Optimal Operation of Cryogenic Calorimeters Through Deep Reinforcement Learning

Journal article

Cryogenic phonon detectors with transition-edge sensors achieve the best sensitivity to sub-GeV/c2 dark matter interactions with nuclei in current direct detection experiments. In such devices, the temperature of the thermometer and the bias current in its readout circuit need careful optimization to achieve optimal detector performance. This task is not trivial and is typically done manually by an expert. In our work, we automated the procedure with reinforcement learning in two settings. Fi...

Expand abstract

Authors: Angloher, G; Banik, S; Benato, G; Bento, A; Bertolini, A

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Springer
• Journal: Computing and Software for Big Science
• Volume: 8
• Issue: 1
• Article number: 10
• Publication date: 2024-05-22
• Acceptance date: 2024-05-15
• DOI: 10.1007/s41781-024-00119-y
• EISSN: 2510-2044
• ISSN: 2510-2036
• Language: English
• Keywords: Transition-edge sensor; Reinforcement learning; Cryogenic calorimeter; Dark matter