强化学习实时优化大型强子对撞机触发器

作者 PulseAugur 编辑部 · [2 个来源] · 2026-06-22 22:56

研究人员开发了一种强化学习代理，能够实时优化大型强子对撞机（Large Hadron Collider）的触发阈值。该系统改编自Group-Filtered Policy Optimization (GFPO)，旨在在遵守背景速率约束的同时最大化信号效率。在模拟数据上进行测试时，该代理将容差时间间隔提高了高达48%，并显示出2%的累积信号效率增益。至关重要的是，在没有进一步调整的情况下，同一代理在真实的CMS碰撞数据上取得了显著改进，标志着RL在这一环境中首次成功应用于触发控制。 AI

影响展示了一种用AI优化复杂科学仪器的新方法，有望提高高能物理领域的数据收集效率。

排序理由这是一篇详细介绍强化学习在科学仪器上新颖应用的学术论文。

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.AI TIER_1 English(EN) · Zixin Ding, Shaghayegh Emam, Giovanna Salvi, Cecilia Tosciri, Abhijith Gandrakota, Jennifer Ngadiuba, Nhan Tran, Christian Herwig, David W. Miller, Yuxin Chen · 2026-06-24 04:00

Learning to Trigger: Reinforcement Learning at the Large Hadron Collider

arXiv:2606.23993v1 Announce Type: cross Abstract: High-throughput scientific facilities such as the Large Hadron Collider depend on real-time event filtering (\textit{triggering}) under tight constraints on bandwidth, latency, and storage. In practice, trigger menus are largely s…
arXiv cs.LG TIER_1 English(EN) · Yuxin Chen · 2026-06-22 22:56

Learning to Trigger: Reinforcement Learning at the Large Hadron Collider

High-throughput scientific facilities such as the Large Hadron Collider depend on real-time event filtering (\textit{triggering}) under tight constraints on bandwidth, latency, and storage. In practice, trigger menus are largely static and hand-tuned and can become suboptimal as …

报道来源 [2]

Learning to Trigger: Reinforcement Learning at the Large Hadron Collider

Learning to Trigger: Reinforcement Learning at the Large Hadron Collider

相关实体

相关话题