Gunam Kwon
Papers
1
Total Citations
6
H-Index
1
About
Gunam Kwon is a rising researcher in robotics and reinforcement learning, with a focus on advancing autonomous manipulation for robotic systems. His work centers on task decomposition and reward-system design to enable complex, high-level robotic behaviors, particularly in pick-and-place operations—a cornerstone of industrial and service robotics. In his most-cited paper, "The Task Decomposition and Dedicated Reward-System-Based Reinforcement Learning Algorithm for Pick-and-Place" (2023, 6 citations), Kwon introduces a novel algorithm that breaks down the pick-and-place task into three subtasks: two reaching motions and one grasping action. By assigning dedicated rewards to each subtask, his method significantly improves learning efficiency and task success rates compared to traditional monolithic approaches. This contribution addresses a critical challenge in robot learning—how to handle long-horizon tasks with sparse rewards—and offers a scalable framework for real-world applications. Though early in his career, Kwon’s work has already garnered attention for its practical impact, demonstrating how structured reinforcement learning can bridge the gap between simulation and physical robotic deployment. His research holds promise for advancing automation in manufacturing, logistics, and assistive technologies.
Research Focus
Key Achievements
Top Papers
- 1