學習觸發：大型強子對撞機中的強化學習

摘要

高吞吐量科學設施（如大型強子對撞機）依賴於在嚴格的頻寬、延遲與儲存限制下進行即時事件篩選（觸發）。實務上，觸發選單大多靜態且經手動調整，當偵測器條件、碰撞堆疊與背景組成隨時間漂移時，可能變得次優。我們將在線閾值調整視為序列決策問題：強化學習代理攝取近期觸發率與訊號敏感特徵的串流摘要，並更新觸發閾值，以在追蹤目標背景率（維持於容忍帶內）的同時最大化訊號效率。我們將群體過濾策略優化（Group-Filtered Policy Optimization, GFPO）適應於串流控制，並引入兩個變體（GFPO-F、GFPO-FR），於訓練期間強制背景率的可行性。在一個模擬真實對撞機運行的基準測試中，我們研究了兩種代表性觸發：對碰撞堆疊變化敏感的總橫向能量（H_{T}）觸發，以及基於重建損失的異常檢測（AD）觸發，用於稀有或非標準特徵。在蒙地卡羅串流上，我們的代理將符合容忍區間的時間比例提高了48%（H_T）與28%（AD），且在這些容忍區間內，訊號效率的累積增益高達2%。從模擬轉移至真實碰撞數據（CMS運行283408）時，相同的代理無需微調，即在容忍度方面比基線提升56%（H_T）與28%（AD），並在兩種觸發上進一步獲得訊號效率增益。據我們所知，這是首次在真實大型強子對撞機碰撞數據上展示基於強化學習的觸發控制。程式碼可於 https://github.com/Zixind/GFPO_LHC 取得（詳見儲存庫）。

English

High-throughput scientific facilities such as the Large Hadron Collider depend on real-time event filtering (triggering) under tight constraints on bandwidth, latency, and storage. In practice, trigger menus are largely static and hand-tuned and can become suboptimal as detector conditions, pileup, and background composition drift over time. We cast online threshold tuning as a sequential decision-making problem: a reinforcement learning agent ingests streaming summaries of recent rates and signal-sensitive features and updates trigger thresholds to maximize signal efficiency while tracking a target background rate within a tolerance band. We adapt Group-Filtered Policy Optimization (GFPO) to streaming control and introduce two variants (GFPO-F, GFPO-FR) that enforce background rate feasibility during training. On a benchmark that emulates realistic collider operation, we study two representative triggers: a total transverse energy (H_{T}) trigger sensitive to pileup variation, and an anomaly-detection (AD) trigger based on reconstruction loss for rare or non-standard signatures. On Monte Carlo streams, our agent increases the fraction of in-tolerance time intervals by 48\% (H_T) and 28\% (AD), with a cumulative gain of up to 2\% in signal efficiency on those in-tolerance intervals. Transferring from simulation to real collision data (CMS Run 283408), the same agent, without fine-tuning, achieves a 56\% (H_T) and 28\% (AD) in-tolerance improvement over baselines, with further signal-efficiency gain on both triggers. To our knowledge, this is the first demonstration of RL-based trigger control on real Large Hadron Collider collision data. Code is available at https://github.com/Zixind/GFPO_LHC (see repo for details).