Shangtong Zhang

Shangtong Zhang is an Alf Weaver Assistant Professor in the Department of Computer Science at the University of Virginia, directing the Sequential Intelligence Lab (SIL). His research specializes in theoretical and empirical aspects of reinforcement learning, with publications in premier AI venues. He serves as Area Chair for top conferences and on NSF panels.

Research interests focus on:

• Reinforcement learning theory
• Deep learning applications
• Algorithmic improvements for stability
• Multi-agent collaboration
• Ethical AI frameworks

Publications demonstrate consistent focus on reinforcement learning advancements, covering theoretical convergence proofs, safety constraints, fairness metrics, and efficient evaluation methods. Recent work emphasizes trustworthy AI, multi-agent coordination, and algorithmic robustness.

Awards include:

• Best paper awards (ICML & AAMAS)
• AAAI New Faculty Highlights
• Rising Star in AI (KAUST)
• IFAAMAS Dissertation Award

Leads the SIL lab with multiple funded projects including NSF CRASH. Supervises PhD students in reinforcement learning meetups and lab research. Education includes DPhil from Oxford, MSc from Alberta, and BSc from Fudan University.