Journals of Accelerator Conferences Website (JACoW)

JACoW is a publisher in Geneva, Switzerland that publishes the proceedings of accelator conferences held around the world by an international collaboration of editors.

URLhttps://doi.org/10.18429/JACoW-IPAC2023-THPL038
TitleUltra fast reinforcement learning demonstrated at CERN AWAKE
Authors
  • S. Hirlaender, L. Lamminger
    University of Salzburg
  • G. Zevi Della Porta, V. Kain
    CERN
AbstractReinforcement learning (RL) is a promising direction in machine learning for the control and optimisation of particle accelerators since it learns directly from experience without needing a model a-priori. However, RL generally suffers from low sample efficiency and thus training from scracth on the machine is often not an option. RL agents are usually trained or pre-tuned on simulators and then transferred to the real environment. In this work we propose a model-based RL approach based on Gaussian processes (GPs) to overcome the sample efficiency limitation. Our RL agent was able to learn to control the trajectory at the CERN AWAKE (Advanced Wakefield Experiment) facility, a problem of 10 degrees of freedom, within a few interactions only. To date, numerical optimises are used to restore or increase and stabilise the performance of accelerators. A major drawback is that they must explore the optimisation space each time they are applied. Our RL approach learns as quickly as numerical optimisers for one optimisation run, but can be used afterwards as single-shot or few-shot controllers. Furthermore, it can also handle safety and time-varying systems and can be used for the online stabilisation of accelerator operation.This approach opens a new avenue for the application of RL in accelerator control and brings it into the realm of everyday applications.
Paperdownload: THPL038.pdf
CiteBibTeX, LaTeX, Text/Word, RIS, EndNote
Conference14th International Particle Accelerator Conference
Series
LocationVenice, Italy
Date07-12 May 2023
PublisherJACoW Publishing, Geneva, Switzerland
Editorial BoardRalph Assmann - Deutsches Elektronen-Synchrotron DESY Peter McIntosh - Science and Technology Facilities Council (STFC/DL/ASTeC) Giovanni Bisoffi - Istituto Nazionale di Fisica Nucleare (INFN/LNL) Alessandro Fabris - Elettra-Sincrotrone Trieste S.C.p.A. Ivan Andrian - Elettra-Sincrotrone Trieste S.C.p.A. Giulia Vinicola - Istituto Nazionale di Fisica Nucleare (INFN/LNF)
Online ISBN978-3-95450-231-8
Online ISSN2673-5490
Received03 May 2023
Revised23 June 2023
Accepted23 June 2023
Issued26 September 2023
DOI10.18429/JACoW-IPAC2023-THPL038
Pages4510-4513