Yueying Li
Papers
2
Total Citations
8
H-Index
2
About
Yueying Li is a researcher whose work spans two distinct yet intellectually rich domains: stochastic systems theory and reinforcement learning. In the area of stochastic differential equations, Li has made notable contributions to understanding synchronization phenomena in complex networked systems, particularly multi-links systems subjected to Lévy noise — a challenging class of stochastic disturbances characterized by jump discontinuities. Their 2020 work introduced a novel Lyapunov functional framework and leveraged feedback discrete-time observations control to rigorously address synchronization, advancing a problem that had previously remained underexplored. On the machine learning front, Li's 2022 research tackled a fundamental bottleneck in planning-based reinforcement learning: the computational inefficiency and scalability challenges that arise in high-dimensional action spaces. By proposing planning within a compact latent action space, Li offered a principled approach to making such methods more practically viable. Together, these contributions — accumulating citations across both fields — reflect a researcher comfortable bridging rigorous mathematical analysis with modern artificial intelligence challenges. Li's portfolio signals a promising trajectory for scholars interested in control theory, stochastic modeling, and intelligent decision-making systems.
Research Focus
Key Achievements
Top Papers
- 1Synchronization of multi-links systems with Lévy noise and application5 citations · 2020
- 2Efficient Planning in a Compact Latent Action Space3 citations · 2022