In recent years, Unmanned Aerial Vehicles (UAVs) have attracted a lot of attention due to their flexibility and mobility. However, due to the increasingly complex environments faced by UAVs and the rising demands on UAV systems, traditional UAV control methods can no longer efficiently control the UAV under multi-constraint situations. Reinforcement Learning (RL), as an emerging robot control technology, is well suited to the needs of UAV systems in terms of its ability to interact with and learn from the environment. Therefore, RL-based UAV systems are gradually becoming a new trend in research. Nonetheless, as a new research field, it faces some challenges. To fully grasp the landscape of RL-based UAV systems, it is paramount to provide a comprehensive overview and analysis of the existing specific RL methods applied to UAV systems. In this survey, we first provide a comprehensive overview and summary of the application of RL in different UAV scenarios based on the classification of RL methods. After that, based on the existing relevant literature, we conduct a systematic analysis of the challenges and recent advancements when applying RL to UAV systems. Finally, we discuss the potential research directions for RL-based UAV systems.

There are a lot of multi-objective optimization problems (MOPs) in the real world, and many multi-objective evolutionary algorithms (MOEAs) have been presented to solve MOPs. However, obtaining non-dominated solutions that trade off convergence and diversity remains a major challenge for a MOEA. To solve this problem, this paper designs an efficient multi-objective sine cosine algorithm based on a competitive mechanism (CMOSCA). In the CMOSCA, the ranking relies on non-dominated sorting, and the crowding distance rank is utilized to choose the outstanding agents, which are employed to guide the evolution of the SCA. Furthermore, a competitive mechanism stemming from the shift-based density estimation approach is adopted to devise a new position updating operator for creating offspring agents. In each competition, two agents are randomly selected from the outstanding agents, and the winner of the competition is integrated into the position update scheme of the SCA. The performance of our proposed CMOSCA was first verified on three benchmark suites (i.e., DTLZ, WFG, and ZDT) with diversity characteristics and compared with several MOEAs. The experimental results indicated that the CMOSCA can obtain a Pareto-optimal front with better convergence and diversity. Finally, the CMOSCA was applied to deal with several engineering design problems taken from the literature, and the statistical results demonstrated that the CMOSCA is an efficient and effective approach for engineering design problems.

The exponential growth of data traffic in 6G drives the dense deployment of small cells. While spectrum reuse enhances capacity, it inevitably exacerbates inter-user and inter-cell interference. Consequently, power allocation is vital for maximizing the instantaneous downlink sum rate subject to transmit power constraints. However, traditional optimization methods, such as fractional programming, rely on global Channel State Information (CSI) and incur high computational complexity, rendering them impractical for dynamic, large scale networks. Although Deep Reinforcement Learning (DRL) offers a promising alternative, existing methods are limited by full CSI dependence, misalignment with instantaneous objectives, and inefficient exploration, hindering robustness in dynamic environments. To address these challenges, this study proposes an enhanced DRL-based power allocation framework termed Information-Gain Deep Deterministic Policy Gradient (IG-DDPG). First, a compact state representation is designed by retaining only the top-I strongest normalized interference channel gains relative to the serving link, while discarding weak and negligible interference sources. This selection rationale effectively preserves dominant interference information to maintain decision accuracy while significantly reducing the state space dimensionality to remove the dependency on global CSI. Second, a max-reward learning mechanism is incorporated into the Deep Deterministic Policy Gradient (DDPG) architecture to directly optimize instantaneous sum rate. Third, building upon the Intrinsic Curiosity Module (ICM), we reinterpret its prediction-error signal as an information-gain surrogate and integrate it as an intrinsic objective. A weighting parameter is introduced to balance the trade-off between the extrinsic instantaneous rate and the intrinsic information gain, guiding the agent toward dynamically informative state transitions. Extensive experiments demonstrate that IG-DDPG consistently outperforms the baseline DDPG algorithm. It improves the average sum rate by no less than 4.3%, increases the top 20% average sum rate by at least 2.4%, and reduces variance by up to 22.15%. These results confirm that IG-DDPG provides a scalable and robust solution for real-time interference management in 6G ultra-dense cellular networks.