Jong-Chan Park
Papers
1
Total Citations
2
H-Index
1
About
Dr. Jong-Chan Park is a rising researcher in artificial intelligence, specializing in hierarchical reinforcement learning (HRL) for complex, long-horizon tasks. His most-cited work introduces a **novelty-aware graph traversal and expansion framework** that addresses the critical challenge of sparse rewards in HRL. By enabling high-level policies to generate adaptive subgoals through structured graph exploration, Park’s approach significantly improves sample efficiency and goal achievement in environments where traditional methods fail. His research bridges the gap between high-level planning and low-level control, offering a scalable solution for robotics and autonomous systems. With 2 citations on his seminal 2024 paper, Park’s contributions are gaining traction for their practical impact on real-world decision-making problems. His work stands out for its innovative integration of novelty detection with hierarchical structures, paving the way for more robust and autonomous learning agents. As an emerging voice in AI, Park’s research promises to advance the frontier of reinforcement learning in sparse-reward settings.
Research Focus
Key Achievements
Top Papers
- 1