Gyu-Young Hwang
Papers
1
Total Citations
22
H-Index
1
About
Gyu-Young Hwang is a researcher at the forefront of edge computing and intelligent control systems, specializing in federated reinforcement learning and its application to real-world devices. His most cited work, "Federated Reinforcement Learning for Controlling Multiple Rotary Inverted Pendulums in Edge Computing Environments" (2020, 22 citations), introduces a novel framework that enables multiple reinforcement learning agents to collaboratively learn optimal control policies across distributed edge devices. This approach addresses the challenge of training autonomous systems—such as robotic arms or pendulums—that share similar dynamics but operate under slightly different conditions, without centralizing sensitive data. Hwang’s contributions lie in bridging the gap between theoretical reinforcement learning and practical deployment, demonstrating how federated learning can scale control tasks while preserving device autonomy and privacy. His work has significant implications for robotics, industrial automation, and IoT networks, where efficient, decentralized decision-making is critical. By tackling the complexities of real-time control in edge environments, Hwang is helping to shape the next generation of adaptive, distributed intelligent systems.
Research Focus
Key Achievements
Top Papers
- 1