Hyunbeen Park

About

Hyunbeen Park is a researcher advancing the intersection of reinforcement learning (RL) and robust control, with a primary focus on enhancing the reliability of autonomous systems in uncertain real-world environments. Their most notable contribution, the 2022 paper "Improved Robustness of Reinforcement Learning Based on Uncertainty and Disturbance Estimator," introduces a novel model-free uncertainty and disturbance estimator (UDE) that integrates seamlessly with RL frameworks. This work addresses a critical limitation of standard RL—its vulnerability to unpredictable disturbances and model inaccuracies—by enabling agents to adaptively compensate for environmental uncertainties without relying on precomputed optimal trajectories. While still early in its citation impact (2 citations), the paper represents a foundational step toward bridging RL theory and practical deployment in robotics and control systems. Park’s research is particularly valuable for students and engineers seeking to deploy RL in safety-critical applications, as it offers a computationally efficient method to improve robustness without sacrificing learning flexibility. By tackling the challenge of real-world uncertainty head-on, Park is contributing to the next generation of adaptive, disturbance-resilient intelligent systems.

Research Focus

Key Achievements

Top Papers

1. 1
   Improved Robustness of Reinforcement Learning Based on Uncertainty and Disturbance Estimator

   2 citations · 2022

Key Collaborators

Contact & Links