Tatsuya Mori

Papers

Total Citations

H-Index

About

Tatsuya Mori is a leading researcher in robust reinforcement learning, with a focus on developing decision-making systems that remain reliable under environmental uncertainty. His key contributions lie at the intersection of hierarchical reinforcement learning and risk-aware optimization, where he has pioneered methods for learning robust options—temporally extended actions—that can withstand model parameter inaccuracies. Notably, his 2019 work, "Learning Robust Options by Conditional Value at Risk Optimization," introduced a novel framework that moves beyond traditional worst-case or average-case approaches, instead leveraging conditional value at risk (CVaR) to balance performance and safety. This work, which has garnered 2 citations, addresses a critical gap in reinforcement learning: how to ensure that learned behaviors remain effective when the simulator or environment model is imperfect. Mori’s research has significant implications for real-world applications such as robotics and autonomous systems, where model uncertainty is inevitable. His work is widely recognized for bridging theoretical rigor with practical robustness, making him a key figure in advancing safe and reliable AI systems.