Heng Dong (董恒)

Heng Dong (董恒)

Ph.D. Student

Tsinghua University

Biography

I am a Ph.D. Student advised by Prof. Chongjie Zhang at Institute for Interdisciplinary Information Sciences (IIIS, Tsinghua University), headed by Prof. Andrew Yao. My research interests include reinforcement learning, multi-agent and robot design.

Download my resumé .

Interests
  • Robot Design
  • Large Language Models
  • Embodied AI
  • Reinforcement Learning
  • Multi-Agent
  • Modular RL
Education

  • Ph.D. Student in Artificial Intelligence, 2020-2025

    Tsinghua University

  • B.S. in Computer Science, 2016-2020

    University of Science and Technology of China

Featured Publications

Heng Dong (董恒), Junyu Zhang, Chongjie Zhang
January, 2024 In ICLR
Leveraging Hyperbolic Embeddings for Coarse-to-Fine Robot Design
Leveraging Hyperbolic Embeddings for Coarse-to-Fine Robot Design

We propose to design multi-cellular robots in a coarse-to-fine manner and leverage hyperbolic embeddings for realization.
PDF Cite Code Project
Heng Dong (董恒), Junyu Zhang, Tonghan Wang, Chongjie Zhang
May, 2023 In ICML
Symmetry-Aware Robot Design with Structured Subgroups
Symmetry-Aware Robot Design with Structured Subgroups

We exploit the structure of the design space in robot design problems with symmetry characteristics and generate robots with high performance more efficiently.
PDF Cite Code Project Poster Slides

Recent Publications

Quickly discover relevant content by filtering publications.
Heng Dong (董恒), Tonghan Wang, Jiayuan Liu, Chongjie Zhang (2022). Low-Rank Modular Reinforcement Learning via Muscle Synergy. In NeurIPS.

PDF Cite Code Project Poster Slides

Heng Dong (董恒), Tonghan Wang, Jiayuan Liu, Chi Han, Chongjie Zhang (2021). Birds of a feather flock together: A close look at cooperation emergence via multi-agent rl. In Arxiv.

PDF Cite Code Project

Yihan Wang, Beining Han, Tonghan Wang, Heng Dong (董恒), Chongjie Zhang (2021). DOP: Off-Policy Multi-Agent Decomposed Policy Gradients. In ICLR.

PDF Cite Code Project

Tonghan Wang, Heng Dong (董恒), Victor Lesser, Chongjie Zhang (2020). ROMA: Multi-Agent Reinforcement Learning with Emergent Roles. In ICML.

PDF Cite Code Project

Contact

If you wish to collaborate on research projects or discuss research-related issues, please feel free to contact me via email.

  • Tsinghua University, Beijing, 100084
  • Weekdays 9:00 to 24:00
    Weekends 9:00 to 20:00
  • Follow Me