Zihan Zhang

Zihan Zhang is an Assistant Professor at the Department of Computer Science and Engineering (CSE), the Hong Kong University of Science and Technology (HKUST). His research focuses on Artificial Intelligence and Theoretical Computer Science, with interests in reinforcement learning, online learning, game theory, and convex optimization. Previously, he was a postdoc researcher at the Paul G. Allen School of CSE, University of Washington, and the Department of ECE, Princeton University. He obtained his Ph.D. and bachelor's degree from the Department of Automation, Tsinghua University, in 2022 and 2017, respectively. His work has been published in top journals and conferences such as JACM, COLT, NeurIPS, and ICML.

Zhang Zihan is a researcher at the Hong Kong University of Science and Technology, specializing in machine learning, reinforcement learning, online learning, and statistics. Their work focuses on advancing model-free reinforcement learning through techniques such as reference-advantage decomposition and variance-aware confidence sets. Zhang has contributed to improving regret bounds and sample complexity in reinforcement learning, particularly in the context of linear mixture MDPs and horizon-free algorithms. Their research also explores multi-distribution learning and batch-regret tradeoffs, aiming to achieve near-optimal performance in both stochastic and deterministic environments. Zhang's publications highlight the development of efficient algorithms for regret minimization and optimal policy learning in complex sequential decision-making problems.