Ho-Bin Choi

About

Ho-Bin Choi is a leading researcher at the intersection of reinforcement learning, edge computing, and intelligent control systems. His most influential work, "Federated Reinforcement Learning for Controlling Multiple Rotary Inverted Pendulums in Edge Computing Environments" (2020, 22 citations), pioneered a novel framework that enables multiple reinforcement learning agents to collaboratively learn optimal control policies across distributed edge devices. This breakthrough addresses a critical challenge in real-world automation: how to train AI controllers for identical hardware (like robotic arms or pendulums) without centralizing sensitive data or requiring massive bandwidth. By demonstrating that agents can share learned knowledge while preserving device autonomy, Choi's research has significant implications for scalable, privacy-preserving industrial automation and smart manufacturing. His work bridges the gap between theoretical reinforcement learning and practical edge deployment, offering a blueprint for future systems where devices continuously improve through federated collaboration. Choi's contributions are particularly valuable for students and engineers seeking to implement distributed AI control in resource-constrained environments, as his approach reduces both computational overhead and communication costs while maintaining robust performance.

Research Focus

Key Achievements

Top Papers

1. 1
   Federated Reinforcement Learning for Controlling Multiple Rotary Inverted Pendulums in Edge Computing Environments

   22 citations · 2020

Key Collaborators

Contact & Links