Tetsuro Morimura

About

Tetsuro Morimura is a leading researcher in reinforcement learning, with a focus on developing robust and reliable algorithms for real-world applications, particularly in robotics. His major contributions center on addressing the vulnerability of conventional least-squares policy iteration methods to outliers in reward signals. In his seminal 2009 paper, "Least absolute policy iteration for robust value function approximation," and its 2010 follow-up, Morimura introduced a novel framework that replaces the squared loss with an absolute loss function. This deceptively simple shift dramatically enhances the robustness of value function approximation, ensuring stable learning even in noisy or unpredictable environments. While each of these foundational papers has garnered modest citation counts of 5 and 6, respectively, their influence is deeply felt in the robotics community, where reliable performance under real-world uncertainty is paramount. Morimura’s work represents a critical step toward bridging the gap between theoretical reinforcement learning and practical deployment, offering a principled solution to a persistent challenge in autonomous systems. His research continues to inspire safer, more resilient machine learning.

Research Focus

Key Achievements

Top Papers

1. 1
   Least absolute policy iteration for robust value function approximation

   6 citations · 2009
2. 2
   Least Absolute Policy Iteration-A Robust Approach to Value Function Approximation

   5 citations · 2010

Key Collaborators

Contact & Links