Multifunctional radar (MFR) can adjust to different working modes based on surrounding environment information, providing a degree of anti-jamming capability. With the enhancement of information exchange capabilities, technologies such as cooperative detection and guidance have advanced significantly, further strengthening the anti-jamming capabilities of MFR network. Therefore, this paper builds a networked radar (NR) model based on complex network theory and presents the radar countermeasure game problem of joint jamming type selection and power allocation under power constraints. Specifically, this paper employs multi-agent reinforcement learning(MARL) algorithms to optimize the selection of jamming types and power allocation for multiple jamming beams, thereby maximizing the long-term jamming effectiveness on NR. To address the hybrid action space decision-making problem in jamming, a serial hierarchical policy network with a shared evaluation network is designed. In addition, according to the jamming task, the state characteristics and total reward are designed reasonably to assist the strategy exploration. Finally, we propose an improved multi-agent hybrid proximal policy optimization (IMAHPPO) algorithm for devising jamming strategies and compare its performance with the standard MAHPPO algorithm and the Multi-Agent Advantage Actor-Critic (MA2C) algorithm, demonstrating the effectiveness and adaptability of the proposed approach.

A critical challenge degrading the survival probability of penetrators in air penetration missions against networked radar systems stems from inefficient jamming resource allocation, particularly in decision-making quality and real-time responsiveness. To address this challenge, we first construct a many-to-many jamming resource allocation model for jammer formations countering networked radar systems, based on the operational scenario where multiple jammers escort penetrators. The objective function and constraint conditions of this model are rigorously formulated. Subsequently, we propose a Particle Swarm Optimization Guided Seasonal Strategy Nutcracker Optimization Algorithm (PSO-SSNOA) based jamming resource allocation method. This approach innovatively integrates Particle Swarm Optimization (PSO) with the Nutcracker Optimization Algorithm (NOA), while enhancing the nutcracker’s behavioral patterns through seasonal adaptation strategies. Extensive simulation results substantiate PSO-SSNOA’s triple advantage: (1) demonstrating 100% stable convergence probability that surpasses NOA’s 80% while matching PSO’s reliability; (2) achieving 76% faster average runtime than standard PSO implementation; and (3) requiring 90% fewer convergence iterations compared to conventional NOA methodology. These quantified metrics confirm the algorithm’s enhanced stability, real-time responsiveness, and optimization efficacy in complex electronic warfare environments.

Jamming resource allocation is an important step in implementing cooperative jamming. Traditional jamming resource allocation considers only the reduction of enemy radar detection performance but ignores the problem of mutual interference in the formation. Therefore, an adaptive scheduling strategy based on the Improved Sparrow Search Algorithm (ISSA) is proposed to improve the jamming efficiency and minimize mutual interference. First, the target detection model and the mutual interference model are established. On this basis, a two-factor objective function based on network detection probability and the degree of mutual interference is constructed. Then, a whole-process cooperative mechanism is proposed, and an improved circle algorithm and a whale predation strategy are introduced. These strategies are used to overcome the problems of slow convergence and local optimization in the standard sparrow search algorithm (SSA). Finally, the effectiveness and timeliness of ISSA are proved by simulation experiments.

In recent years, deep reinforcement learning (DRL) has made some progress in jamming type selection (JTS). However, during the training process of the agent, exploration of the action space is necessary, which leads to poor jamming effects in the early stages of training, posing a significant threat to the aircraft’s survivability. Therefore, this paper proposes a method of JTS based on generative adversarial imitation learning (GAIL). Firstly, the agent learns from expert strategies to achieve high reward returns, avoiding wasted time from blind exploration, thereby ensuring that the agent maintains a good jamming effect throughout its application process. Secondly, based on generative adversarial theory, the discriminator measures the difference between the generated and expert strategies. This difference is used as an internal reward to assist in updating the neural network parameters, effectively reducing the complexity of reward function design. Finally, through case analysis, it can be observed that using the GAIL algorithm can achieve rewards close to those of the expert strategy. When applied online, it does not rely on accurate predictions or precise modeling of the external environment, allowing for quick real-time decision-making. Additionally, its performance surpasses that of traditional JTS strategies.

This paper investigates the formation joint resource scheduling problem from the perspective of cooperative jamming against radar systems. First, the formation survivability is redefined based on the task requirements. Then, a hierarchical adaptive scheduling strategy solution framework is constructed for state prediction and detection fusion of the networked radar system. Considering the scene constraints, an Improved Adaptive Parameter Evolution Marine Predators Algorithm is designed as an optimizer and embedded in the proposed framework to jointly optimize the platform beam allocation and jamming mode selection. Based on the original algorithm, real number random coding is used to perform dimensional conversion of decision variables, an adaptive parameter evolution mechanism is designed to reduce the dependence on algorithm parameters, and an adaptive selection mechanism for dominant strategies and a search intensity control strategy are proposed to help decision-makers explore the optimal resource scheduling strategy quickly and accurately. Finally, considering the formation maneuvering behavior and incomplete information, the proposed method is compared with existing base strategies in different typical scenarios. It is proved that the proposed strategy can fully exploit the limited jamming resources and maximize the survivability of the formation in radar system cooperative jamming scenarios, demonstrating superior jamming performance and shorter decision time.

This paper addresses the resource allocation problem for aircraft formation cooperative jamming against networked radar systems (NRS) under terrain occlusion conditions, proposing a jamming decision strategy that integrates terrain occlusion judgement with an improved plant rhizome growth optimiser (IPRGO). By constructing a hybrid terrain model of ‘low‐frequency base + Gaussian peak clusters’ and integrating radar masking angle calculation with the Bresenham line algorithm, rapid line‐of‐sight (LoS) judgement is achieved, effectively identifying the radar's effective detection range. Based on this, a jamming effectiveness evaluation function with the dual objectives of NRS detection probability and localisation probability is established, and a jamming resource allocation optimisation model is constructed by jointly considering jamming beam selection and power allocation. To further enhance solution efficiency and accuracy, the standard plant rhizome growth optimiser (PRGO) is improved by introducing random key encoding, a hybrid search strategy, adaptive temperature regulation and a diversified elite strategy, forming the IPRGO algorithm. Simulation results indicate that the strategy considering terrain occlusion can dynamically allocate jamming resources, avoid power wastage on occluded radars and significantly improve resource utilisation efficiency. The IPRGO algorithm outperforms genetic algorithms (GA), ant colony optimisation (ACO), cuckoo search (CS) and the standard PRGO in reducing detection and localisation probabilities, and it exhibits high computational efficiency with an average computation time per instance of only 0.1841 s, making it suitable for high‐granularity online decision‐making. The strategy proposed in this paper holds promising prospects for engineering application in complex electromagnetic countermeasure environments.