Papers

2

Total Citations

11

H-Index

2

About

Jonghyeok Park is a rising force in the field of robot learning, whose research focuses on advancing reinforcement learning (RL) algorithms to make autonomous systems more stable, efficient, and capable. His work addresses two critical challenges in modern RL: improving how robots learn from complex, multimodal sensory data and ensuring training stability in the face of intermittent environmental perturbations. In his highly cited 2023 paper, Park introduced a multimodal advantage function that enables more accurate advantage estimation, allowing robots to better evaluate the long-term consequences of their actions—a key step toward more intelligent and adaptable robotic behavior. This contribution has already garnered 9 citations, signaling its early impact on the community. More recently, in 2025, he tackled the persistent problem of training instability by developing a method that preserves gradient norms, ensuring that learning remains robust even when faced with sudden changes or noisy feedback. Park’s work is particularly notable for its practical orientation, directly addressing real-world deployment challenges where robots must operate reliably in unpredictable environments. As his research continues to mature, Jonghyeok Park is establishing himself as a thoughtful innovator at the intersection of reinforcement learning and robotics.

Research Focus

Key Achievements

2
H-Index
2
Papers
11
Total Citations
6
Avg Citations/Paper
🏆 Most Cited Paper
Reinforcement learning with multimodal advantage function for accurate advantage estimation in robot learning
9 citations · 2023
📈 Most Prolific Year: 2023 (1 Papers)
🤝 Key Collaborators: 3
🏛 Institutions: Pohang University of Science and Technology, Pusan National University

Top Papers

  1. 1
  2. 2

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 14 days ago