Enregistré dans:
Détails bibliographiques
Auteurs principaux: Xin, Xiaoyu, Zhang, Longxu, Lei, Jinlong, Hong, Yiguang
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2604.27318
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910179417653248
author Xin, Xiaoyu
Zhang, Longxu
Lei, Jinlong
Hong, Yiguang
author_facet Xin, Xiaoyu
Zhang, Longxu
Lei, Jinlong
Hong, Yiguang
contents Revealing the interaction topology underlying strategic behavior is fundamental to prediction, intervention, and policy design in networked systems. Yet the interaction matrix is often unobservable, and passive observation of repeated actions fails to provide sufficient excitation for reliable recovery. This paper studies topology recovery in repeated linear-quadratic network games under decaying active probing, where probing inputs are injected into a subset of players and the unknown interaction matrix is inferred from the resulting action trajectories. We first characterize a structural recoverability condition that determines when noiseless probing experiments can make the interaction matrix identifiable. We then show that, under suitable stability and controllability assumptions, a concrete decaying probing signal guarantees exact finite-step recovery while preserving convergence of the repeated-play process. To handle decision perturbations, we further develop a reweighted sparse estimator that achieves almost-sure consistency together with finite-time exact support recovery. These results clarify what can be recovered in both noiseless and perturbed settings.
format Preprint
id arxiv_https___arxiv_org_abs_2604_27318
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Revealing Strategic Interactions in Network Games Under Decaying Active Probing
Xin, Xiaoyu
Zhang, Longxu
Lei, Jinlong
Hong, Yiguang
Optimization and Control
Revealing the interaction topology underlying strategic behavior is fundamental to prediction, intervention, and policy design in networked systems. Yet the interaction matrix is often unobservable, and passive observation of repeated actions fails to provide sufficient excitation for reliable recovery. This paper studies topology recovery in repeated linear-quadratic network games under decaying active probing, where probing inputs are injected into a subset of players and the unknown interaction matrix is inferred from the resulting action trajectories. We first characterize a structural recoverability condition that determines when noiseless probing experiments can make the interaction matrix identifiable. We then show that, under suitable stability and controllability assumptions, a concrete decaying probing signal guarantees exact finite-step recovery while preserving convergence of the repeated-play process. To handle decision perturbations, we further develop a reweighted sparse estimator that achieves almost-sure consistency together with finite-time exact support recovery. These results clarify what can be recovered in both noiseless and perturbed settings.
title Revealing Strategic Interactions in Network Games Under Decaying Active Probing
topic Optimization and Control
url https://arxiv.org/abs/2604.27318