Hirotaka Moriguch
Papers
1
Total Citations
4
H-Index
1
About
Hirotaka Moriguchi is a researcher in robotics and artificial intelligence, with a primary focus on reinforcement learning and neuroevolution. His work investigates how evolutionary algorithms can optimize artificial neural networks for continuous control tasks, particularly in quadruped locomotion. Moriguchi’s most cited paper, “Sample efficiency analysis of Neuroevolution algorithms on a quadruped robot” (2013), provides a critical comparison of neuroevolution methods, evaluating their ability to learn effective policies with limited interactions. This study has garnered 4 citations, establishing a foundation for understanding the trade-offs between exploration and convergence in policy search. His contributions address the challenge of sample efficiency—a key bottleneck in applying reinforcement learning to physical robots. By analyzing algorithm performance on a quadruped platform, Moriguchi has helped advance the practical deployment of neuroevolution in real-world robotics. His work is particularly valuable for students and researchers seeking to bridge the gap between simulation and hardware, offering insights into how evolutionary strategies can be tailored for sample-constrained environments.
Research Focus
Key Achievements
Top Papers
- 1