Reinforcement learning theory and algorithms
How to make sequential decision-making reliable when models are imperfect, data are limited, and safety constraints matter.
About me
I am an Eric and Wendy Schmidt AI Postdoctoral Fellow at the AI for Science Institute, Cornell University, working with Prof. Fengqi You.
Before joining Cornell, I received my Ph.D. in Computer Science from the Institute for Interdisciplinary Information Sciences at Tsinghua University in 2025, advised by Prof. Chenye Wu and Prof. Ran Duan. I was also a visiting student researcher in Computing and Mathematical Sciences at Caltech from 2023 to 2024, advised by Prof. Adam Wierman. I received my bachelor's degree in Computer Software Engineering from Huazhong University of Science and Technology in 2020.
Research areas
Research
My research develops theoretical and algorithmic foundations for reliable sequential decision-making under uncertainty, with applications in energy systems and AI infrastructure.
Energy system operations
How to operate power systems reliably when renewable uncertainty, flexible demand, privacy requirements, and large-scale decisions interact.
AI infrastructure and data centers
How to plan and operate AI data centers when power availability, workload flexibility, and regional infrastructure constraints limit growth.
NeurIPS 2025, Spotlight
Reinforcement Learning with Imperfect Transition Predictions: A Bellman-Jensen Approach[PDF]
ICML 2025
Overcoming the Curse of Dimensionality in Reinforcement Learning Through Approximate Factorization[PDF]
IEEE Transactions on Smart Grid
Self-Improving Online Storage Control for Stable Wind Power Commitment[PDF]
IEEE Transactions on Power Systems
Sample-Adaptive Robust Economic Dispatch with Statistical Guarantees[PDF]
IEEE Control Systems Letters
On the Optimal Deterministic Policy Learning in Chance-Constrained Markov Decision Processes[PDF]
Teaching
Teaching
Guest lectures
- Fall 2025: AI for Science, Cornell University
- Fall 2025: AI for Energy Systems, Cornell University
- Spring 2026: Deep Learning, Cornell University
Teaching assistance
- Fall 2021: Combinatorial Mathematics, Tsinghua University
- Fall 2022: AI Research Practice, Yao Class, Tsinghua University
News
News
Sep. 2025
[Schmidt AI]
I joined the AI for Science Institute at Cornell University as an Eric and Wendy Schmidt AI Postdoctoral Fellow.
Sep. 18, 2025
[NeurIPS 2025 Spotlight]
Our work on reinforcement learning with imperfect transition predictions was accepted as a Spotlight.
Sep. 9, 2025
[L-CSS]
Our work on deterministic policy learning in chance-constrained Markov decision processes was accepted.
Aug. 2025
[ICML 2025]
Our paper on approximate factorization for reinforcement learning was accepted to ICML 2025 and will be presented in Vancouver.
Apr. 21, 2025
[ACM e-Energy 2025]
Our work on closed-loop bilevel robust optimization for economic dispatch was accepted.
Dec. 2024
[CDC 2024]
Attended the IEEE Conference on Decision and Control.
Jul. 21, 2024
[IEEE PESGM 2024]
Presented our work on sample-adaptive joint chance-constrained optimization for economic dispatch in Seattle.
Jan. 1, 2024
[T-SG]
Our work on self-improving online storage control for stable wind power commitment was accepted.
Oct. 2023
[INFORMS 2023]
Attended the INFORMS Annual Meeting.
Aug. 27, 2023
[Caltech CMS visit]
Began a six-month visit to Computing + Mathematical Sciences at Caltech, collaborating with Prof. Adam Wierman.
Service
Professional Service
Reviewer for NeurIPS, AAAI, IEEE CDC, ACC, PSCC, IEEE SmartGridComm, ACM e-Energy, Applied Energy, IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE Transactions on Smart Grid, IEEE Transactions on Power Systems, and related journals.
TPC member for IEEE SmartGridComm, ACM e-Energy poster session.
Contact