JACoW is a publisher in Geneva, Switzerland that publishes the proceedings of accelerator conferences held around the world by an international collaboration of editors.
TY - CONF AU - Kain, V. AU - Bruchon, N. AU - Hirlaender, S. AU - Madysa, N. AU - Skowroński, P.K. AU - Valentino, G. AU - Vojskovic, I. ED - Gianfelice, Eliana ED - Nagaitsev, Sergei ED - Kim, Dong Eon ED - Marx, Michaela ED - Schaa, Volker R. W. TI - Test of Machine Learning at the CERN LINAC4 J2 - Proc. of HB2021, Batavia, IL, USA, 04-08 October 2021 CY - Batavia, IL, USA T2 - ICFA Advanced Beam Dynamics Workshop on High-Intensity and High-Brightness Hadron Beams T3 - 64 LA - english AB - The CERN H⁻ linear accelerator, LINAC4, served as a test bed for advanced algorithms during the CERN Long Shutdown 2 in the years 2019/20. One of the main goals was to show that reinforcement learning with all its benefits can be used as a replacement for numerical optimization and as a complement to classical control in the accelerator control context. Many of the algorithms used were prepared beforehand at the electron line of the AWAKE facility to make the best use of the limited time available at LINAC4. An overview of the algorithms and concepts tested at LINAC4 and AWAKE will be given and the results discussed. PB - JACoW Publishing CP - Geneva, Switzerland SP - 181 EP - 185 KW - controls KW - linac KW - electron KW - target KW - network DA - 2024/03 PY - 2024 SN - 2673-5571 SN - 978-3-95450-225-7 DO - doi:10.18429/JACoW-HB2021-TUEC4 UR - https://jacow.org/hb2021/papers/tuec4.pdf ER -