R&D of the KEK Linac accelerator tuning based on reinforcement study

We have developed a machine-learning-based operation tuning scheme for the KEK e^-/e⁺ injector linac (Linac), to improve the injection efficiency. The tuning scheme is based on the various accelerator operation data (control parameters, monitoring data and environmental data) of Linac. For the studies, we use the accumulated Linac operation data. In this paper, we show 1) the study of the long-term correlation between the accelerator operation parameters and the environmental data, and 2) the preparation study of the environment-driven machine learning (reinforcement learning) based on the short-term correlation between the accelerator operation parameters and the environmental data to improve the injection efficiency. (author)