Yang Li (李阳)

Yang Li (李阳)

Computer Science PhD Student At Universtiy of Manchester

Home Page

I am a doctoral student in Computer Science at the University of Manchester specializing, with a particular emphasis on multi-agent learning and applications of AI. I am supervised by Dr. Wei Pan and co-supervised by Prof. Angelo Cangelosi. Before starting PhD journey, I obtained the Master degree in Information and Communication Engineering from the University of Chinese Academy of Sciences under Prof. Jun Wang and Prof. Yang Yang, and the Bachelor degree in Digital Media Technology from Dalian University of Technology.

My recent research focuses on multi-agent learning in open-ended worlds, aiming to improve the adaptability of multi-agent systems to varying tasks, emergent on-the-fly co-players, and other evolving environments. The ultimate aim of my research is to advance multi-agent interaction in real-world applications where unpredictability is the norm.

Update

  • Two under-review papers are public. Aligning Individual and Collective Objectives in Multi-Agent Cooperation as first author and Open Ad Hoc Teamwork with Cooperative Game Theory as second author.
  • First-authored paper “Self-Supervised MAFENN for Classifying Low-labeled Distorted Images over Mobile Fading Channels” has been accepted by Transactions on Mobile Computing (CCF-A, IF=7.9). Thanks all co-authors “Yang Li, Fanglei Sun, Jingchen Hu, Chang Liu, Fan Wu, Kai Li, Ying Wen, Zheng Tian, Yaodong Yang, Jiangcheng Zhu, Zhifeng Chen, Jun Wang, Yang Yang”. Early Access
  • We updated our COLE-Platform GitHub Repo with following new features:
    • Support Human-Human Experiments (human branch)
    • Play with LLM Agent like GPT-4 (human branch)
    • Training your own COLE_SV agent (cole_training branch)
    • ZSC baseline agents including SP, FCP, PBT, MEP (baseline_training branch)

Selected Publications

  • Yang Li, Wenhao Zhang, Jianhong Wang, Shao Zhang, Yali Du, Ying Wen, and Wei Pan. “Aligning Individual and Collective Objectives in Multi-Agent Cooperation.” arXiv preprint arXiv:2402.12416 (2024). Paper Link.
  • Yang Li*, Shao Zhang*, Jichen Sun, Yali Du, Ying Wen, Xinbing Wang, and Wei Pan. 2023. Cooperative open-ended learning framework for zero-shot coordination. In Proceedings of the 40th International Conference on Machine Learning (ICML’23), Vol. 202. JMLR.org, Article 844, 20470–20484. Paper Link; Website; GitHub.
  • Yang Li*, Shao Zhang*, Jichen Sun, Wenhao Zhang, Yali Du, Ying Wen, Xinbing Wang, and Wei Pan. “Tackling Cooperative Incompatibility for Zero-Shot Human-AI Coordination.” arXiv preprint arXiv:2306.03034 (2023). Paper Link.
  • Yang Li, Kun Xiong, Yingping Zhang, Jiangcheng Zhu, Stephen Marcus McAleer, Wei Pan, Jun Wang, Zonghong Dai, and Yaodong Yang. “JiangJun: Mastering Xiangqi by Tackling Non-Transitivity in Two-Player Zero-Sum Games.” Transactions on Machine Learning Research (2023). Paper Link; Website; GitHub.
  • Yang Li, Fanglei Sun, Jingchen Hu, Chang Liu, Fan Wu, Kai Li, Ying Wen, Zheng Tian, Yaodong Yang, Jiangcheng Zhu, Zhifeng Chen, Jun Wang, Yang Yang. “Self-Supervised MAFENN for Classifying Low-labeled Distorted Images over Mobile Fading Channels.” IEEE Transactions on Mobile Computing (2023). Early Access.