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 (EECS) from UC Berkeley in 2025, where I was advised by Prof. Claire Tomlin and Prof. Somayeh Sojoudi.

Research interests:  

As autonomous systems scale to decentralized multi-agent settings, agents must operate under limited and asymmetric information about one another. This raises fundamental questions about how agents should reason, learn, and act strategically across both cooperative and non-cooperative interactions, where richer behaviors and challenges emerge.

My research addresses these questions through the lenses of dynamic game theory, control, and reinforcement learning. Broadly, I study multi-agent decision-making under uncertainty, with a focus on differentiable games (whose equilibria are differentiable with respect to game parameters), information structure, learning, and safety, as well as the computational methods that enable these systems to scale in practice. My work is motivated by applications in autonomous driving, advanced air mobility, multi-robot coordination, and infrastructure-scale autonomy.

Current directions:

1. Computational Dynamic Game Theory: Optimization and learning-based approaches for strategic decision-making, leveraging differentiable structure and principled approximations for efficient computation of equilibria;

2. From Aligning to 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 align 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 validation.