% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@ARTICLE{Awal:358549,
      author       = {Awal, Awal Abdulhasan Hasan Ali and Hetzel, Jan Henry and
                      Gebel, Ralf Heinz and Pretz, Jörg},
      title        = {{I}njection optimization at particle accelerators via
                      reinforcement learning: {F}rom simulation to real-world
                      application},
      journal      = {Physical review accelerators and beams},
      volume       = {28},
      number       = {3},
      issn         = {2469-9888},
      address      = {College Park, MD},
      publisher    = {American Physical Society},
      reportid     = {GSI-2025-00601},
      pages        = {034601},
      year         = {2025},
      note         = {"Published by the American Physical Society under the terms
                      of the Creative Commons Attribution 4.0 International
                      license. Further distribution of this work must maintain
                      attribution to the author(s) and the published article’s
                      title, journal citation, and DOI."},
      abstract     = {Optimizing the injection process in particle accelerators
                      is crucial for enhancing beam quality and operational
                      efficiency. This paper presents a framework for utilizing
                      reinforcement learning (RL) to optimize the injection
                      process at accelerator facilities. By framing the
                      optimization challenge as an RL problem, we developed an
                      agent capable of dynamically aligning the beam’s
                      transverse space with desired targets. Our methodology
                      leverages the soft actor-critic algorithm, enhanced with
                      domain randomization and dense neural networks, to train the
                      agent in simulated environments with varying dynamics
                      promoting it to learn a generalized robust policy. The agent
                      was evaluated in live runs at the cooler synchrotron COSY
                      and it has successfully optimized the beam cross section
                      reaching human operator level but in notably less time. An
                      empirical study further validated the importance of each
                      architecture component in achieving a robust and generalized
                      optimization strategy. The results demonstrate the potential
                      of RL in automating and improving optimization tasks at
                      particle acceleration facilities.},
      cin          = {HES},
      ddc          = {530},
      cid          = {I:(DE-Ds200)HES-20160901OR377},
      pnm          = {621 - Accelerator Research and Development (POF4-621) /
                      6G12 - FAIR (GSI) (POF4-6G12)},
      pid          = {G:(DE-HGF)POF4-621 / G:(DE-HGF)POF4-6G12},
      experiment   = {$EXP:(DE-Ds200)External_experiment-20200803$},
      typ          = {PUB:(DE-HGF)16},
      UT           = {WOS:001447589700004},
      doi          = {10.1103/PhysRevAccelBeams.28.034601},
      url          = {https://repository.gsi.de/record/358549},
}