Fandi Gou
Papers
1
Total Citations
2
H-Index
1
About
Fandi Gou is a rising researcher in multi-agent systems and reinforcement learning, with a focus on autonomous control in complex, obstacle-rich environments. His work addresses the challenging problem of multi-agent encirclement control, where multiple agents must coordinate to surround a mobile target while simultaneously avoiding collisions with obstacles—a delicate balance that has long eluded traditional approaches. Gou’s most-cited paper, “A Policy-Guided Reinforcement Learning Method for Encirclement Control in Multiobstacle Environment” (2025), introduces a novel framework that leverages policy guidance to dynamically optimize this tradeoff, achieving robust performance in high-density obstacle settings. Though early in his career, with this work garnering 2 citations, Gou’s contribution is notable for its practical implications in robotics, surveillance, and autonomous swarms. His research bridges theoretical reinforcement learning with real-world constraints, offering a scalable solution for decentralized multi-agent coordination. As a young scholar, Gou’s innovative approach to integrating obstacle avoidance with encirclement tasks marks him as a promising voice in the field, with potential for significant impact as his methods are adopted and extended.
Research Focus
Key Achievements
Top Papers
- 1