Реферат: This work introduces a reinforcement learning algorithm designed for real-time luminosity optimization in collider experiments. The neural network architecture is selected from multiple candidates through systematic evaluation of their training performance. Prior to training, the input data undergo multistage preprocessing before being fed into the neural network. Our approach combines off-line pretraining on historical accelerator data with online fine-tuning during operation. By processing accelerator measurements over multisecond timescales, the reinforcement learning model dynamically adjusts the magnetic structure to maintain luminosity stability under changing beam conditions. The autonomous nature of the method eliminates the need for manual intervention, enhancing both operational efficiency and beam stability in long-term operation. Experimental validation on the VEPP-4M collider demonstrates the feasibility of the approach and provides a foundation for future development and deployment in accelerator systems.

Библиографическая ссылка: Mamutov R. , Baranov G. , Gerasev A.
Reinforcement Learning for Real-Time Luminosity Optimization in Colliders
Physical Review Accelerators and Beams. 2025. V.28. 122802 :1-16. DOI: 10.1103/71jq-vbl6 WOS Scopus РИНЦ OpenAlex СКИФ ID

Даты:

Поступила в редакцию:	29 авг. 2025 г.
Принята к публикации:	8 дек. 2025 г.
Опубликована online:	29 дек. 2025 г.

Идентификаторы БД:

Web of science:	WOS:001654855700001
Scopus:	2-s2.0-105026259743
РИНЦ:	88723781
OpenAlex:	W4417210033
СКИФ ID:	4241

Цитирование в БД:

БД	Цитирований
OpenAlex	Нет цитирований
Scopus	Нет цитирований

Альметрики: