T. HIRAOKA

About

T. Hiraoka is a researcher whose work lies at the intersection of reinforcement learning and robust decision-making under uncertainty. Their primary research focus is on developing algorithms that enable agents to learn reliable, high-level behaviors—known as options—even when the environment model is imperfect or uncertain. Hiraoka’s most notable contribution is the introduction of a novel framework that leverages Conditional Value at Risk (CVaR) optimization to learn robust options. This approach moves beyond traditional methods that consider only worst-case or average-case scenarios, offering a more balanced and principled way to handle model parameter uncertainty. The work, published in 2019, has garnered attention in the reinforcement learning community and provides a foundation for building safer and more dependable autonomous systems. Hiraoka’s research is particularly relevant for applications where simulators are inaccurate, such as robotics and autonomous navigation, and their contributions are helping to bridge the gap between theoretical robustness and practical deployment.

Research Focus

Key Achievements

Top Papers

1. 1
   Learning Robust Options by Conditional Value at Risk Optimization

   2 citations · 2019

Key Collaborators

Contact & Links