用图结构世界模型学习自组网动态，让网络决策适应不同规模节点。
Learning Ad Hoc Network Dynamics via Graph-Structured World Models
- 基于图注意力机制的递归状态空间模型，保留每个节点的隐状态。
- 在仅训练50个节点的模型上，对30到1000个节点的场景保持高连通性。
- 适用于大规模自组网中无监督的集群头选择，适合通信系统研究者。
自组织无线网络具有复杂的内在耦合动态：节点移动、能量耗尽与拓扑变化，难以进行解析建模。纯模型无关的深度强化学习需要持续在线交互，而现有基于模型的方法使用扁平状态表示，丢失了节点间结构信息。为此，我们提出G-RSSM，一种图结构递归状态空间模型，通过跨节点多头注意力机制维护每个节点的隐状态，从离线轨迹中联合学习动态。我们将该方法应用于下游聚类任务，其中簇头选择策略完全通过学习到的世界模型中的想象推演进行训练。在涵盖MANET、VANET、FANET、WSN和战术网络的27种评估场景中，当训练节点数为N=50时，所学策略在N=30至1000的网络中仍能保持高连通性。本文首次将多物理场图结构世界模型应用于规模无关的无线自组网中组合型节点决策问题。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。