Russian researchers create RLABC AI program for tuning particle accelerators
Researchers at HSE University and the Budker Institute of Nuclear Physics of the Siberian Branch of the Russian Academy of Sciences have developed the RLABC program, which uses reinforcement learning to select accelerator magnet settings. In a computer experiment on a channel model based on the VEPP-5 injection complex, about 66–71% of particles reached the end of the transport channel. The work has been published in the journal Computer Physics Communications, and the code is open.
Aziz Karimov