Publications
See all publications also at Google Scholar.
- Consensus-based Decentralized Multi-agent Reinforcement Learning for Random Access Network Optimization.
Myeung Suk Oh, Zhiyao Zhang, Hairi, Alvaro Velasquez and Jia Liu
MobiHoc 2025, Houston, TX, Oct. 2025 (acceptance rate: 23%) [PDF]
- Enabling Pareto-Stationarity Exploration in Multi-Objective Reinforcement Learning: A Multi-Objective Weighted-Chebyshev Actor-Critic Approach.
Hairi, Jiao Yang, Tianchen Zhou, Haibo Yang, Chaosheng Dong, Fan Yang, Michinari Momma, Yan Gao, Jia Liu.
64th IEEE Conference on Decision and Control (CDC), Rio de Janeiro, Brazil, Dec. 2025 [PDF]
- Finite-Time Global Optimality Convergence in Deep Neural Actor-Critic Methods for Decentralized
Multi-Agent Reinforcement Learning. Zhiyao Zhang*, Myeung Suk Oh*, Hairi, Ziyue Luo, Alvaro Velasquez and Jia Liu.
ICML 2025, Vancouver, Canada,Jul. 2025 (acceptance rate: 26.9%) [PDF]
- On the Hardness of Decentralized Multi-agent Policy Evaluation under Byzantine Attacks.
Hairi*, Minghong Fang*, Zifan Zhang, Alvaro Velasquez and Jia Liu.
WiOpt24, Seoul, South Korea, Oct. 2024. (Invited and refereed paper) [PDF]
- Finite-Time Convergence and Sample Complexity of Actor-Critic Multi-Objective Reinforcement Learning.
Hairi*, Tianchen Zhou*, Haibo Yang, Jia Liu, Tian Tong, Fan Yang, Michinari Momma, and Yan Gao.
ICML 2024, Vienna, Austria, Jul. 2024. (Acceptance rate: 27%). [PDF]
- Byzantine-Robust Decentralized Federated Learning.
Minghong Fang, Zifan Zhang, Hairi, Prashant Khanduri, Jia Liu, Songtao Lu, Yuchen Liu and Neil Gong,
ACM CCS, Salt Lake City, UT, Oct. 2024. (Acceptance rate: 19%) [PDF]
- Sample and Communication Efficient Fully Decentralized MARL Policy Evaluation: via a New Approach: Local TD Update.
Hairi, Zifan Zhang and Jia Liu.
AAMAS 2024, Auckland, New Zealand, May 2024. (Acceptance rate: 25%) [PDF]
- Finite-Time Convergence and Sample Complexity of Multi-Agent Actor-Critic Reinforcement Learning with Average Reward.
Hairi, Jia Liu and Songtao Lu.
ICLR 2022. (Spotlight Presentation, spotlight rate: 5%, acceptance rate 32%) [PDF]
- Beyond Scaling: Calculable Error Bounds of the Power-of-Two Choices Mean-Field Model in Heavy-Traffic.
Hairi, Xin Liu and Lei Ying.
MobiHoc 2021. (Acceptance rate: 20.1%) [PDF]
- NetDyna: Mining Networked Coevolving Time Series with Missing Values.
Hairi, Hanghang Tong and Lei Ying. IEEE BigData, Los Angeles, California, Dec, 2019. (Acceptance rate: 18.7%).[PDF]
* Equal contribution