Finding Kissing Numbers with Game-theoretic Reinforcement Learning

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Ma, Chengdong, Zhaowei, Théo Tao, Li, Pengyu, Liu, Minghao, Chen, Haojun, Mao, Zihao, Cheng, Yuan, Qi, Yuan, Yang, Yaodong
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911440792715264
author Ma, Chengdong
Zhaowei, Théo Tao
Li, Pengyu
Liu, Minghao
Chen, Haojun
Mao, Zihao
Cheng, Yuan
Qi, Yuan
Yang, Yaodong
author_facet Ma, Chengdong
Zhaowei, Théo Tao
Li, Pengyu
Liu, Minghao
Chen, Haojun
Mao, Zihao
Cheng, Yuan
Qi, Yuan
Yang, Yaodong
contents Since Isaac Newton first studied the Kissing Number Problem in 1694, determining the maximal number of non-overlapping spheres around a central sphere has remained a fundamental challenge. This problem is the local analogue of Hilbert's 18th problem, bridging geometry, number theory, and information theory. Although significant progress has been made through lattices and codes, the irregularities of high-dimensional geometry, dimensional structure variability, and combinatorial explosion beyond Go limit the scalability and generality of existing methods. Here we model the problem as a two-player matrix completion game and train the reinforcement learning system, PackingStar, to play the games. The matrix entries represent pairwise cosines of sphere center vectors. One player fills entries while another corrects suboptimal ones to improve exploration quality, cooperatively maximizing the matrix size, corresponding to the kissing number. These matrices are decomposed into representative substructures, providing diverse bases and structural constraints that steer subsequent games and make extremely large spaces tractable. PackingStar surpasses records from dimensions 25 to 31 and sets new lower bounds for generalized kissing numbers under various angular constraints. It achieves the first breakthrough beyond rational structures from 1971 in 13 dimensions and discovers over 6000 new structures in other dimensions. Notably, some configurations challenge long-held antipodal paradigms, revealing algebraic correspondences with finite simple groups as well as geometric relationships across dimensions. Inspired by these patterns, humans devised further improved constructions. These results demonstrate AI's power to explore high-dimensional spaces beyond human intuition via extreme-scale reinforcement learning and open new pathways for the Kissing Number Problem and broader geometry research.
format Preprint
id arxiv_https___arxiv_org_abs_2511_13391
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Finding Kissing Numbers with Game-theoretic Reinforcement Learning
Ma, Chengdong
Zhaowei, Théo Tao
Li, Pengyu
Liu, Minghao
Chen, Haojun
Mao, Zihao
Cheng, Yuan
Qi, Yuan
Yang, Yaodong
Machine Learning
Artificial Intelligence
Since Isaac Newton first studied the Kissing Number Problem in 1694, determining the maximal number of non-overlapping spheres around a central sphere has remained a fundamental challenge. This problem is the local analogue of Hilbert's 18th problem, bridging geometry, number theory, and information theory. Although significant progress has been made through lattices and codes, the irregularities of high-dimensional geometry, dimensional structure variability, and combinatorial explosion beyond Go limit the scalability and generality of existing methods. Here we model the problem as a two-player matrix completion game and train the reinforcement learning system, PackingStar, to play the games. The matrix entries represent pairwise cosines of sphere center vectors. One player fills entries while another corrects suboptimal ones to improve exploration quality, cooperatively maximizing the matrix size, corresponding to the kissing number. These matrices are decomposed into representative substructures, providing diverse bases and structural constraints that steer subsequent games and make extremely large spaces tractable. PackingStar surpasses records from dimensions 25 to 31 and sets new lower bounds for generalized kissing numbers under various angular constraints. It achieves the first breakthrough beyond rational structures from 1971 in 13 dimensions and discovers over 6000 new structures in other dimensions. Notably, some configurations challenge long-held antipodal paradigms, revealing algebraic correspondences with finite simple groups as well as geometric relationships across dimensions. Inspired by these patterns, humans devised further improved constructions. These results demonstrate AI's power to explore high-dimensional spaces beyond human intuition via extreme-scale reinforcement learning and open new pathways for the Kissing Number Problem and broader geometry research.
title Finding Kissing Numbers with Game-theoretic Reinforcement Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2511.13391