Yanfang Fu
Papers
1
Total Citations
2
H-Index
1
About
Yanfang Fu is a researcher advancing the frontier of cooperative multi-agent reinforcement learning (MARL), with a focus on developing scalable frameworks for complex, real-world coordination problems. In their highly cited 2025 work, "A Coordination Optimization Framework for Multi-Agent Reinforcement Learning Based on Reward Redistribution and Experience Reutilization," Fu introduces a novel approach that addresses two persistent challenges in MARL: sparse rewards and inefficient sample usage. By redesigning how agents share and reinterpret reward signals and reusing past experiences more effectively, this framework significantly improves learning efficiency and coordination in domains such as autonomous robot control, strategic decision-making, and decentralized unmanned swarm systems. Though early in its trajectory, the paper has already garnered 2 citations, signaling growing recognition of its practical impact. Fu’s contributions are particularly notable for bridging theoretical optimization with deployable multi-agent solutions, offering a pathway to more robust and adaptive collective intelligence. Their work stands as a valuable resource for students and researchers seeking to understand how reward structures and experience replay can be reimagined to unlock the full potential of cooperative MARL in dynamic, real-world environments.
Research Focus
Key Achievements
Top Papers
- 1