The unmanned combat system-of-systems (UCSoS) in modern warfare is comprised of various interconnected entities that work together to support mission accomplishment. The soaring number of entities makes the UCSoS fragile and susceptible to triggering cascading effects when exposed to uncertain disturbances such as attacks or failures. Reconfiguring the UCSoS to restore its effectiveness in a self-coordinated and adaptive manner based on the battlefield situation and operational requirements has attracted increasing attention. In this paper, we focus on the UCSoS reconstruction with heterogeneous costs, where the collaboration nodes may have different reconstruction costs. Specifically, we adopt the heterogeneous network to capture the interdependencies among combat entities and propose a more representative metric to evaluate the UCSoS reconstruction effectiveness. Next, we model the combat network reconstruction problem with heterogeneous costs as a nonlinear optimization problem and prove its NP-hardness. Then, we propose an approach called SoS-Restorer, which is based on deep reinforcement learning (DRL), to address the UCSoS reconstruction problem. The results show that SoS-Restorer can quickly generate reconstruction strategies and improve the operational capabilities of the UCSoS by about 20∼60% compared to the baseline algorithm. Furthermore, even when the size of the UCSoS exceeds that of the training data, SoS-Restorer exhibits robust generalization capability and can efficiently produce satisfactory results in real time.

Unmanned Aerial Vehicles (UAVs) hold great promise for Mobile Edge Computing (MEC) owing to their flexible mobility, rapid deployment, and low-cost characteristics. However, UAV-enabled MEC still faces challenges in terms of the real-time arrival of computational tasks, energy reservation, and the actual response efficiency of the system. In this study, we focus on a UAV-enabled MEC scenario, where multiple UAVs function as airborne edge servers, offering computation services to multiple ground-based user devices (UDs). We aim to minimize the cost of the MEC system by optimizing the computation offloading policy. Specifically, we take task latency into account to ensure the timeliness of real-time tasks. The Lyapunov optimization method is employed to maintain a uniform and stable queue for energy consumption. Additionally, we draw on the concept of maximum completion time in shop-floor scheduling to optimize the actual response latency. To this end, we propose a joint optimization algorithm. First, the joint optimization problem is transformed into a per-time-slot real-time optimization problem (PROP) using the Lyapunov optimization framework. Then, a reinforcement learning method, LyraRD, is proposed to solve the PROP. Experimental results verify that the proposed approach outperforms the benchmarks in terms of system performance.

Network disintegration is a fundamental issue in the field of complex networks, with its core in identifying critical nodes or sets and removing them to weaken network functionality. The research on this problem has significant strategic value and has increasingly attracted attention, including in controlling the spread of diseases and dismantling terrorist organizations. In this paper, we focus on the problem of network disintegration with discrete entity resources from the attack view, that is, optimizing resource allocation to maximize the effect of network disintegration. Specifically, we model the network disintegration problem with limited entity resources as a nonlinear optimization problem and prove its NP-hardness. Then, we design a method based on deep reinforcement learning (DRL), Net-Cracker, which transforms the two-stage entity resource and network node selection task into a single-stage object selection problem. Extensive experiments demonstrate that compared with the benchmark algorithm, Net-Cracker can improve the solution quality by about 8∼62%, while enabling a 30-to-160-fold speed up. Net-Cracker also exhibits strong generalization ability and can find better results in a near real-time manner even when the network scale is much larger than that in training data.

Autonomous stealth navigation through modern Integrated Air Defense Systems requires Unmanned Aerial Vehicles (UAVs) to minimize radar detectability while maintaining efficient flight. This poses a severe continuous-control challenge under partial observability, as the dynamic radar cross-section (RCS) is highly coupled with the aircraft’s real-time attitude. In this paper, we formulate this task as a Partially Observable Markov Decision Process (POMDP) and propose an attention-guided deep reinforcement learning framework. Specifically, we design a cross-attention state encoder to adaptively process variable-length, localized radar warning signals, enabling dynamic threat prioritization. The control policy is optimized using the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm to generate high-precision continuous lateral maneuvers. Extensive simulations demonstrate that our proposed TD3-Att framework achieves improved convergence stability, higher average returns, and robust zero-shot generalization compared to DDPG and SAC baselines. Notably, the learned policy steers the aircraft along low-RCS heading/aspect angles, providing an effective continuous-control solution for navigating contested electromagnetic environments.

In disaster response and other infrastructure-limited settings, UAV-mounted access points can rapidly restore service availability for mobile ground users as demand and fleet availability evolve. Existing single-slot coverage formulations, however, can mask prolonged individual outages and do not jointly represent heterogeneous service priorities, finite battery capacities, and periodic recharging. We study persistent geometricmulti-UAV service coverage, where a user is available for service when it lies inside a UAV footprint. We propose Priority- and Outage-Guided Safe QMIX (POGS-QMIX), a hybrid hierarchical framework in which a centralized online coordinator forms conflict-reduced UAV–user targets from fleet-wide priority and outage information, while parameter-shared QMIX agents independently choose target-conditioned low-level actions. The framework couples class-balanced outage memory, assignment, dense target-progress feedback, and a return-energy action mask. The evaluation includes learning and non-learning baselines, greedy-versus-Hungarian assignment, multi-seed statistics, sensitivity studies, operating-condition studies, and energy-stress tests. In the default scenario, POGS-QMIX obtains high-priority coverage $0.547\pm 0.009$ and maximum high-priority outage $38.0\pm 4.7$ slots over five independent seeds.