Homepage
Back to top

Publications

Conference Papers

  • GemNet: Menu-Based, Strategy-Proof Multi-Bidder Auctions Through Deep Learning

    2024

    Tonghan Wang*, Yanchen Jiang*, David C. Parkes

    ACM EC 2024

    Exemplary Paper in AI Track

    PDF

  • Multi-Sender Persuasion: A Computational Perspective

    2024

    Tonghan Wang*, Safwan Hossian*, Tao Lin*, Yiling Chen, David C. Parkes, Haifeng Xu

    ICML 2024

    PDF

  • Position: Social Environment Design Should be Further Developed for AI-based Policy-Making

    2024

    Edwin Zhang, Sadie Zhao, Tonghan Wang, Safwan Hossain, Henry Gasztowtt, Stephan Zheng, David C. Parkes, Milind Tambe, Yiling Chen

    ICML 2024

    PDF

  • Deep Contract Design via Discontinuos Neural Networks

    2023

    Tonghan Wang, Paul Dütting, Dmitry Ivanov, Inbal Talgam-Cohen, David C. Parkes

    NeurIPS 2023

    PDF

  • Symmetry-Aware Robot Design with Structured Subgroups

    2023

    Heng Dong, Junyu Zhang, Tonghan Wang, Chongjie Zhang

    ICML 2023

    PDF

  • Low-Rank Modular Reinforcement Learning via Muscle Synergy

    2022

    Tonghan Wang*, Heng Dong*, Jiayuan Liu, Chongjie Zhang

    NeurIPS 2022

    PDF ｜ Code

  • Non-Linear Coordination Graphs

    2022

    Tonghan Wang*, Yipeng Kang*, Qianlan Yang, Xiaoran Wu, Chongjie Zhang

    NeurIPS 2022

    Spotlight Paper

    PDF

  • Self-Organized Polynomial-Time Coordination Graphs

    2022

    Qianlan Yang, Weijun Dong, Zhizhou Ren, Jianhao Wang, Tonghan Wang, Chongjie Zhang

    ICML 2022

    PDF | Code

  • Context-Aware Sparse Deep Coordination Graphs

    2022

    Tonghan Wang*, Liang Zeng*, Weijun Dong, Qianlan Yang, Chongjie Zhang

    ICLR 2022

    Spotlight Paper

    PDF | Code

  • Celebrating Diversity in Shared Multi-Agent Reinforcement Learning

    2021

    Chenghao Li*, Tonghan Wang*, Chengjie Wu, Qianchuan Zhao, Jun Yang, Chongjie Zhang

    NeurIPS 2021

    PDF | Website | Code

  • RODE: Learning Roles to Decompose Multi-Agent Tasks

    2021

    Tonghan Wang, Tarun Gupta, Anuj Mahajan, Bei Peng, Shimon Whiteson, and Chongjie Zhang

    ICLR 2021

    PDF | Website | Code

  • DOP: Off-Policy Multi-Agent Decomposed Policy Gradients

    2021

    Tonghan Wang*, Yihan Wang*, Beining Han*, Heng Dong, and Chongjie Zhang

    ICLR 2021

    PDF | Video | Code

  • Incorporating Pragmatic Reasoning Communication into Emergent Language

    2020

    Yipeng Kang, Tonghan Wang, Gerard de Melo

    NeurIPS 2020

    Spotlight Paper

    PDF

  • ROMA: Multi-Agent Reinforcement Learning with Emergent Roles

    2020

    Tonghan Wang, Heng Dong, Victor Lesser, and Chongjie Zhang

    ICML 2020

    PDF | Website | Code

  • Influence-Based Multi-Agent Exploration

    2020

    Tonghan Wang*, Jianhao Wang*, Yi Wu, and Chongjie Zhang

    ICLR 2020

    Spotlight Paper

    PDF | Website | Code

  • Learning Nearly Decomposable Value Functions with Communication Minimization

    2020

    Tonghan Wang*, Jianhao Wang*, Chongyi Zheng, and Chongjie Zhang

    ICLR 2020

    PDF | Website | Code

  • Convergence of Multi-Agent Learning with a Finite Step Size in General-Sum Games

    2019

    Xinliang Song, Tonghan Wang, and Chongjie Zhang

    AAMAS 2019

    PDF

  • Compact Object Representation of a Non-Rigid Object for Real-Time Tracking in AR Systems

    2018

    Tonghan Wang, Xueying Qin, Fan Zhong, Baoquan Chen, and Ming C. Lin

    ISMAR 2018

    PDF | Website

Journal Papers

  • Multi-agent policy transfer via task relationship modeling

    2024

    Tonghan Wang, Rongjun Qin, Feng Chen, Lei Yuan, Xiaoran Wu, Zongzhang Zhang, Chongjie Zhang, Yang Yu

    Science China Information Sciences

    Article

  • Celebrating Diversity With Subtask Specialization in Shared Multiagent Reinforcement Learning                                        

    2023

    Chenghao Li, Tonghan Wang, Chengjie Wu, Qianchuan Zhao, Jun Yang, Chongjie Zhang

    IEEE Transactions on Neural Networks and Learning Systems

    Article

Workshop Papers

  • Multi-agent policy transfer via task relationship modeling

    2022

    Tonghan Wang*, Rongjun Qin*, Feng Chen*, Lei Yuan, Xiaoran Wu, Zongzhang Zhang, Chongjie Zhang, Yang Yu                                                    

    NeurIPS 2022 Deep Reinforcement Learning Workshop

    PDF

  • Model and Method: Training-Time Attack for Cooperative Multi-Agent Reinforcement Learning

    2022

    Tonghan Wang*, Siyang Wu*, Xiaoran Wu, Jingfeng Zhang, Yujing Hu, Changjie Fan, Chongjie Zhang

    NeurIPS 2022 Deep Reinforcement Learning Workshop

    PDF

Contact me