Nan Jiang

Nan Jiang is an Associate Professor in the Department of Computer Science at the University of Illinois at Urbana-Champaign (UIUC) since 2024, previously serving as an Assistant Professor (2018–2024) and Postdoctoral Researcher at Microsoft Research NYC (2017–2018). He earned his PhD in Computer Science and Engineering from the University of Michigan (2017) and a Bachelor of Engineering in Automation from Tsinghua University (2011).

Research Interests focus on the theoretical foundations of reinforcement learning (RL), particularly in function-approximation settings, off-policy evaluation, and partially observable environments (POMDPs). His work addresses challenges like error propagation, Bellman rank, and latent state discovery, with applications in low-rank MDPs, power grid optimization, and network control. He co-authored a monograph on RL theory with Alekh Agarwal and Sham Kakade.

Recent Publications emphasize scalable RL algorithms, off-policy evaluation in complex environments, and theoretical advancements in latent dynamics. Notable trends include integrating causal inference for confounded environments, robustness in MDPs, and modular approaches for sample-efficient learning.

Scientific Honors include the Google Research Scholar Award (2024), Sloan Research Fellowship (2024), ICML Outstanding Paper Runner-Up (2022), NSF CAREER Award (2022), and AAMAS Best Paper Award (2015). He has also received multiple teaching excellence recognitions at UIUC.

Advising includes current PhD students Philip Amortila, Audrey Huang, Yuheng Zhang, and Wei Xiong (co-advised with Tong Zhang), alongside former advisees like Tengyang Xie (now Assistant Professor at UW-Madison) and Jinglin Chen (TikTok).