Unmanned aerial vehicles (UAVs) are playing an increasingly pivotal role in modern communication networks, offering flexibility and enhanced coverage for a variety of applications. However, UAV networks pose significant challenges due to their dynamic and distributed nature, particularly when dealing with tasks such as power allocation, channel assignment, caching, and task offloading. Traditional optimization techniques often struggle to handle the complexity and unpredictability of these environments, leading to suboptimal performance. This survey provides a comprehensive examination of how deep reinforcement learning (DRL) can be applied to solve these mathematical optimization problems in UAV communications and networking. Rather than simply introducing DRL methods, the focus is on demonstrating how these methods can be utilized to solve complex mathematical models of the underlying problems. We begin by reviewing the fundamental concepts of DRL, including value-based, policy-based, and actor-critic approaches. Then, we illustrate how DRL algorithms are applied to specific UAV network tasks by discussing from problem formulations to DRL implementation. By framing UAV communication challenges as optimization problems, this survey emphasizes the practical value of DRL in dynamic and uncertain environments. We also explore the strengths of DRL in handling large-scale network scenarios and the ability to continuously adapt to changes in the environment. In addition, future research directions are outlined, highlighting the potential for DRL to further enhance UAV communications and expand its applicability to more complex, multi-agent settings.

For a communication control system in a disaster area where drones (also called unmanned aerial vehicles (UAVs)) are used as aerial base stations (ABSs), the reliability of communication is a key challenge for drones to provide emergency communication services. However, the effective configuration of UAVs remains a major challenge due to limitations in their communication range and energy capacity. In addition, the relatively high cost of drones and the issue of mutual communication interference make it impractical to deploy an unlimited number of drones in a given area. To maximize the communication services provided by a limited number of drones to the ground user equipment (UE) within a certain time frame while minimizing the drone energy consumption, we propose a multi-agent proximal policy optimization (MAPPO) algorithm. Considering the dynamic nature of the environment, we analyze diverse observation data structures and design novel objective functions to enhance the drone performance. We find that, when drone energy consumption is used as a penalty term in the objective function, the drones—acting as agents—can identify the optimal trajectory that maximizes the UE coverage while minimizing the energy consumption. At the same time, the experimental results reveal that, without considering the machine computing power required for training and convergence time, the proposed key algorithm demonstrates better performance in communication coverage and energy saving as compared with other methods. The average coverage performance is $10$–$45\%$ higher than that of the other three methods, and it can save up to $3\%$ more energy.

Unmanned aerial vehicle (UAV)-assisted communication networks offer an effective solution for establishing connectivity and enabling data delivery in scenarios where direct communication with terrestrial infrastructure is infeasible, such as in disaster areas. In such networks, unknown user locations, dynamic node mobility, and multi-hop transmission collectively increase the complexity of the communication process. Specifically, the uncertainty of user positions makes it difficult for UAVs to establish and maintain reliable communication links, while the mobility of both mobile users (MUs) and UAVs leads to frequent fluctuations in link quality. Furthermore, the dynamic network topology increases the complexity of routing in multi-hop transmissions, requiring UAVs to continuously adjust their trajectories to ensure stable and efficient data relaying. In this paper, we apply received signal strength indicator (RSSI)-based multilateration and deep reinforcement learning (DRL) to address the associated difficulties. Specifically, UAVs estimate the positions of nearby MUs using RSSI-based multilateration. The joint problem of mobility control and data forwarding is formulated as an Markov decision process (MDP), and a multi-agent proximal policy optimization (MAPPO) algorithm is employed to learn decentralized decision-making policies. Extensive simulations demonstrate that the proposed scheme improves transmission completion ratio and reduces transmission delay in UAV-assisted communication networks.

Unmanned aerial vehicles serving as aerial base stations can rapidly restore connectivity after disasters, yet abrupt changes in user mobility and traffic demands shift the quality of service trade-offs and produce strong non-stationarity. Deep reinforcement learning policies suffer from plasticity loss under such shifts, as representation collapse and neuron dormancy impair adaptation. We propose plasticity-enhanced multi-agent mixture of experts (PE-MAMoE), a centralized training with decentralized execution framework built on multi-agent proximal policy optimization. PE-MAMoE equips each UAV with a sparsely gated mixture of experts actor whose router selects a single specialist per step. A non-parametric Phase Controller injects brief, expert-only stochastic perturbations after phase switches, resets the action log-standard-deviation, anneals entropy and learning rate, and schedules the router temperature, all to restore policy plasticity without destabilizing safe behaviors. We derive a dynamic regret bound showing the tracking error scales with both environment variation and cumulative noise energy. In a phase-driven simulator with mobile users and 3GPP-style channels, PE-MAMoE improves normalized interquartile mean return by 26.3% over the best baseline, increases served-user capacity by 12.8%, and reduces collisions by approximately 75%. Diagnostics confirm persistently higher expert feature rank and periodic dormant-neuron recovery at regime switches.