Mariko URAKAWA
Papers
1
Total Citations
8
H-Index
1
About
Mariko Urakawa is a pioneering researcher in the field of robotic motion acquisition and reinforcement learning, with a focus on adaptive reward systems. Her most-cited work, "Advance Motion Acquisition of an Actual Robot by Reinforcement Learning using Reward Change" (2006, 8 citations), introduces a novel approach to Q-Learning by dynamically adjusting rewards based on performance improvement—mirroring human training processes. This contribution challenges traditional fixed-reward paradigms, offering a more flexible and efficient method for teaching robots complex motions. Urakawa’s research bridges the gap between artificial intelligence and human learning psychology, demonstrating how reward adaptation can accelerate skill acquisition in real-world robotic systems. Her work has influenced subsequent studies in adaptive robotics and machine learning, particularly in environments requiring incremental progress. By exploring how reward changes impact learning outcomes, Urakawa provides a foundation for more intuitive and responsive AI training methods. Her achievements underscore the importance of interdisciplinary thinking, combining robotics, cognitive science, and reinforcement learning to advance autonomous systems. For students and researchers, her work offers a compelling example of how human-inspired mechanisms can enhance machine learning efficiency and adaptability.
Research Focus
Key Achievements
Top Papers
- 1