Jin Hyunk Lee
Papers
1
Total Citations
4
H-Index
1
About
Jin Hyunk Lee is a roboticist whose research focuses on reinforcement learning for dexterous manipulation, with a particular emphasis on enabling anthropomorphic robotic hands to perform natural, human-like object interactions. His most cited work tackles the fundamental challenge of reward engineering in RL, proposing a reward shaping method that leverages hand pose priors to guide on-policy learning. This approach allows robots to learn stable, reliable manipulation behaviors without requiring task-specific reward functions, addressing a critical bottleneck in robotic learning. While his citation count is still growing—a reflection of his early-career stage—his contributions are notable for their practical impact on making RL-based manipulation more accessible and robust. Lee’s work sits at the intersection of robotics, machine learning, and biomechanics, offering a pathway toward more intuitive and adaptive robotic hands. His research is particularly relevant for students and researchers interested in bridging the gap between simulated training and real-world robotic control.
Research Focus
Key Achievements
Top Papers
- 1