Reinforcement Learning-Based Multinode Interdiction in Unknown Networks

This article addresses the multinode cooperative jamming problem in communication networks with unknown topology. To overcome the combinatorial explosion in decision-making and the credit assignment challenge under full-bandit feedback, we propose a novel reinforcement learning (RL) algorithm based on the multiarmed bandit (MAB) framework. The core of our approach is a collective-to-individual reward allocation model, which introduces a jamming overlap coefficient to quantify node interdependencies and employs the least absolute shrinkage and selection operator (LASSO) regression to estimate individual node contributions from the observed composite rewards. Building upon this, we design a triphase "collection-construction-exploitation" learning strategy. This strategy efficiently balances exploration and exploitation, enabling the jammers to progressively identify and focus on the most disruptive node combinations without any prior knowledge of the network structure. Theoretical analysis demonstrates that the algorithm achieves a sublinear regret bound under certain conditions. Comprehensive simulations across diverse network topologies and scenarios demonstrate that the proposed method significantly outperforms existing benchmarks in terms of cumulative regret, confirming its strong robustness and adaptability.