Youn‐Hee Han
Papers
3
Total Citations
51
H-Index
3
About
Youn-Hee Han is a leading researcher in the intersection of reinforcement learning (RL), edge computing, and automated control systems. Her work focuses on solving the critical challenge of applying RL to real-world environments, particularly for controlling multiple devices in smart factories, robotics, and IoT ecosystems. Han’s major contribution lies in pioneering **federated reinforcement learning** frameworks that enable multiple agents to collaboratively learn optimal control policies across distributed edge devices—without sharing raw data. Her most influential paper, “Federated Reinforcement Learning Acceleration Method for Precise Control of Multiple Devices” (2021, 25 citations), introduces techniques to overcome the reality gap between simulation and physical deployment. Another key work (2020, 22 citations) demonstrates this approach on rotary inverted pendulums, showing how agents with slightly different hardware can still converge on robust control strategies. Her research has direct implications for Software-Defined Networking (SDN)-based IoT environments, where automatic, human-free control is essential. With over 50 total citations across her core publications, Han is establishing herself as a vital voice in making RL practical for distributed, real-world automation—a critical step toward scalable smart manufacturing and autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3