Resume
Academic Achievements
- Publications: 'Constrained Optimization From a Control Perspective via Feedback Linearization' accepted to NeurIPS 2025, 'Optimism as Risk-Seeking in Multi-Agent Reinforcement Learning' new paper, 'On the Optimal Control of Network LQR with Spatially-exponential Decaying Structure' accepted to Automatica, 'Scalable Spectral Representations for Multi-agent Reinforcement Learning in Network MDPs' accepted to AISTATS 2025, 'Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity' accepted to ICLR, 'Gradient play in stochastic games: stationary points, convergence, and sample complexity' accepted to Transaction of Automatic Control (TAC).
- Awards: Selected for the Rising Stars program at the 2025 Northeast Robotics Colloquium (NERC), EECS rising star in 2024, recipient of the MIT Postdoctoral Fellowship for Engineering Excellence.
Research Experience
- Postdoc for Engineering Excellence at MIT, working with Prof. Asu Ozdaglar and Prof. Gioele Zardini.
Education
- Ph.D.: Harvard University, School of Engineering and Applied Sciences, Advisor: Prof. Na Li; B.S.: Peking University, Department of Mathematics, Scientific and Engineering Computing, Graduated in 2019.
Background
- Research Interests: Reinforcement learning, control theory, machine learning, multi-agent systems. Background: Dedicated to research on learning, control, and decision-making in multi-agent systems, aiming to design scalable, efficient, and provable learning/control algorithms that address challenges such as communication constraints, strategic behavior, and model uncertainty.
Miscellany
- Personal interests and hobbies not specifically mentioned.