Options
Learning-based Optimisation of Particle Accelerators Under Partial Observability Without Real-World Training
Publikationstyp
Conference Paper
Date Issued
2022-01-01
Sprache
English
Author(s)
Volume
162
Start Page
10575
End Page
10585
Citation
39th International Conference on Machine Learning (ICML 2022)
Contribution to Conference
39th International Conference on Machine Learning, ICML 2022
Scopus ID
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. Our method outperforms conventional optimisation algorithms in both the achieved result and time taken as well as already achieving close to human-level performance. We expect that such automation of machine optimisation will push the limits of operability, increase machine availability and lead to a paradigm shift in how such machines are operated, ultimately facilitating advances in a variety of fields, such as science and medicine among many others.
Subjects
MLE@TUHH
DDC Class
004: Computer Sciences