Wataru Hatanaka
Papers
1
Total Citations
3
H-Index
1
About
Wataru Hatanaka is a leading researcher in the intersection of reinforcement learning, formal methods, and robotics, with a focus on enabling autonomous systems to operate reliably under uncertainty. His major contributions center on integrating linear temporal logic (LTL) specifications into RL frameworks, allowing robots to follow complex, temporally extended instructions even when event detectors are imperfect. In his highly cited 2023 work, "Reinforcement Learning of Action and Query Policies With LTL Instructions Under Uncertain Event Detector," Hatanaka pioneers a dual-policy approach that simultaneously learns action and query strategies, addressing a critical gap in prior methods that assumed perfect symbolic perception. This work has garnered 3 citations in a short time, reflecting its timely impact on the field. Beyond this, Hatanaka’s research advances the robustness of robot decision-making in partially observable environments, bridging theoretical guarantees with practical deployment. His achievements include developing frameworks that enable robots to actively query their environment to resolve ambiguity, a key step toward trustworthy autonomous systems. For students and researchers, Hatanaka’s work offers a compelling blueprint for combining formal verification with learning in uncertain, real-world settings.
Research Focus
Key Achievements
Top Papers
- 1