Guannan Qu

Guannan Qu is an Assistant Professor in the Department of Electrical and Computer Engineering at Carnegie Mellon University (CMU), affiliated with the College of Engineering. He holds a B.S. from Tsinghua University (2014) and a Ph.D. in Applied Mathematics from Harvard University (2019). Before joining CMU, he was a CMI and Resnick Postdoctoral Scholar at Caltech (2019–2021). His research focuses on control theory, optimization, and reinforcement learning (RL), with applications to power systems, multi-agent systems, IoT, and cyber-physical systems. Key areas include scalable RL for networked systems, stability-aware learning, and model-based RL for nonlinear control.

Education:

• Ph.D., Applied Mathematics, Harvard University, 2019
• B.S., Electrical Engineering, Tsinghua University, 2014

Research Interests:

• Machine learning and reinforcement learning for large-scale systems
• Control and optimization of networked systems (e.g., power grids, robotics)
• Model-based and model-free control synthesis
• Scalable distributed algorithms for decentralized decision-making
• Applications in smart grids, IoT, and transportation systems

Awards:

• NSF CAREER Award (2023)
• Caltech Simoudis Discovery Award
• Amazon AI4Science Fellowship
• IEEE SmartGridComm Best Student Paper Award
• AAAIP 2025 Workshop Best Paper Award

Advising & Grants:

• Advises PhD students in RL and control (e.g., Alex Deweese, Ziyi Zhang)
• Recipient of NSF EPCN, C3 AI Institute, and CMU CyLab grants
• Developed scalable RL frameworks for voltage control and inverter coordination

Labs & Teams: Active in CMU’s robotics and power systems research groups, collaborating with industry partners on real-world applications of ML and control theory.