Tonghan Wang

IIIS, Tsinghua University
Beijing, China

Email Email
Google Scholar Google Scholar
Github Github

Tonghan Wang is currently a Master student working with Prof. Chongjie Zhang at Institute for Interdisciplinary Information Sciences, Tsinghua University, headed by Prof. Andrew Yao. His primary research goal is to develop innovative models and methods to enable effective multi-agent cooperation, allowing a group of individuals to explore, communicate, and accomplish tasks of higher complexity. His research interests include multi-agent learning, reinforcement learning, and reasoning under uncertainty.



  1. Tonghan Wang*, Heng Dong*, Jiayuan Liu, Chi Han, Chongjie Zhang
    Birds of a Feather Flock Together: A Close Look at Cooperation Emergence via Multi-Agent RL.
    PDF | Video | Code
  2. Tonghan Wang*, Chenghao Li*, Chengjie Wu*, Jun Yang, Qianchuan Zhao, Chongjie Zhang
    Celebrating Diversity in Shared Multi-Agent Reinforcement Learning.
    PDF | Video | Code
  3. Tonghan Wang*, Liang Zeng*, Weijun Dong, Qianlan Yang, Chongjie Zhang
    Context-Aware Sparse Deep Coordination Graphs.
    PDF | Code

Confernece Papers

  1. Tonghan Wang, Tarun Gupta, Anuj Mahajan, Bei Peng, Shimon Whiteson, and Chongjie Zhang
    RODE: Learning Roles to Decompose Multi-Agent Tasks.
    ICLR 2021: International Conference on Learning Representations
    PDF | Video | Code
  2. Tonghan Wang*, Yihan Wang*, Beining Han*, Heng Dong, and Chongjie Zhang
    DOP: Off-Policy Multi-Agent Decomposed Policy Gradients.
    ICLR 2021: International Conference on Learning Representations
    PDF | Video | Code
  3. Yipeng Kang, Tonghan Wang, Gerard de Melo
    Incorporating Pragmatic Reasoning Communication into Emergent Language.
    NeurIPS 2020 (Spotlight): Annual Conference on Neural Information Processing Systems
  4. Tonghan Wang, Heng Dong, Victor Lesser, and Chongjie Zhang
    ROMA: Multi-Agent Reinforcement Learning with Emergent Roles.
    ICML 2020: International Conference on Machine Learning
    PDF | Video | Code
  5. Tonghan Wang*, Jianhao Wang*, Yi Wu, and Chongjie Zhang
    Influence-Based Multi-Agent Exploration.
    ICLR 2020 (Spotlight): International Conference on Learning Representations
    PDF | Video | Code
  6. Tonghan Wang*, Jianhao Wang*, Chongyi Zheng, and Chongjie Zhang
    Learning Nearly Decomposable Value Functions with Communication Minimization.
    ICLR 2020: International Conference on Learning Representations
    PDF | Video | Code
  7. Xinliang Song, Tonghan Wang, and Chongjie Zhang
    Convergence of Multi-Agent Learning with a Finite Step Size in General-Sum Games
    AAMAS 2019: International Conference on Autonomous Agents and Multi-Agent Systems
  8. Tonghan Wang, Xueying Qin, Fan Zhong, Baoquan Chen, and Ming C. Lin
    Compact Object Representation of a Non-Rigid Object for Real-Time Tracking in AR Systems
    ISMAR 2018: IEEE International Symposium on Mixed and Augmented Reality Adjunct
    PDF | Video

Reviewer Activities