Ryuta Tonomura

About

Ryuta Tonomura is a researcher whose work lies at the intersection of reinforcement learning, robotics, and adaptive state-space modeling. His primary contributions focus on addressing the critical challenge of applying reinforcement learning to real-world environments, where continuous sensory information must be effectively discretized. In his most cited work, "Reinforcement Learning Based on State Space Model using Growing Neural Gas for a Mobile Robot" (2018), Tonomura proposed a novel method for constructing state spaces using Growing Neural Gas (GNG). This approach enables mobile robots to autonomously learn and adapt their internal representations of complex, continuous environments, significantly improving the efficiency and applicability of reinforcement learning in physical tasks. While his citation count is still growing, this work demonstrates his early impact in bridging neural network-based state modeling with robotic control. Tonomura’s research is particularly valuable for students and engineers seeking to deploy reinforcement learning in unstructured, real-world settings, offering a practical pathway from theoretical algorithms to embodied robotic systems.

Research Focus

Key Achievements

Top Papers

1. 1
   Reinforcement Learning Based on State Space Model using Growing Neural Gas for a Mobile Robot

   2 citations · 2018

Key Collaborators

Contact & Links