Jingjing Bu

I am a PhD candidate in the Department of Electrical Engineering. I am currently a member of Robotics, Aerospace, and Information Networks (RAIN) lab and advised by Mehran Mesbahi and Maryam Fazel. I am broadly interested in machine learning, convex and distributed optimization, optimal control, game thoery, multi-agent systems and Koopman operator theory with a particular focus on bridging learning and control. My current work blends linear quadratic optimal control, optimization, reinforcement learning, dynamic and differential game theory.

Education

• Ph.D Student in Electrical Engineering, University of Washington, Seattle ( 2015 – present)
• Master Student in Electrical Engineering, University of Washington, Seattle (2013 – 2015)
• B.Sc in Physics, Beijing University of Aeronautic and Astronautics, Beijing, China (2009)

Professional Experience

• Datang Telecom, Beijing, China 2009-2013

Research Interests

• Reinforcement Learning
• Convex Optimization and Distributed Optimization
• Optimal Control
• Multi-agent Systems
• Game Theory
• Koopman Operator Theory in Dynamical Systems and Control

Publications

Preprint:

• Jingjing Bu, Afshin Mesbahi, Mehran Mesbahi, “Policy Gradient-based Algorithms for Continuous-time Linear Quadratic Control“, arXiv:2006.09178, 2020.
• Jingjing Bu, Mehran Mesbahi, “A Note on Nesterov’s Accelerated Method in Nonconvex Optimization: a Weak Estimate Sequence Approach“, arXiv:2006.08548, 2020.
• Jingjing Bu, Lillian J. Ratliff, Mehran Mesbahi, “Global Convergence of Policy Gradient for Sequential Zero-Sum Linear Quadratic Dynamic Games“, arXiv:1911.04672, 2019.
• Jingjing Bu,  Afshin Mesbahi, Maryam Fazel, Mehran Mesbahi, “LQR through the Lens of First Order Methods: Discrete-time Case“, arXiv:1907.08921, 2019.
• Jingjing Bu, Afshin Mesbahi, Mehran Mesbahi, “On Topological and Metrical Properties of Stabilizing Feedback Gains: the MIMO Case“, arXiv:1904.02737, 2019.

Journal Papers:

• Jingjing Bu, Mehran Mesbahi, “Global Convergence of Policy Gradient Algorithms for Indefinite Least Squares Stationary Optimal Control“, to appear in  IEEE Control Systems Letters
• Jingjing Bu, Afshin Mesbahi, Mehran Mesbahi, “On Topological and Metrical Properties of Stabilizing Feedback Gains“, to appear as full paper in IEEE Transactions on Automatic Control, 2019.
• Afshin Mesbahi, Jingjing Bu, Mehran Mesbahi, “Nonlinear Observability via Koopman Analysis: Characterizing the Role of Symmetry“, to appear in Automatica, 2019
• Guofeng Zhang, Jingjing Bu, “Entanglement Evolution between Atoms in the Non-degenerate Two Photons Tavis-Cummings Model in Resonance and Non-resonance cases”, Acta Physica Sinica, 2010.

Conference Papers:

• Jingjing Bu, Mehran Mesbahi, “Global Convergence of Policy Gradient Algorithms for Indefinite Least Squares Stationary Optimal Control“, to be presented in IEEE Conference on Decision and Control, Jeju Island, Republic of Korea, 2020
• Jingjing Bu, Afshin Mesbahi, Mehran Mesbahi, “LQR via the Lens of First Order Flows“, 2020 American Control Conference, Denver, CO.
• Afshin Mesbahi, Jingjing Bu, Mehran Mesbahi, “On Modal Properties of the Koopman Operator for Nonlinear Systems with Symmetry“, 2019 American Control Conference, Philadelphia, PA.
• Jingjing Bu, Maryam Fazel, Mehran Mesbahi, “Accelerated Consensus with Linear Rate of Convergence“, 2018 American Control Conference, Milwaukee, WI.

Teaching

• EE215 Fundamentals of Electrical Engineering (2015)
• EE233 Circuit Theory, University of Washington (2014)
• EE447 Control System Analysis, University of Washington (2015)
• EE474 Introduction to Embedded Systems, University of Washington (2015)
• EE510 Mathematical Foundations of Systems Theory, University of Washington(2016)