conference proceedings

Reinforcement learning loop for the ARES experimental area.

Learning-based Optimisation of Particle Accelerators Under Partial Observability Without Real-World Training

J. Kaiser, O. Stein, A. Eichler Deutsches Elektronen-Synchrotron DESY 39th International Conference on Machine Learning Abstract In recent work, it has been shown that reinforcement learning (RL) is capable of solving a variety of problems at sometimes super-human performance levels. But despite continued advances in the field, applying RL to complex real-world control and optimisation problems has proven difficult. In this contribution, we demonstrate how to successfully apply RL to the optimisation of a highly complex real-world machine – specifically a linear particle accelerator – in an only partially observable setting and without requiring training on the real machine....

Success rate of the various algorithms over initial beam intensity.

Automated Intensity Optimisation Using Reinforcement Learning at LEIR

N. Madysa, V. Kain, R. Alemany Fernandez, N. Biancacci, B. Goddard, F. M. Velotti CERN 13th Particle Accelerator Conference Abstract High intensities in the Low Energy Ion Ring (LEIR) at CERN are achieved by stacking several multi-turn injec- tions from the pre-accelerator Linac3. Up to seven consec- utive 200 μs long, 200 ms spaced pulses are injected from Linac3 into LEIR. Two inclined septa, one magnetic and one electrostatic, combined with a collapsing horizontal or- bit bump allows a 6-D phase space painting via a linearly ramped mean momentum along the Linac3 pulse and in- jection at high dispersion....

Online training of NAF Agent of AWAKE electronline trajectory steering in the horizontal plane.

Test of Machine Learning at the CERN LINAC4

V. Kain1, N. Bruchon1, S. Hirlander1, N. Madysa1, I. Vojskovic1, P. Skowronski1, G. Valentino2 1CERN, 2University of Malta 61st ICFA ABDW on High-Intensity and High-Brightness Hadron Beams Abstract The CERN H−linear accelerator, LINAC4, served as atest bed for advanced algorithms during the CERN LongShutdown 2 in the years 2019/20. One of the main goals wasto show that reinforcement learning with all its benefits canbe used as a replacement for numerical optimization and asa complement to classical control in the accelerator controlcontext....

RL environment for beam optimisation in theARES EA.

First Steps Toward an Autonomous Accelerator, A Common Project Between DESY and KIT

A. Eichler1, F. Burkart1, J. Kaiser1, W. Kuropka1, O. Stein1, E. Bründermann2, A. Santamaria Garcia2, C. Xu2 1Deutsches Elektronen-Synchrotron DESY, 2Karlsruhe Institute of Technology KIT 12th International Particle Accelerator Conference Abstract Reinforcement learning algorithms have risen in pop-ularity in the accelerator physics community in recentyears, showing potential in beam control and in the opti-mization and automation of tasks in accelerator operation.The Helmholtz AI project “Machine Learning Toward Au-tonomous Accelerators” is a collaboration between DESYand KIT that works on investigating and developing rein-forcement learning applications for the automatic start-upof electron linear accelerators....

Reinforcement learning agent joint with the physics-based polynomial neural network.

Physics-Enhanced Reinforcement Learning for Optimal Control

A. Ivanov, I. Agapov, A. Eichler, S. Tomin Deutsches Elektronen Synchrotron DESY 12th International Particle Accelerator Conference Abstract We propose an approach for incorporating acceleratorphysics models into reinforcement learning agents. The proposed approach is based on the Taylor mapping technique for the simulation of particle dynamics. The resulting computational graph is represented as a polynomial neural network and embedded into the traditional reinforcement learning agents. The application of the model is demonstrated in a nonlinear simulation model of beam transmission....

Simple scheme of the EOS laser alignment set up.

Toward the Application of Reinforcement Learning to the Intensity Control of a Seeded Free-Electron Laser

N. Bruchon, G. Fenu, G. Gaio, M. Lonza, F. A. Pellegrino, E. Salvato University of Trieste 23rd International Conference on Mechatronics Technology Abstract The optimization of particle accelerators is a challenging task, and many different approaches have been proposed in years, to obtain an optimal tuning of the plant and to keep it optimally tuned despite drifts or disturbances. Indeed, the classical model-free approaches (such as Gradient Ascent or Extremum Seeking algorithms) have intrinsic limitations....

Scheme of the FERMI FEL seed laser alignmentset up

Free-electron Laser Optimization with Reinforcement Learning

N. Bruchon1, G. Gaio2, G. Fenu1, M. Lonza2, F. A. Pellegrino1, E. Salvato1 1University of Trieste, 2Elettra Sincrotrone Trieste 17th International Conference on Accelerator and Large Experimental Physics Control Systems Abstract Reinforcement Learning (RL) is one of the most promis-ing techniques in Machine Learning because of its modestcomputational requirements with respect to other algorithms.RL uses an agent that takes actions within its environmentto maximize a reward related to the goal it is designed toachieve....

General feedback scheme using the CSR powersignal to construct both, the state and reward signal of the Markov decision process (MDP).

Feedback Design for Control of the Micro-Bunching Instability Based on Reinforcement Learning

T. Boltz, M. Brosi, E. Bründermann, B. Haerer, P. Kaiser, C. Pohl, P. Schreiber, M. Yan,T. Asfour, A.-S. Müller Karlsruhe Insitute of Technology KIT 10th International Particle Accelerator Conference Abstract The operation of ring-based synchrotron light sourceswith short electron bunches increases the emission of co-herent synchrotron radiation (CSR) in the THz frequencyrange. However, the micro-bunching instability resultingfrom self-interaction of the bunch with its own radiationfield limits stable operation with constant intensity of CSRemission to a particular threshold current....

Using a neural network control policy for rapid switching between beam parameters in an FEL

A. L. Edelen1, S. G. Biedron2, J. P. Edelen3, S. V. Milton4, P. J. M. van der Slot5 1Colorado State University, 2Element Aero, 3Fermi National Accelerator Laboratory, 4Los Alamos National Laboratory, 5University of Twente 38th International Free Electron Laser Conference Abstract FEL user facilities often must accommodate requests for a variety of beam parameters. This usually requires skilled operators to tune the machine, reducing the amount of available time for users....