Ziyan Wang

Email: ziyan.wang[at]kcl[dot]ac[dot]uk

I am currently the second-year Ph.D. student at Cooperative AI Lab, King’s College London. I am supervised by Dr Yali Du and Prof. Sanjay Modgil. I received my M.S. degree from the University College London, where I was supervised by Prof. Jun Wang. I have also been fortunate to work closely with Prof. Fei Fang at the Carnegie Mellon University.

My research interests lie in the intersection of Multi-agent Reinforcement Learning, Large Language Models, and Robotics. Current research themes include:

  • Multi-agent Reinforcement Learning: Developing algorithms that enable agents to learn to collaborate and compete in complex environments.
  • Human Robot Cooperation: Bridging the gap between human and robot communication, enabling robots to understand huamn’s free-form instructions.
  • Safe Reinforcement Learning: Ensuring that agents learn policies that satisfy given constraints while accomplishing tasks.
  • Large Language Models: Exploring the capabilities of large language models in multi-agent settings.

News

Nov 2024 🎉 One paper is accepted to NeurIPS 2024 Causal Representation Learning Workshop. Also happy to share that I got the NeurIPS 2024 Scholar Award! 🏆
Sep 2024 Happy to share that two of our papers have been accepted to NeurIPS’24 as co-first author, with one selected for Oral presentation (acceptance rate around: 0.5%). Excited for the discussions in Vancouver this December! :maple_leaf:
Apr 2024 Invited practical tutorial on Optimisation at OxML ML Summer School in May, 2024. :school:
Mar 2024 Two papers are accepted to ICLR’24 GenAI4DM Workshop, see you in Austria! :airplane:

Selected Publications

*: Equal contribution, : Corresponding author
  1. Policy Learning from Tutorial Books via Understanding, Rehearsing and Introspecting Oral NeurIPS'24
    Xiong-Hui Chen*, Ziyan Wang*, Yali Du, Shengyi Jiang, Meng Fang, Yang Yu, and Jun Wang
    In The Thirty-Eight Annual Conference on Neural Information Processing Systems (NeruIPS) , 2024
  2. Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf NeurIPS'24
    Xuanfa Jin*, Ziyan Wang*, Yali Du, Meng Fang, Haifeng Zhang, and Jun Wang
    In The Thirty-Eight Annual Conference on Neural Information Processing Systems (NeruIPS) , 2024
  3. Safe Multi-agent Reinforcement Learning with Natural Language Constraints ICLR'24 GenAI4DM Workshop
    Ziyan Wang, Meng Fang, Tristan Tomilin, Fei Fang, and Yali Du
    In ICLR 2024 Workshop on Generative Models for Decision Making (ICLR GenAI4DM) , 2024
  4. MACCA: Offline Multi-agent Reinforcement Learning with Causal Credit Assignment NeurIPS'24 CRL Workshop
    In NeurIPS 2024 Causal Representation Learning Workshop (NeurIPS CRL) , 2024
  5. M³HF: Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality Preprint
    Ziyan Wang, Zhicheng Zhang, Fei Fang, and Yali Du
    In Under Review , 2024
  6. Chessgpt: Bridging policy learning and language modeling NeurIPS'23
    Xidong Feng, Yicheng Luo, Ziyan Wang, Hongrui Tang, Mengyue Yang, Kun Shao, David Mguni, Yali Du, and Jun Wang
    In The Thirty-Seventh Annual Conference on Neural Information Processing Systems (NeruIPS) , 2023

Professional Services

  • Conference reviewer for ICML 2024, NeurIPS 2024, ICLR 2025, AISTATS 2025
  • Journal reviewer for IEEE Transactions on Knowledge and Data Engineering (TKDE), IEEE Transactions on Artificial Intelligence (TAI)