Mengguang Li
Papers
2
Total Citations
16
H-Index
2
About
Mengguang Li is an emerging researcher specializing in multi-agent reinforcement learning, large-population systems, and robotic swarm control. Their work sits at the intersection of control theory and machine learning, tackling one of the field's most formidable challenges: scaling intelligent decision-making to systems with vast numbers of interacting agents. Li's most notable contributions include pioneering work on task-driven robotic swarm control, where they developed scalable algorithms combining collision avoidance with mean-field control theory — a mathematically elegant framework for approximating the collective behavior of large agent populations. This research directly addresses the computational intractability that plagues traditional multi-agent approaches as system size grows. Complementing this, their comprehensive survey on large-population systems and scalable multi-agent reinforcement learning has served as a valuable synthesis of the field, bridging diverse application domains including epidemiology, economics, and autonomous robotics. Both papers have garnered 8 citations each, reflecting growing recognition within the research community. For students and practitioners working on swarm robotics, autonomous systems, or distributed AI, Li's work offers both theoretical grounding and practical algorithmic insights into one of modern AI's most complex open problems.
Research Focus
Key Achievements
Top Papers
- 1
- 2