avatar

Siyi Hu

Research Fellow
Adelaide Univeristy
theohsy (at) gmail.com


About Me

I am currently a Research Fellow at Adelaide Univeristy. Prior to this, I was a PhD student under the guidance of Prof. Xiaojun Chang at the University of Technology Sydney.

Research Interests

My research sits at the intersection of artificial intelligence, cooperative decision-making, and large language models (LLMs). I focus on building intelligent systems that can work together in dynamic, real-world settings—from satellite clusters to human-AI teams. I led the development of MARLlib, a widely adopted open-source library that helps researchers prototype and benchmark multi-agent reinforcement learning (MARL) algorithms. More recently, I’ve extended my work to GenAI, creating ProAgent, a framework that uses LLMs to enable proactive and interpretable cooperation between agents and humans. Whether through scalable algorithms or applied systems, my goal is to make AI more adaptable, accessible, and aligned with real-world needs.

News

Publications

  1. AAAI 2024 (oral)
    ProAgent: Building Proactive Cooperative AI with Large Language Models
    Ceyao Zhang^, Kaijie Yang^, Siyi Hu^, Zihao Wang, Guanghe Li, Yihang Sun, Cheng Zhang, Zhaowei Zhang, Anji Liu, Song-Chun Zhu, Xiaojun Chang, Junge Zhang, Feng Yin, Yitao Liang, Yaodong Yang* (^Equal contribution *Corresponding authors)
    The 38th Annual AAAI Conference on Artificial Intelligence
    PDF Code Project Page BibTex

  2. JMLR 2023
    MARLlib: A Scalable and Efficient Multi-agent Reinforcement Learning Library
    Siyi Hu, Yifan Zhong, Minquan Gao, Weixun Wang, Hao Dong, Xiaodan Liang, Zhihui Li, Xiaojun Chang*, Yaodong Yang* (*Corresponding authors)
    Journal of Machine Learning Research 24, 1-23
    PDF Code BibTex

  3. ICLR 2024 (spotlight)
    Maximum Entropy Heterogeneous-Agent Mirror Learning
    Jiarong Liu, Yifan Zhong, Siyi Hu, Haobo Fu, Qiang Fu, Xiaojun Chang, Yaodong Yang* (*Corresponding authors)
    The Twelfth International Conference on Learning Representations
    PDF Code BibTex

  4. JMLR 2023
    Heterogeneous-Agent Reinforcement Learning
    Yifan Zhong, Jakub Grudzien Kuba, Siyi Hu, Jiaming Ji, Yaodong Yang* (*Corresponding authors)
    Journal of Machine Learning Research
    PDF Code BibTex

  5. ICML 2022
    Policy Diagnosis via Measuring Role Diversity in Cooperative Multi-agent RL
    Siyi Hu, Chuanlong Xie, Xiaodan Liang, Xiaojun Chang* (*Corresponding authors)
    International Conference on Machine Learning, 2022
    PDF BibTex

  6. ICLR 2021 (spotlight)
    UPDeT: Universal Multi-agent RL via Policy Decoupling with Transformers
    Siyi Hu, Fengda Zhu, Xiaojun Chang*, Xiaodan Liang (*Corresponding authors)
    International Conference on Learning Representations, 2021
    PDF Code BibTex

Services

Reviewers


Powered by Jekyll and Minimal Light theme.