Yusuke Kon
Papers
1
Total Citations
4
H-Index
1
About
Yusuke Kon is a researcher in developmental robotics and cognitive systems, with a focus on how robots can autonomously learn to categorize objects through active exploration. His key research areas include reinforcement learning, object categorization, and behavior-based learning in artificial agents. Kon’s major contribution is the introduction of Discernment Behavior Reinforcement Learning, a framework that enables robots to learn effective observation behaviors by using categorization progress as an intrinsic reward signal. This approach addresses a fundamental challenge: robots must decide not only what to observe, but how to observe—through multiple behaviors—to build accurate object categories. His most cited work, "Effective reward function in discernment behavior reinforcement learning based on categorization progress" (2016), has garnered 4 citations and lays the groundwork for more adaptive and autonomous learning in robotic systems. By shifting the focus from passive perception to active, goal-driven exploration, Kon’s research offers a principled way for robots to develop richer understandings of their environment. His work is particularly relevant for students and researchers interested in bridging reinforcement learning, cognitive development, and autonomous robotics.
Research Focus
Key Achievements
Top Papers
- 1