Yingfeng Chen

NetEase (China)

Papers

3

Total Citations

41

H-Index

2

About

Yingfeng Chen is a leading researcher in artificial intelligence, specializing in multi-agent reinforcement learning and autonomous navigation systems. His most impactful contribution is the development of a value function transfer method for deep multi-agent reinforcement learning, which enables efficient knowledge reuse from single-agent systems to accelerate learning in sparse-interaction multi-agent environments—a breakthrough with applications in robot control and competitive games like soccer. This work, published in 2019, has garnered 34 citations, underscoring its significance in advancing scalable AI solutions. More recently, Chen has pioneered a closed-loop perception, decision-making, and reasoning mechanism for human-like navigation, addressing the limitations of traditional open-loop systems in dynamic real-world scenarios. This innovative framework, detailed in two 2022 papers with a combined 7 citations, integrates continuous feedback to enhance robustness in robotics and autonomous driving. Chen’s research bridges foundational theory and practical deployment, offering transformative tools for complex, interactive systems. His work stands out for its focus on real-world applicability, making him a key figure in the next generation of intelligent autonomous agents.

Research Focus

Key Achievements

2
H-Index
3
Papers
41
Total Citations
14
Avg Citations/Paper
🏆 Most Cited Paper
Value Function Transfer for Deep Multi-Agent Reinforcement Learning Based on N-Step Returns
34 citations · 2019
📈 Most Prolific Year: 2022 (2 Papers)
🤝 Key Collaborators: 15
🏛 Institutions: NetEase (China)

Top Papers

  1. 1
  2. 2
  3. 3

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago