiang, Lihe Li, Feng Chen, Zongzhang Zhang, Yang Yu. Robust Multi-agent Communication via Multi-view Message Certification. SCIS (Science China Information Sciences). arXiv preprint arXiv:2305.13936.

• Lei Yuan, Feng Chen, Zongzhang Zhang, Yang Yu. Communication-Robust Multi-Agent Learning by Adaptable Auxiliary Multi-Agent Adversary Generation. FCS (Frontiers of Computer Science). arXiv preprint arXiv:2305.05116.

• Jiahan Cao Lei Yuan, Jianhao Wang, Shaowei Zhang, Chongjie Zhang, Yang Yu, and De-Chuan Zhan. LINDA: Multi-Agent Local Information Decomposition for Awareness of Teammates. SCIS (Science China Information Sciences). arXiv preprint arXiv:2109.12508.

• Rongjun Qin, Feng Chen, Tonghan Wang, Lei Yuan, Xiaoran Wu, Yipeng Kang, Zongzhang Zhang, Chongjie Zhang, and Yang Yu. Multi-Agent Policy Transfer via Task Relationship Modeling. SCIS (Science China Information Sciences). arXiv:2203.04482.

• Hua Yang, Minghao Zhao, Lei Yuan, Yang Yu, Zhenhua Li, Ming Gu. Memory-Effcient Transformer-based Network Model for Traveling Salesman Problem. NN (Neural Networks, 2023).

Preprints:

• Ke Xue, Yutong Wang, Lei Yuan, Cong Guan, Chao Qian, Yang Yu. Heterogeneous Multi-agent Zero-Shot Coordination by Coevolution. arXiv preprint arXiv:2208.04957.

Teaching Assistant

• Multi-Agent Systems (with Associate Prof. Zongzhang Zhang; for undergraduate students, Spring 2021)

• Introduction to Machine Learning (with Prof. Zhi-Hua Zhou, Prof. De-Chuan Zhan, and Dr. Han-Jia Ye; For Undergraduate Students, Spring, 2020)

Academic Service

• Reviewer for Conferences ICML, ICLR, NeurIPS, AAAI, DAI, ECAI. Science China Information Sciences, Chinese Journal of Electronics, Machine Learning, IEEE Transactions on Emerging Topics in Computational Intelligence (TETCI).

Correspondence

Email: yuanl {AT} lamda.nju.edu.cn OR yuanleiml {AT}gmail.com

Laboratory: Shaoyifu Building, Xianlin Campus of Nanjing University

Address: National Key Laboratory for Novel Software Technology, Nanjing University, Xianlin Campus Mailbox 603, 163 Xianlin Avenue, Qixia District, Nanjing 210023, China
(南京市栖霞区仙林大道163号, 南京大学仙林校区603信箱, 软件新技术全国重点实验室, 210023.)