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’sresearch interests broadly span machine learning. Some of the research directions he is currently exploring include the following:

1. World models and model-based RL. He is interested in developing physically-plausible models that capture dynamics of real-world environments, with the goal of improving both the sample and computational efficiency of RL agents.
2. Fundamental problems in RL. While not necessarily theoretical in nature, these problems often require rigorous empirical design and evaluation.
3. The connections between RL and other areas of AI. This includes using the RL perspective to better understand supervised and unsupervised learning (e.g. generative models), as well as investigating how RL can contribute to LLMs.
4. More broadly: problems involving generalization under distribution shift, non-i.i.d. data, and changing environments. These challenges arise across a wide range of applications, and his work seeks to develop methods that remain robust under such conditions.

Openings: He is looking for highly motivated PhD students. Please refer to his personal website for details.