Welcome to Ke Sun's Homepage.

My name is Ke Sun (孙科). I am currently a postdoctoral researcher at University of Pennsylvania, working with Prof. Qi Long and Prof. Weijie Su.

Previously, I was a postdoctoral fellow working with Prof. Susan A. Murphy at Harvard University in 2025. I received my Ph.D. degree in Statistical Machine Learning from University of Alberta in 2024, advised by Prof. Linglong Kong, and was affiliated at Alberta Machine Intelligence Institute (Amii). During my Ph.D., I was fortunate to visit Prof. Chengchun Shi at the London School of Economics and Political Science (LSE) in 2023. I obtained my MPhil in Data Science at Peking University (PKU) in 2020 under the supervision of Prof. Zhouchen Lin and Prof. Zhanxing Zhu. I earned my Bachelor's degree in statistics from SouthWestern University of Finance and Economics (SWUFE) in 2017.

Contact: kesun[AT] fas.harvard.edu Links: Google Scholar / CV / Github / LinkedIn

Research Interests

My research interest is reinforcement learning. I analyze and develop sequential decision-making algorithms grounded in mathematical and statistical principles to build intelligent agents that can reason, explore, and adapt in complex and unknown environments.

Uncertainty & Exploration: Distributional Learning and Risk Control, Entropy Regularization, Predictive Uncertainty
Robustness & Adaptation: Environmental Nonstationarity, Safe and Robust RL, Transfer/Multi-task/Meta/Continual RL
Offline & Causality: Imitation Learning, Offline and Hybrid RL, Causality for RL, Adaptive Experiment Design
Foundations in Embodied Agents: Generative and Un/Self-supervised RL, Model-based RL and World Model, Multi-agent RL
Foundations in LLM Post-training: Mechanism Analysis, Efficiency, and Reward Modeling for Reasoning and Alignment

Selected Preprints / Publications [Full Publications]

[7] Ke Sun, Linglong Kong, Hongtu Zhu, Chengchun Shi. ARMA-Design: Optimal Treatment Allocation Strategies for A/B Testing in Partially Observable Experiments. (Major Revision in Journal of American Statistical Association, 2025)

[6] Ke Sun*, Hongming Zhang*, Jun Jin, Chao Gao, Xi Chen, Wulong Liu, Linglong Kong. Principled Fast and Meta Knowledge Learners for Continual Reinforcement Learning. International Conference on Learning Representations (ICLR), 2026.

[5] Ke Sun, Yingnan Zhao, Enze Shi, Yafei Wang, Xiaodong Yan, Bei Jiang, Linglong Kong. Intrinsic Benefits of Being Categorical Distributional: Uncertainty-aware Regularized Exploration in Reinforcement Learning. Advances in Neural Information Processing Systems (NeurIPS), 2025

[4] Ke Sun, Yingnan Zhao, Wulong Liu, Bei Jiang, Linglong Kong. Distributional Reinforcement Learning with Regularized Wasserstein Loss [code]. Advances in Neural Information Processing Systems (NeurIPS), 2024

[3] Ke Sun*, Yafei Wang*, Yi Liu, Yingnan Zhao, Bo Pan, Shangling Jui, Bei Jiang, Linglong Kong. (*equal contribution in alphabetical order). Damped Anderson Mixing for Deep Reinforcement Learning: Acceleration, Convergence, and Stabilization [code]. Advances in Neural Information Processing Systems (NeurIPS), 2021.

[2] Ke Sun, Zhanxing Zhu, Zhouchen Lin. AdaGCN: AdaBoosting Graph Convolutional Networks into Deep Models [code]. International Conference on Learning Representations (ICLR), 2021.

[1] Ke Sun, Zhouchen Lin, Zhanxing Zhu. Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labels [code]. Association for the Advancement of Artificial Intelligence (AAAI), 2020.

* denotes equal contribution

Favorite Quotes

Practice without theory is blind, but equally, theory without practice is mere intellectual play. ——Immanuel Kant

The statistical community has been committed to the almost exclusive use of data models. This commitment has led to irrelevant theory, questionable conclusions, and has kept statisticians from working on a large range of interesting current problems. …… The danger is that if we define the boundaries of our field in terms of familiar tools and familiar problems, we will fail to grasp the new opportunities. —— Leo Breiman

Talk is cheap, show me the code. —— Linus Torvalds