Tonghan Wang 王同翰

Tonghan Wang is currently a PhD student working with Prof. David Parkes and Prof. Milind Tambe in the EconCS group at Harvard University. Before joining Harvard, he got a M.S. degree at Institute for Interdisciplinary Information Sciences, Tsinghua University, headed by Prof. Andrew Yao, under the supervision of Prof. Chongjie Zhang. His primary research interest is machine learning for problems involving multiple agents, including computational economics and multi-agent coordination in games or complex systems like robotics.

Publications

Confernece Papers

1. Tonghan Wang, Paul Dütting, Dmitry Ivanov, Inbal Talgam-Cohen, David C. Parkes
   Deep Contract Design via Discontinuos Neural Networks.
   NeurIPS 2023: Annual Conference on Neural Information Processing Systems
   PDF
2. Heng Dong, Junyu Zhang, Tonghan Wang, Chongjie Zhang
   Symmetry-Aware Robot Design with Structured Subgroups.
   ICML 2023: International Conference on Machine Learning
   PDF
3. Tonghan Wang*, Heng Dong*, Jiayuan Liu, Chongjie Zhang
   Low-Rank Modular Reinforcement Learning via Muscle Synergy.
   NeurIPS 2022: Annual Conference on Neural Information Processing Systems
   PDF ｜ Code
4. Tonghan Wang*, Yipeng Kang*, Qianlan Yang, Xiaoran Wu, Chongjie Zhang
   Non-Linear Coordination Graphs.
   NeurIPS 2022 [Spotlight]: Annual Conference on Neural Information Processing Systems
   
5. Qianlan Yang, Weijun Dong, Zhizhou Ren, Jianhao Wang, Tonghan Wang, Chongjie Zhang
   Self-Organized Polynomial-Time Coordination Graphs.
   ICML 2022: International Conference on Machine Learning
   PDF | Code
6. Tonghan Wang*, Liang Zeng*, Weijun Dong, Qianlan Yang, Chongjie Zhang
   Context-Aware Sparse Deep Coordination Graphs.
   ICLR 2022 [Spotlight]: International Conference on Learning Representations
   PDF | Code
7. Chenghao Li*, Tonghan Wang*, Chengjie Wu, Qianchuan Zhao, Jun Yang, Chongjie Zhang
   Celebrating Diversity in Shared Multi-Agent Reinforcement Learning.
   NeurIPS 2021: Annual Conference on Neural Information Processing Systems
   PDF | Video | Code
8. 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
9. 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
10. Yipeng Kang, Tonghan Wang, Gerard de Melo
    Incorporating Pragmatic Reasoning Communication into Emergent Language.
    NeurIPS 2020 [Spotlight]: Annual Conference on Neural Information Processing Systems
    PDF
11. 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
12. 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
13. 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
14. 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
    PDF
15. 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

• ICLR 2022: 10th International Conference on Learning Representations.
• NeurIPS 2021: 35th Conference on Neural Information Processing Systems.
• ICML 2021: 38th International Conference on Machine Learning.
• ICLR 2021 Outstanding Reviewer Award: 9th International Conference on Learning Representations.
• IJCAI 2021: 30th International Joint Conference on Artificial Intelligence.
• NeurIPS 2020: 34th Conference on Neural Information Processing Systems.
• IJCAI 2020: 29th International Joint Conference on Artificial Intelligence.

Experience

• Teaching Assistant: Artificial Intelligence: Principles and Techniques, Fall, 2019
• Teaching Assistant: Deep Reinforcement Learning, Spring, 2020
• Teaching Assistant: Artificial Intelligence: Principles and Techniques, Fall, 2020

Education

• M.Sc. in Computer Science (GPA: 3.92 / 4.00)
  IIIS, Tsinghua University @ Beijing, China, 2018 -- Present
  Multi-Agent Reinforcement Learning
• B.Sc. in Computer Science (GPA: 3.99 / 4.00)
  Taishan Academy, Shandong University @ Shandong, China, 2014 -- 2018
  Computer Vision, Augmented Reality, Multi-Agent Reinforcement Learning
  Thesis: Anonymous Hierarchical Multi-Agent Policy Gradients (with distinction)