Terushi Hirabayashi

Papers

Total Citations

H-Index

About

Terushi Hirabayashi specializes in Bayesian optimization and policy search for complex industrial systems, with a particular focus on waste incineration plants. His pioneering work addresses the challenge of controlling large-scale machinery in weakly observable environments, where sensor data is limited and environmental conditions are highly variable. His most cited paper, "Bayesian Policy Optimization for Waste Crane With Garbage Inhomogeneity" (2020, 10 citations), introduces a framework that enables waste cranes to autonomously optimize their control policies through trial and error, despite the massive, slow-moving nature of the equipment and the inhomogeneity of waste. This work has significant implications for improving efficiency in waste-to-energy processes. Hirabayashi further advanced the field with "Gaussian Process Self-triggered Policy Search in Weakly Observable Environments" (2022, 2 citations), which tackles the challenge of decision-making when environmental state information is scarce due to technical or cost constraints. His research bridges the gap between theoretical Bayesian methods and practical industrial automation, offering scalable solutions for real-world systems with limited sensing capabilities.