陈烽 Feng Chen M.Sc. Student, LAMDA Group School of Artificial Intelligence National Key Laboratory for Novel Software Technology Nanjing University, Nanjing 210023, China Supervisor: Associate Prof. Zongzhang Zhang Email: chenf@lamda.nju.edu.cn Laboratory: Shaoyifu Building, Nanjing University Xianlin Campus

Biography

Currently I am a M.Sc. student of School of Artificial Intelligence in Nanjing University and a member of LAMDA Group, led by professor Zhi-Hua Zhou.

I received my B.Sc. degree in Computer Science and Technology from School of Artificial Intelligence, Nanjing University in June 2022. In September 2022, I was admitted to pursue a M.Sc. degree in Nanjing University, under the supervision of Associate Professor Zongzhang Zhang.

Research Interests

My research interest includes Reinforcement Learning and Generative Models. Especially, I am interested in

• Multi-Agent Reinforcement Learning

  Multi-Agent Reinforcement Learning (MARL) has attracted widespread attention and applied in numerous domains, including sensor networks, autonomous vehicle teams, and traffic signal control. I am interested in cooperative MARL, in which different agents learn to coordinate to accomplish tasks. Specifically, I have done some exploration in multi-agent communication and robust multi-agent reinforcement learning.

• Generative Models for Decision Making

  Generative models, particularly the diffusion model, are AI algorithms designed to create new data instances resembling the training data, excelling in tasks like image synthesis and style transfer. In the field of decision making, the diffusion model can serve as the RL policy, the action planner, or the data synthesizer for data augmentation.

Selected Publications

• Feng Chen, Fuguang Han, Cong Guan, Lei Yuan, Zhilong Zhang, Yang Yu, Zongzhang Zhang.
  Stable Continual Reinforcement Learning via Diffusion-based Trajectory Replay.
  In Proceedings of the 12th International Conference on Learning Representations (ICLR-2024) (Workshop GenAI4DM), 2024.

• 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.
  Science China Information Sciences (SCIS).

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

• 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-2022), 2022

• 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.
  In Proceedings of the 12th International Conference on Learning Representations (ICLR-2024) (Workshop LLMAgents), 2024.

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

• Lei Yuan*, Ziqian Zhang*, Ke Xue, Hao Yin, Feng Chen, Lihe Li, Cong Guan, Chao Qian, Yang Yu.
  Robust Multi-Agent Coordination via Evolutionary Generation of Auxiliary Adversarial Attackers.
  In Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI 2023) (Oral Presentation), 2023.

* Equal Contribution.

Correspondence

Email: chenf@lamda.nju.edu.cn

Laboratory: A201, 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, 软件新技术国家重点实验室, 210023.)