Hierarchical clustering in particle physics through reinforcement\n learning

2020/11/16 by Johann Brehmer, Sebastian Macaluso, Brehmer, Johann +5 · 2 citations
Computer Science · Decision Sciences · Physics and Astronomy · #Artificial Intelligence (cs.AI) #Computational Physics and Python Applications #Distributed and Parallel Computing Systems #FOS: Computer and information sciences #FOS: Physical sciences #High Energy Physics - Phenomenology (hep-ph) #Machine Learning (cs.LG) #Particle physics theoretical and experimental studies #Scientific Computing and Data Management

paper · pdf · doi:10.48550/arxiv.2011.08191

openalex publication_date 2020/11/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Particle physics experiments often require the reconstruction of decay\npatterns through a hierarchical clustering of the observed final-state\nparticles. We show that this task can be phrased as a Markov Decision Process\nand adapt reinforcement learning algorithms to solve it. In particular, we show\nthat Monte-Carlo Tree Search guided by a neural policy can construct\nhigh-quality hierarchical clusterings and outperform established greedy and\nbeam search baselines.\n

Citations

• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm

Cited by

• SCULPT: An Interactive Machine Learning Platform for Analyzing Multi-Particle Coincidence Data from Cold Target Recoil Ion Momentum Spectroscopy
• Theory-informed neural networks for particle physics

Related

• Hierarchical clustering with deep Q-learning
• Theory-informed neural networks for particle physics
• Particle Physics Model Building with Reinforcement Learning
• A data-driven and model-agnostic approach to solving combinatorial assignment problems in searches for new physics
• HyperTrack: Neural Combinatorics for High Energy Physics