Hanbin Zhou

[Email] [CV] [Blog]

Hi there! This is Hanbin Zhou, currently a PhD student at the Hong Kong University of Science and Technology (Guangzhou). I am fortunate to be advised by Prof. Tianyuan Jin. Prevously, I obtained my Master’s degree from the University of Southern California, where I had the privilege to work with Prof. Haipeng Luo.

My research interests generally lie in the intersection of statistical learning, online decision making and optimization. Specifically, I work on reinforcement learning theory, especially under adversarial and multi-agent settings.

Publications

Improved Sample Complexity for Markov Games via Variance-Aware Bandit Learning
Hanbin Zhou*, Canzhe Zhao*, Shuai Li
Under Review

Misc

One might find my github username somewhat obscure, it basically stands for

$$\text{HZZHUGHES}=\text{HZ}+\text{Z}+\text{HUGHES}$$

where $\text{HZ}$ is the abbreviation of my hometown Hangzhou, $\text{Z}$ is the initial of my surname and $\text{HUGHES}$ is my English name.