Siyi Hu

Postdoc, University of South Australia

Joined

September 2020

Names

Siyi Hu (Preferred)

Emails

****@163.com (Confirmed)

****@unisa.edu.au (Confirmed)

Personal Links

Homepage

Career & Education History

Postdoc

University of South Australia (unisa.edu.au)

2024 – Present

PhD student

University of Technology Sydney (uts.edu.au)

2022 – 2024

PhD student

Monash University (monash.edu)

2020 – 2022

Advisors, Relations & Conflicts

No relations added

Expertise

No areas of expertise listed

Publications

SatBench: Satellite Coordination Benchmark Based on Multi-Agent Reinforcement Learning
Mingjun Fan, Siyi Hu, Zehong Cao, Jianglin Qiao, Mahardhika Pratama, Ryszard Kowalczyk
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
SSVPO: Effective Step-Level Credit Assignment for RL Training of Language Models
Yugu Li, Zehong Cao, Jianglin Qiao, Siyi Hu
- ICLR 2026 Poster
- Readers: Everyone
Maximum Entropy Heterogeneous-Agent Reinforcement Learning
Jiarong Liu, Yifan Zhong, Siyi Hu, Haobo Fu, QIANG FU, Xiaojun Chang, Yaodong Yang
- ICLR 2024 spotlight
- Readers: Everyone
MARLlib: Extending RLlib for Multi-agent Reinforcement Learning
Siyi Hu, Yifan Zhong, Minquan Gao, Weixun Wang, Hao Dong, Zhihui Li, Xiaodan Liang, Yaodong Yang, Xiaojun Chang
- Published: 01 Feb 2023, Last Modified: 14 Jan 2026
- Submitted to ICLR 2023
- Readers: Everyone
Role Diversity Matters: A Study of Cooperative Training Strategies for Multi-Agent RL
Siyi Hu, Chuanlong Xie, Xiaodan Liang, Xiaojun Chang
- Published: 28 Jan 2022, Last Modified: 13 Feb 2023
- ICLR 2022 Submitted
- Readers: Everyone
MAIN: A Multi-agent Indoor Navigation Benchmark for Cooperative Learning
Fengda Zhu, Siyi Hu, Yi Zhang, Haodong Hong, Yi Zhu, Xiaojun Chang, Xiaodan Liang
- 20 May 2021 (modified: 24 May 2023)
- Submitted to NeurIPS 2021 Datasets and Benchmarks Track (Round 1)
- Readers: Everyone
UPDeT: Universal Multi-agent RL via Policy Decoupling with Transformers
Siyi Hu, Fengda Zhu, Xiaojun Chang, Xiaodan Liang
- Published: 12 Jan 2021, Last Modified: 05 May 2023
- ICLR 2021 Spotlight
- Readers: Everyone

Siyi Hu

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

SatBench: Satellite Coordination Benchmark Based on Multi-Agent Reinforcement Learning

SSVPO: Effective Step-Level Credit Assignment for RL Training of Language Models

Maximum Entropy Heterogeneous-Agent Reinforcement Learning

MARLlib: Extending RLlib for Multi-agent Reinforcement Learning

Role Diversity Matters: A Study of Cooperative Training Strategies for Multi-Agent RL

MAIN: A Multi-agent Indoor Navigation Benchmark for Cooperative Learning

UPDeT: Universal Multi-agent RL via Policy Decoupling with Transformers

Co-Authors