Koichi Hashiguchi

About

Koichi Hashiguchi is a researcher in robotics and machine learning, with a primary focus on enabling humanoid robots to learn and autonomously generate complex, multi-step action sequences. His key research areas include recurrent neural networks with parametric bias (RNNPB), reinforcement learning, and robot behavior generation. Hashiguchi’s major contribution lies in developing a framework that allows a humanoid robot to first learn primitive behaviors—such as walking or grasping—through RNNPB, and then automatically combine and sequence these actions using reinforcement learning. This approach bridges the gap between low-level motor control and high-level task planning, enabling robots to adapt to new situations without explicit programming. While his most-cited work, "Multiple Action Sequence Learning and Automatic Generation for a Humanoid Robot Using RNNPB and Reinforcement Learning" (2012), has garnered 2 citations, it represents an important step toward more flexible and intelligent robotic systems. Hashiguchi’s work is particularly notable for integrating neural network-based learning with reinforcement learning, offering a pathway for robots to acquire and refine complex behaviors autonomously. His research continues to influence the fields of developmental robotics and autonomous learning systems.

Research Focus

Key Achievements

Top Papers

1. 1
   Multiple Action Sequence Learning and Automatic Generation for a Humanoid Robot Using RNNPB and Reinforcement Learning

   2 citations · 2012

Key Collaborators

Contact & Links