关键词: 分层强化学习, 可解释性人工智能, 防空反导决策, Dueling DQN, 协同优化

Abstract: Air and missile defense (AMD) systems are a core pillar of a nation’s aerospace security shield, and target-interception capability is decisive for overall combat effectiveness. As operations evolve, the AMD interception problem is increasing-ly characterized by large target scales, pronounced value heterogeneity, and stringent real-time requirements; existing techniques typically face an interception policy space that grows exponentially with target count, poor sample efficiency under delayed rewards, and opaque decision processes—limitations that fall short of operational needs. To address these challenges, this paper proposes an interception strategy framework based on Explainable Hierarchical Duel-ing DQN (EHD-DQN). It suppresses exponential policy-space growth and shortens the decision chain through a hierar-chical decoupling of “upper-level ranking → lower-level interception”; improves sample efficiency and convergence stabil-ity under delayed rewards via temporally decayed multi-experience buffers; and embeds an explainability module that combines Gradient-weighted Class Activation Mapping (Grad-CAM) and Local Interpretable Model-agnostic Explanations (LIME) to inject explanation signals into the training loop and provide traceable decision rationales. Compared with DQN, DDPG, PPO, and three traditional optimization algorithms—rolling-horizon mixed-integer linear programming (RH-MILP), non-dominated sorting genetic algorithm II (NSGA-II), and adaptive large neighborhood search (ALNS)—EHD-DQN achieves superior performance in interception count, ammunition utilization, and engagement timing for high-value targets, while furnishing transparent, staff-oriented justifications for command decision-making. The results indicate that EHD-DQN offers an efficient and explainable decision-making paradigm for AMD command-and-control systems.

Key words: Hierarchical Reinforcement Learning, Explainable Artificial Intelligence, Air Defense and Anti-Missile Decision-Making, Dueling DQN, Collaborative Optimization