Jehyun Park

About

Jehyun Park is a researcher at the intersection of reinforcement learning, robotics, and virtual reality (VR), with a focus on developing intelligent systems that operate reliably under real-world uncertainty. His most cited work, "Distributional and hierarchical reinforcement learning for physical systems with noisy state observations and exogenous perturbations" (2023, 10 citations), addresses a critical challenge in robotics: how to train agents that remain robust when sensors are noisy and environments are unpredictable. By combining distributional and hierarchical RL, Park’s approach enables physical systems to make safer, more adaptive decisions—a key step toward deploying autonomous robots in dynamic, human-centric settings. In earlier work, Park tackled the practical problem of customer guidance in VR simulators, proposing a "Customer-Specific Robotic Attendant" (2020, 7 citations) that automates complex, repetitive instructions to maintain high service quality. He has also contributed to online learning with "Multi-output Infinite Horizon Gaussian Processes" (2021), advancing methods for real-time prediction from noisy sensory streams. With a growing citation record and a focus on bridging theory and application, Park is shaping how robots learn and interact in noisy, real-world environments.

Research Focus

Key Achievements

Top Papers

1. 1
   Distributional and hierarchical reinforcement learning for physical systems with noisy state observations and exogenous perturbations

   10 citations · 2023
2. 2
   Customer-Specific Robotic Attendant for VR Simulators

   7 citations · 2020
3. 3
   Multi-output Infinite Horizon Gaussian Processes

   2 citations · 2021

Key Collaborators

Contact & Links