

























Abstract:Ad hoc wireless networks exhibit complex, innate and coupled dynamics: node mobility, energy depletion and topology change that are difficult to model analytically. Model-free deep reinforcement learning requires sustained online interaction whereas existing model based approaches use flat state representations that lose per node structure. Therefore we propose G-RSSM, a graph structured recurrent state space model that maintains per node latent states with cross node multi head attention to learn the dynamics jointly from offline trajectories. We apply the proposed method to the downstream task clustering where a cluster head selection policy trains entirely through imagined rollouts in the learned world model. Across 27 evaluation scenarios spanning MANET, VANET, FANET, WSN and tactical networks with N=30 to 1000 nodes, the learned policy maintains high connectivity with only trained for N=50. Herein, we propose the first multi physics graph structured world model applied to combinatorial per node decision making in size agnostic wireless ad hoc networks.
| Comments: | 6 pages, 4 figures. Submitted to the IEEE Global Communications Conference (GLOBECOM) 2026 |
| Subjects: | Machine Learning (cs.LG); Multiagent Systems (cs.MA); Networking and Internet Architecture (cs.NI) |
| Cite as: | arXiv:2604.14811 [cs.LG] |
| (or arXiv:2604.14811v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2604.14811 arXiv-issued DOI via DataCite |
From: Ertan Onur [view email]
[v1]
Thu, 16 Apr 2026 09:32:15 UTC (124 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。