Jingqi Li

Hello! I'm Jingqi Li, a Peter O'Donnell Jr. Postdoctoral Fellow at the Oden Institute for Computational Engineering and Sciences, UT Austin. I work with Prof. David Fridovich-Keil on game-theoretic control and learning. I received my Ph.D. in Electrical Engineering and Computer Sciences from UC Berkeley in 2025, where I was advised by Prof. Claire Tomlin and Prof. Somayeh Sojoudi, and was a member of Berkeley AI Research (BAIR) Lab.

Research interests:  

As autonomous systems scale to decentralized multi-agent settings, strategic interaction under information asymmetry becomes unavoidable. Yet principled computational foundations remain lacking.

I develop theoretical and algorithmic solutions for decentralized strategic autonomy, enabling agents to make provably safe and strategic decisions using only local information. I work at the intersection of dynamic games, control theory, and reinforcement learning, with applications in autonomous driving, air mobility, multi-robot coordination, and infrastructure-scale autonomy.
Current directions:

1. Computational Dynamic Game Theory: Developing optimization and learning-based methods for strategic decision-making, leveraging differentiable structure and principled approximations to efficiently compute strategic decisions;

2. Exploiting Information Asymmetry: In practice, agents' uneven access to knowledge about their environment—information asymmetry—can disrupt coordination and lead to 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. Decentralized Strategic Autonomy: Developing a unified theory and architecture for decentralized strategic autonomy, enabling agents to make decisions, learn, and coordinate under limited information, with real-world hardware validation.