Professor Yangchen PAN

Prof. Yangchen Pan joined the City University of Hong Kong after serving as a Lecturer (Teaching and Research) in Machine Learning in the Department of Engineering Science at the University of Oxford. Prior to his appointment at Oxford, he got his PhD in Computer Science at the University of Alberta. His doctoral research focused on developing sample-efficient reinforcement learning algorithms. He also spent a short period working in industry in Canada and the United States.

During his tenure at the University of Oxford, Prof. Pan was awarded the prestigious UK Engineering and Physical Sciences Research Council (EPSRC) New Investigator Award, securing about £450,000 to develop sample- and computation-efficient AI paradigms that aim to make advanced AI systems both more capable and more accessible. In addition, he has secured more than 70,000 GPU computing hours through UKRI—to support a range of AI research projects.

Prof. Pan has published in leading machine learning and artificial intelligence venues, including the Journal of Machine Learning Research (JMLR), Journal of Artificial Intelligence Research (JAIR), Transactions on Machine Learning Research (TMLR), ICML, NeurIPS, and ICLR. He actively serves the research community as an Area Chair, or (Senior) Program Committee member for leading conferences and journals, including NeurIPS, ICML, ICLR, AISTATS, and others. His service has been recognized with the AISTATS 2022 Top Reviewer Award and the NeurIPS 2021 Outstanding Reviewer Award.

Prof. Pan's research focuses on scalable, robust, and efficient sequential and strategic decision-making under uncertainty, where decisions must account for their long-term consequences. While much of this work is grounded in reinforcement learning, it also draws on related areas of machine learning and artificial intelligence. His current research interests include:

• Computationally and sample-efficient reinforcement learning, with a particular emphasis on efficient planning using world models for physical systems with evolving dynamics.
• Robust decision-making under distribution shift across both space and time, including continual and lifelong learning.