通过深度强化学习实现低温量热计的最优运行
仪器与探测器
2025-03-28 v1
摘要
配备跃变边缘传感器（transition-edge sensor）的低温声子探测器在当前直接探测暗物质搜寻中对轻暗物质-原子核散射具有最佳灵敏度。在此类器件中，温度计的温度及其读出电路中的偏置电流需要仔细优化以实现最优探测器性能。该任务并不简单，通常由专家手动完成。在我们的工作中，我们在两种设置下利用强化学习实现了该过程的自动化。首先，我们在三个 CRESST 探测器响应的仿真上训练，将其作为虚拟强化学习环境。其次，我们在 CRESST 地下装置中运行的相同探测器上现场训练。在两种情况下，我们都能以与人类专家相当的速度和结果优化标准探测器。我们的方法能够以最少的人工干预调谐大规模低温探测器装置。
引用
@article{arxiv.2311.15147,
title = {Optimal operation of cryogenic calorimeters through deep reinforcement learning},
author = {G. Angloher and S. Banik and G. Benato and A. Bento and A. Bertolini and R. Breier and C. Bucci and J. Burkhart and L. Canonica and A. D'Addabbo and S. Di Lorenzo and L. Einfalt and A. Erb and F. v. Feilitzsch and S. Fichtinger and D. Fuchs and A. Garai and V. M. Ghete and P. Gorla and P. V. Guillaumon and S. Gupta and D. Hauff and M. Ješkovský and J. Jochum and M. Kaznacheeva and A. Kinast and S. Kuckuk and H. Kluck and H. Kraus and A. Langenkämper and M. Mancuso and L. Marini and B. Mauri and L. Meyer and V. Mokina and K. Niedermayer and M. Olmi and T. Ortmann and C. Pagliarone and L. Pattavina and F. Petricca and W. Potzel and P. Povinec and F. Pröbst and F. Pucci and F. Reindl and J. Rothe and K. Schäffner and J. Schieck and S. Schönert and C. Schwertner and M. Stahlberg and L. Stodolsky and C. Strandhagen and R. Strauss and I. Usherov and F. Wagner and V. Wagner and M. Willers and V. Zema and C. Heitzinger and W. Waltenberger},
journal= {arXiv preprint arXiv:2311.15147},
year = {2025}
}
备注
23 pages, 14 figures, 2 tables