This study proposes a layerwise quantum-based deep reinforcement learning (LQ-DRL) method for optimizing continuous large space and time series problems using deep-layer training. The actions in LQ-DRL are optimized using a layerwise quantum embedding that leverages the advantages of quantum computing to maximize reward and reduce training loss. Moreover, this study employs a local loss to minimize the occurrence of barren plateaus phenomena and further enhance performance. As a particular case, the proposed scheme is employed to jointly optimize: 1) unmanned aerial vehicle (UAV) trajectory planning; 2) user grouping; and 3) power allocation for higher energy efficiency of a UAV as the reward. The combination of these optimized factors is referred to as action space in the presented LQ-DRL. The LQ-DRL is employed to solve the optimization problem due to its nonconvexity, continuous and large action space, and time-series domain. In a practical view, LQ-DRL aims to solve the issue of energy consumption related to limited-battery energy of a UAV base station (BS) while maintaining Quality of Service (QoS) for users, by gaining maximum energy efficiency as the reward. One of real applications, as an example, LQ-DRL can be employed to maximize the energy efficiency of a UAV BS in UAV empowered disaster recovery networks scenario. The quantum circuits of layerwise quantum embedding are presented to show the practical implementation in noisy intermediate-scale quantum computers. Based on the results, LQ-DRL outperformed the classical DRL by achieving higher effective dimension, rewards, and lower learning losses. In addition, better performances were achieved using more layers.
This study proposes a layerwise quantum-based deep reinforcement learning (LQ-DRL) method for optimizing continuous large space and time series problems using deep-layer training. The actions in LQ-DRL are optimized using a layerwise quantum embedding that leverages the advantages of quantum computing to maximize reward and reduce training loss. Moreover, this study employs a local loss to minimize the occurrence of barren plateaus phenomena and further enhance performance. As a particular case, the proposed scheme is employed to jointly optimize: 1) unmanned aerial vehicle (UAV) trajectory planning; 2) user grouping; and 3) power allocation for higher energy efficiency of a UAV as the reward. The combination of these optimized factors is referred to as action space in the presented LQ-DRL. The LQ-DRL is employed to solve the optimization problem due to its nonconvexity, continuous and large action space, and time-series domain. In a practical view, LQ-DRL aims to solve the issue of energy consumption related to limited-battery energy of a UAV base station (BS) while maintaining Quality of Service (QoS) for users, by gaining maximum energy efficiency as the reward. One of real applications, as an example, LQ-DRL can be employed to maximize the energy efficiency of a UAV BS in UAV empowered disaster recovery networks scenario. The quantum circuits of layerwise quantum embedding are presented to show the practical implementation in noisy intermediate-scale quantum computers. Based on the results, LQ-DRL outperformed the classical DRL by achieving higher effective dimension, rewards, and lower learning losses. In addition, better performances were achieved using more layers.
This study proposes quantum-based deep deterministic policy gradient (Q-DDPG) and quantum-based recurrent DDPG (Q-RDDPG) schemes for time-series optimization in UAV communications. Herein, Q-DDPG based actor-critic reinforcement learning is utilized to optimize action selections in a large state and continuous action space. In this scheme, quantum models are exploited to reduce computational complexity and training loss. As a particular case, Q-DDPG and Q-RDDPG are employed for trajectory optimization and dynamic resource allocation in UAV communications. Quantum circuits of the Q-DDPG schemes are described to showcase their implementation in noisy intermediate-scale quantum (NISQ) computers. The results demonstrate that Q-DDPG and Q-RDDPG schemes achieved higher rewards with lower training losses compared to classical DDPG.
The increasing demands for ultra-reliable low-latency communication (URLLC), high-capacity, connectivity, and mobility in next-generation wireless networks have driven the integration of unmanned aerial vehicles (UAVs) as flexible and adaptive communication nodes. UAV-assisted networks offer enhanced coverage, dynamic deployment, and cost-effective infrastructure for the sixth generation (6G) and beyond. However, optimizing UAV trajectory planning, resource allocation, and interference management is particularly challenging, especially in dynamic and large-scale environments. Classical reinforcement learning (RL) techniques, while effective in adaptive optimization, suffer from computational inefficiencies and slow convergence in high-dimensional state-action spaces. To address these constraints, quantum reinforcement learning (QRL) emerges as a novel paradigm that leverages quantum computing principles, such as superposition and entanglement, to enhance decision-making efficiency. This study provides a comprehensive overview of QRL algorithms and investigates their transformative potential in UAV-assisted wireless communication networks. We analyze UAV deployment strategies, network architectures, and topologies, highlighting their advantages as well as inherent challenges. Furthermore, we examine the limitations of classical RL algorithms and assess how QRL overcomes them while improving computational efficiency and exploration capabilities. In addition, we present a detailed review of existing QRL algorithms applicable to next-generation UAV-enhanced wireless networks, identifying key challenges that must be addressed for practical deployment. Finally, we identify open research challenges and offer future directions for integrating QRL into UAV-assisted communication, paving the way for scalable, intelligent, and high-performance wireless systems.
An intelligent adaptation technique is necessary due to the complexity and unpredictability of the air space, and autonomous unmanned aerial vehicle (UAV) navigation uses quantum reinforcement learning (QRL) as an advanced control mechanism. This work suggests quantum-inspired encoding and optimization algorithms for policy learning in order to overcome the shortcomings in efficiency and scalability of conventional and deep reinforcement learning approaches. The technique employs quantum-parametric policy optimization on a hybrid quantum-classical architecture after forming UAV navigation as a Markov Decision Process and adding quantum amplitude encoding. Dynamic obstacle and random wind disturbance experiments will be carried out in a high-fidelity 3D simulation environment. QRL has decreased energy usage by up to 17% and increased the top classical RL baseline's convergence speed by 40%. Even in inclement weather, the success rate remains around 95%, and the minimum obstacle clearance never falls below 1.8 meters. Analysis shows that QRL yields safer, more robust and sample-efficient policies that are better at generalizing to unseen maps and disturbance-heavy environments. Based on the above results, the technical feasibility and engineering value of quantum-enhanced learning algorithms for robust UAV autonomous navigation have been demonstrated; thus, they can serve as a model for future intelligent aerial decision systems.
This paper explores the application of Deep Reinforcement Learning (DRL) for optimizing quantum resource allocation in quantum computing. Traditional quantum resource allocation often relies on manual design and expert knowledge, which can be computationally expensive and limit scalability. We propose a novel framework utilizing DRL to automate this process, learning optimal strategies for allocating quantum resources (qubits, gates, and time) to maximize the performance of quantum algorithms. The core of our approach involves constructing a DRL model where the agent learns to make decisions regarding resource allocation based on the current state of the quantum system and the desired algorithm outcome. We define a state space representing the quantum system's configuration, action space encompassing various resource allocation options, and a reward function that reflects the algorithm's success. Through this framework, we aim to significantly enhance the efficiency and performance of quantum computations. This work presents a foundational approach, paving the way for more sophisticated DRL-based quantum resource allocation strategies.
This paper exploits a quantum-empowered machine learning algorithm to enhance computation learning speed. We leverage quantum phenomena such as superposition and entanglement to work on large-scale multi-dimensional data represented by quantum states. Under stochastic behaviors and quantum uncertainty, we examine the offloading problem to maximize the computational task processing efficiency, considering the computation latency, energy consumption, and quantum network adaptability. From the Markov decision process, the paper proposes a novel quantum-empowered deep reinforcement learning (Qe-DRL) approach, combining quantum computing theory and machine learning to achieve exploration and exploitation trade-off via quantum parallelism significantly. Furthermore, we develop a modified Grover’s algorithm with exponential convergence speed to provide a searching strategy for transition quantum states probabilities. Simulation results establish the effectiveness of the proposed Qe-DRL algorithm and its superior computational learning speed. Our proposed Qe-DRL algorithm outperforms other benchmarks in terms of energy efficiency performance.
The utilization of unmanned aerial vehicles (UAVs) in defense for functions, such as delivery and surveillance, has surged due to the fast progress of technology. UAV tracking and navigation system optimization is critical as UAV operations become more complicated. Quantum computing (QC) can significantly improve optimization procedures for real-time tracking, overcoming computational challenges and enhancing efficiency in UAV operations by handling large amounts of data. The study’s objective is to establish how QC performs in the optimization of UAV tracking. A novel Dynamic Kookaburra-tuned Malleable Convolutional Neural Network (DK-MCNN) is proposed to improve the tracking performance of UAVs. The data collected from video feeds from cameras mounted on UAVs, readings from GPS and other sensors outlining the specific paths and maneuvers the UAV will perform, ensuring diverse scenarios, including various terrains and environments. The data preprocessed using data cleaning and normalization involve removing erroneous or redundant data to ensure high-quality datasets. The study specifically focuses on leveraging QC into UAV tracking systems and promises to enhance performance, including speed, optimization, data handling and robustness. This technology has the potential to transform UAV operations, making them more efficient, reliable and capable of handling complex tasks in dynamic environments. The study evaluates the tracking accuracy, computational efficiency and resilience of the proposed method compared to traditional approaches across a range of operating situations. Extensive simulations of several tracking scenarios, encompassing urban, rural and disaster response situations, are employed to assess the efficacy of UAVs in monitoring and navigating across dynamic terrain. The outcomes illustrate the potential for real-time applications in UAV systems, by showing that the suggested technique dramatically decreases processing time and improves tracking accuracy, when compared to conventional algorithms.