关键词: network dismantling, hypergraph, deep reinforcement learning, evolutionary strategies, combinatorial optimization

Abstract: Assessing the vulnerability of complex systems requires effective hypergraph dismantling strategies, yet existing methods struggle with the dynamic nature of cascading failures and the rugged optimization landscapes of high-order networks. In this paper, we propose a novel framework: hypergraph dismantling via evolutionary deep reinforcement learning (HD-EDR). First, we model a realistic dismantling environment incorporating hyperdegree-based and residual-capacity-based load redistribution mechanisms. Second, we introduce a hybrid learning architecture that synergizes the global exploration of evolutionary strategies with the gradient-based exploitation of deep reinforcement learning. A bidirectional parameter synchronization mechanism is designed to prevent the agent from being trapped in local optima. Furthermore, we integrate an inductive encoder to capture the evolving high-order dependencies of the residual network in real time. Extensive experiments across nine real-world datasets demonstrate that our framework significantly outperforms state-of-the-art baselines, providing a highly effective and robust strategy for maximizing structural damage in high-order networks.

Key words: network dismantling, hypergraph, deep reinforcement learning, evolutionary strategies, combinatorial optimization