Yongan Zhang
Papers
1
Total Citations
3
H-Index
1
About
Yongan Zhang is a researcher at the forefront of efficient deep reinforcement learning (DRL) and neural architecture search (NAS), with a focus on bridging the gap between high-performance AI and real-world deployment constraints. His most cited work, "Auto-Agent-Distiller: Towards Efficient Deep Reinforcement Learning Agents via Neural Architecture Search" (2020), addresses a critical challenge in DRL: the computational complexity that limits its use in resource-constrained applications like intelligent robotics and real-time control. By pioneering automated methods to distill powerful yet compact agents, Zhang’s research enables DRL models to achieve competitive performance while dramatically reducing their inference cost and memory footprint. This contribution has garnered 3 citations, reflecting its relevance to the growing demand for deployable AI. Zhang’s work stands out for its practical impact, offering a systematic approach to designing lightweight neural architectures without sacrificing the decision-making capabilities that made AlphaGo a milestone. His research is particularly valuable for students and engineers seeking to implement DRL in edge devices or autonomous systems, where efficiency is paramount.
Research Focus
Key Achievements
Top Papers
- 1