Xiangfeng Wang
Papers
2
Total Citations
34
H-Index
2
About
Xiangfeng Wang is a leading researcher in reinforcement learning and optimization, with a focus on advancing multi-agent systems and structured decision-making under complex constraints. His major contributions include pioneering work on **structured cooperative reinforcement learning** with time-varying composite action spaces, addressing a critical gap in applying RL to real-world tasks where action spaces are dynamic and composed of multiple functional sub-actions. This research, published in 2021 and garnering 26 citations, extends RL beyond static, low-dimensional environments like games to practical domains such as robotics and autonomous systems. Wang also made notable strides in **computational geometry and collision detection**, developing methods to compute distances between convex sets with Minkowski sum structures—a key tool for safe navigation and manipulation in robotics, cited 8 times. His work bridges theoretical optimization and applied AI, offering scalable solutions for cooperative control and safety-critical systems. With a growing citation impact, Wang’s research is shaping the future of adaptive, real-time decision-making in complex environments, making him a vital figure for students and researchers exploring the intersection of RL, optimization, and multi-agent coordination.
Research Focus
Key Achievements
Top Papers
- 1
- 2