CV

Research Appointment

Aug. 2024-present: Postdoctoral Researcher, Automatic Control Lab (IfA), ETH Zurich, Zurich, Switzerland. Advisor: Prof. Florian Dorfler.

2018-2024: Ph.D. in Control Science and Engineering, Department of Automation, Tsinghua University, Beijing, China. Advisor: Prof. Keyou You.
Dec. 2022-May 2023: Visiting Scientist, Automatic Control Lab (IfA), ETH Zurich, Zurich, Switzerland. Advisor: Prof. Florian Dorfler.
2014-2018: B.Eng. in Automation, Harbin Institute of Technology, Harbin, China.

I work on data-driven control, adaptive control, reinforcement learning, and their applications to networked and safety-critical dynamical systems.

2025: Outstanding Ph.D. Dissertation Award, Chinese Association of Automation (20 recipients nationwide).
2023: Outstanding Doctoral Student Award, Beijing Association of Automation (10 recipients citywide).
2021: Best Oral Presentation Award, Beijing AI Academic Forum.
2021-2023: Scholarships, Tsinghua University.

2025: Organizer, NCCR Workshop on Interconnection of Autonomous Systems, Switzerland.

2026: Co-Lecturer and Head Teaching Assistant, Computational Control, ETH Zurich. Designed and delivered a lecture on data-driven LQR, integrated research into teaching, led the tutorial component, supervised teaching assistants, and delivered four tutorial sessions.
2025: Teaching Assistant, Computational Control, ETH Zurich. Delivered three tutorial sessions on data-driven and learning-based control.
2024-2025: Teaching Assistant, Control Systems, ETH Zurich. Designed exams and course exercises.
2022: Teaching Assistant, Operations Research, Tsinghua University. Led tutorials, graded exams and exercise sheets, and held office hours.
2021: Teaching Assistant, Convex Optimization, Tsinghua University. Led tutorials, graded exams and exercise sheets, and held office hours.

2026: Rafael Dux, MSc Thesis, Delft University of Technology. “Data-Enabled Policy Optimization for Aeroelastic Flutter and Loads Control.” Co-supervised with Prof. Xuerui Wang; ongoing.
2026: Lorenzo Pasini, Ph.D. student, University of Padova. “Adaptive Control for Nonlinear Systems via Policy Gradient Methods.” Co-supervised with Han Wang and Prof. Alessandro Chiuso; ongoing.
2025: Thierry Schwaller, MSc Thesis, ETH Zurich. “Adaptive Control via Reinforcement Learning: Optimality, Stability, and Robustness.” Co-supervised with Marcell Bartos; ongoing.
2025: Thierry Schwaller, Semester Thesis, ETH Zurich. “Bridging Indirect and Direct Data-Driven LQR Control via Regularization.” Resulted in a conference paper.
2025: Emmanuel Otibu Darko Korankye, MSc Thesis, Ashesi-ETH Master’s Program, Ashesi University, Ghana. “Direct Data-Driven and Adaptive Control for Racing Cars.” Co-supervised with Han Wang; received top grades and led to an ongoing journal paper.
2025: Félix Laurent, MSc Thesis, ETH Zurich. “Indirect Policy Gradient Adaptive Control for Linear Time-Varying Systems.” Co-supervised with Jaap Eising; resulted in a conference paper.
2024: Shubo Kang, Ph.D. student, Tsinghua University. “Linear Convergence of Data-Enabled Policy Optimization for Linear Quadratic Tracking.” Co-supervised with Prof. Keyou You; resulted in a conference paper.

2025: “LQR learning pipelines: between reinforcement learning and adaptive control,” Scalable Optimization and Control (SOC) Lab, University of California San Diego, United States. Online invited talk..
2025: “LQR learning pipelines: between reinforcement learning and adaptive control,” Institute for Systems Theory and Automatic Control (IST), University of Stuttgart, Germany.
2025: “LQR learning pipelines: between reinforcement learning and adaptive control,” Jan C. Willems Center for Systems and Control, University of Groningen, The Netherlands.
2025: “LQR learning pipelines: between reinforcement learning and adaptive control,” Faculty of Aerospace Engineering, Delft University of Technology, The Netherlands.
2025: “LQR learning pipelines: between reinforcement learning and adaptive control,” Urban Energy Systems Lab, Empa, Switzerland.
2025: “LQR learning pipelines: between reinforcement learning and adaptive control,” School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, China.
2025: “LQR learning pipelines: between reinforcement learning and adaptive control,” School of Automation Science and Electrical Engineering, Beihang University, China.
2024: “Data-enabled policy optimization for direct adaptive learning of the LQR,” International Young Scholars Forum, Shanghai University, China.

2025: “LQR learning pipelines: between reinforcement learning and adaptive control,” European Research Network System Identification (ERNSI), . Oral presentation; selected as the only non-PI speaker..
2025: “Regularization for covariance parameterization of the direct data-driven LQR,” IEEE Conference on Decision and Control (CDC), Brazil.
2025: “Direct adaptive control of grid-connected power converters via output-feedback data-enabled policy optimization,” European Control Conference (ECC), Greece.
2023: “Globally convergent policy gradient methods for linear quadratic control of partially observed systems,” IFAC World Congress, Japan.

Prof. Florian Dorfler, Automatic Control Laboratory, ETH Zurich, dorfler@ethz.ch
Prof. Keyou You, Department of Automation, Tsinghua University, youky@tsinghua.edu.cn