 |
Hao Liang is a postdoctoral researcher at University of Maryland, College Park, working with Kaiqing Zhang. He received his PhD from The Chinese University of Hong Kong (CUHK), Shenzhen, under the supervision of Zhi-Quan (Tom) Luo. Prior to joining UMD, he was a Research Associate at Kingβs College London. His research lies at the intersection of statistical and computational efficiency in decision-making algorithms, with a particular focus on risk awareness, safety, and multi-agent systems Email: haoliang1 at link.cuhk.edu.cn [CV] [Google Scholar] [LinkedIn] |
|---|
News
Sep 2026
Invited to serve as an Area Chair for ICLR 2027
May 2026
One paper accepted to the IEEE Transactions on Signal Processing (TSP): "Optimistic Thompson Sampling for No-Regret Learning in Unknown Games" [link]
May 2026
Recognized as an ICML 2026 Gold Reviewer
Apr 2026
One paper accepted to ICML 2026: "How Does the Lagrangian Guide Safe Reinforcement Learning through Diffusion Models?" [link]
Jan 2026
Two papers accepted to ICLR 2026: "Is Pure Exploitation Sufficient in Exogenous MDPs with Linear Function Approximation?" [link]
Nov 2025
Served as Local Organizing Chair of the 7th International Conference on Distributed Artificial Intelligence (DAI 2025)
Oct 2025
Our paper, "Why GRPO Needs Normalization: A Local-Curvature Perspective on Adaptive Gradients" will be presented at NeurIPS 2025 Workshop on Efficient Reasoning
π TL;DR: We reveal that GRPOβs normalization acts as an adaptive gradient mechanism aligned with local curvature, accelerating and stabilizing LLM reasoning training.
Sep 2025
Our paper, "Causality Meets Locality: Provably Generalizable and Scalable Policy Learning for Networked Systems" is accepted by NeurIPS 2025 (Spotlight) [link]
π TL;DR: We develop GSAC, a causality-aware framework enabling provable scalability and fast cross-domain adaptation in large networked systems.
Jul 2024
My paper, "Bridging Distributional and Risk-sensitive Reinforcement Learning with Provable Regret Bounds" is accepted by JMLR
π TL;DR: We bridge distributional and risk-sensitive RL under entropic risk measures, achieving near-optimal regret with computationally efficient DRL algorithms.
Jul 2024
Presented "Bridging Distributional and Risk-Sensitive Reinforcement Learning: Balancing Statistical, Computational, and Risk Considerations" at ICML 2024 FoRLaC Workshop
Mar 2024
Delivered a talk "Efficient Risk-aware Decision-making: A Distributional Perspective" at Vector Institute
Mar 2024
Delivered a talk "A Distribution Optimization Framework for Confidence Bounds of Risk Measures" at the Informs Optimization Society (IOS) Conference
Jan 2024
My paper, "Regret Bounds for Risk-sensitive Reinforcement Learning with Lipschitz Dynamic Risk Measures" is accepted at AISTATS 2024
Jul 2023
Presented "A Distribution Optimization Framework for Confidence Bounds of Risk Measures" at ICML 2023
Selected Papers
| Is Pure Exploitation Sufficient in Exogenous MDPs with Linear Function Approximation? [link] | ICLR 2026 |
| Hao Liang, Jiayu Cheng, Sean R. Sinclair, Yali Du | |
| Why GRPO Needs Normalization: A Local-Curvature Perspective on Adaptive Gradients [link] | NeurIPS 2025 Workshop on Efficient Reasoning |
| Cheng Ge*, Heqi Yin*, Hao Liangβ , Jiawei Zhangβ | |
| * Equal contribution. β Co-last authors. | |
| Causality Meets Locality: Provably Generalizable and Scalable Policy Learning for Networked Systems [link] | NeurIPS 2025 (Spotlight) |
| Hao Liang*, Shuqing Shi*, Yudi Zhang, Biwei Huang, Yali Du | |
| Bridging Distributional and Risk-sensitive Reinforcement Learning with Provable Regret Bounds [link] | JMLR |
| Hao Liang, Zhi-Quan Luo | |
| Regret Bounds for Risk-sensitive Reinforcement Learning with Lipschitz Dynamic Risk Measures [link] | AISTATS 2024 |
| Hao Liang, Zhi-Quan Luo | |
| A Distribution Optimization Framework for Confidence Bounds of Risk Measures [link] | ICML 2023 |
| Hao Liang, Zhi-Quan Luo | |