Jingqi Li

I'm a Peter O' Donnell Jr. Postdoctoral Fellow at UT Austin, where I work with Professor David Fridovich-Keil on game-theoretic control and learning. I earned my Ph.D. in Electrical Engineering and Computer Sciences from UC Berkeley in 2025, advised by Professor Claire Tomlin and Professor Somayeh Sojoudi.

Research interests

My research develops theoretical and algorithmic solutions for safe, strategic multi-agent autonomy. Drawing on dynamic games, control theory, and reinforcement learning, I study how agents reason about one another under uncertainty to achieve decentralized coordination with performance and safety guarantees. Much of my research is motivated by applications in autonomous driving, drone racing, air mobility, and multi-robot manipulation.
Current directions:

1. Game-Theoretic Control and Learning: Developing efficient mathematical programming, reinforcement learning, and hybrid approaches to enable safe, strategic decision-making;

2. From Aligning to Exploiting Information Asymmetry: In practice, agents often act with partial knowledge of their environment. Agents' uneven access to knowledge—information asymmetry—can disrupt coordination and cascade into failures. Rather than always seeking to eliminate such asymmetry, I study how structured information asymmetry can instead shape strategic interaction and be harnessed to steer coordination outcomes;

3. Towards Decentralized, Strategic Autonomy: My long-term goal is to build a unified theory and architecture for decentralized autonomy, where agents reason, learn, and coordinate through local interaction, achieving system-level performance beyond centralized autonomy.