Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces G-RSSM, a graph-structured recurrent state space model that learns ad hoc network dynamics from offline trajectories by maintaining per-node latent states and employing cross-node multi-head attention. The model is used to train a cluster head selection policy via imagined rollouts, demonstrating effective connectivity maintenance across diverse network types (MANET, VANET, FANET, WSN, tactical networks) and scales (N=30 to 1000). The key result is a size-agnostic policy trained only on N=50 nodes that generalizes effectively to much larger networks.
Train a wireless network management policy on 50 nodes, and it works on 1000 – all thanks to a graph-structured world model that captures per-node dynamics.
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.