The IEEE 802.11ah standard is introduced to address the growing scale of internet of things (IoT) applications. To reduce contention and enhance energy efficiency in the system, the restricted access window (RAW) mechanism is introduced in the medium access control (MAC) layer to manage the significant number of stations accessing the network. However, to achieve optimized network performance, it is necessary to appropriately determine the RAW parameters, including the number of RAW groups, the number of slots in each RAW, and the duration of each slot. In this paper, we optimize the configuration of RAW parameters in the uplink IEEE 802.11ah-based IoT network. To improve network throughput, we analyze and establish a RAW parameters optimization problem. To effectively cope with the complex and dynamic network conditions, we propose a deep reinforcement learning (DRL) approach to determine the preferable RAW parameters to optimize network throughput. To enhance learning efficiency and stability, we employ the proximal policy optimization (PPO) algorithm. We construct network environments with periodic and random traffic in an NS-3 simulator to validate the performance of the proposed PPO-based RAW parameters optimization algorithm. The simulation results reveal that using the PPO-based DRL algorithm, optimized RAW parameters can be obtained under different network conditions, and network throughput can be improved significantly.

In real-world scenarios, making navigation decisions for autonomous driving involves a sequential set of steps. These judgments are made based on partial observations of the environment, while the underlying model of the environment remains unknown. A prevalent method for resolving such issues is reinforcement learning, in which the agent acquires knowledge through a succession of rewards in addition to fragmentary and noisy observations. This study introduces an algorithm named deep reinforcement learning navigation via decision transformer (DRLNDT) to address the challenge of enhancing the decision-making capabilities of autonomous vehicles operating in partially observable urban environments. The DRLNDT framework is built around the Soft Actor-Critic (SAC) algorithm. DRLNDT utilizes Transformer neural networks to effectively model the temporal dependencies in observations and actions. This approach aids in mitigating judgment errors that may arise due to sensor noise or occlusion within a given state. The process of extracting latent vectors from high-quality images involves the utilization of a variational autoencoder (VAE). This technique effectively reduces the dimensionality of the state space, resulting in enhanced training efficiency. The multimodal state space consists of vector states, including velocity and position, which the vehicle\'s intrinsic sensors can readily obtain. Additionally, latent vectors derived from high-quality images are incorporated to facilitate the Agent\'s assessment of the present trajectory. Experiments demonstrate that DRLNDT may achieve a superior optimal policy without prior knowledge of the environment, detailed maps, or routing assistance, surpassing the baseline technique and other policy methods that lack historical data.

Energy efficiency and security issues are the main concerns in wireless sensor networks (WSNs) because of limited energy resources and the broadcast nature of wireless communication. Therefore, how to improve the energy efficiency of WSNs while enhancing security performance has attracted widespread attention. In order to solve this problem, this paper proposes a new deep reinforcement learning (DRL)-based strategy, i.e., DeepNR strategy, to enhance the energy efficiency and security performance of WSN. Specifically, the proposed DeepNR strategy approximates the Q-value by designing a deep neural network (DNN) to adaptively learn the state information. It also designs DRL-based multi-level decision-making to learn and optimize the data transmission paths in real time, which eventually achieves accurate prediction and decision-making of the network. To further enhance security performance, the DeepNR strategy includes a defense mechanism that responds to detected attacks in real time to ensure the normal operation of the network. In addition, DeepNR adaptively adjusts its strategy to cope with changing network environments and attack patterns through deep learning models. Experimental results show that the proposed DeepNR outperforms the conventional methods, demonstrating a remarkable 30% improvement in network lifespan, a 25% increase in network data throughput, and a 20% enhancement in security measures.

Multi-agent reinforcement learning (MARL) algorithms based on trust regions (TR) have achieved significant success in numerous cooperative multi-agent tasks. These algorithms restrain the Kullback-Leibler (KL) divergence (i.e., TR constraint) between the current and new policies to avoid aggressive update steps and improve learning performance. However, the majority of existing TR-based MARL algorithms are on-policy, meaning that they require new data sampled by current policies for training and cannot utilize off-policy (or historical) data, leading to low sample efficiency. This study aims to enhance the data efficiency of TR-based learning methods. To achieve this, an approximation of the original objective function is designed. In addition, it is proven that as long as the update size of the policy (measured by the KL divergence) is restricted, optimizing the designed objective function using historical data can guarantee the monotonic improvement of the original target. Building on the designed objective, a practical off-policy multi-agent stochastic policy gradient algorithm is proposed within the framework of centralized training with decentralized execution (CTDE). Additionally, policy entropy is integrated into the reward to promote exploration, and consequently, improve stability. Comprehensive experiments are conducted on a representative benchmark for multi-agent MuJoCo (MAMuJoCo), which offers a range of challenging tasks in cooperative continuous multi-agent control. The results demonstrate that the proposed algorithm outperforms all other existing algorithms by a significant margin.

Target detection in high-contrast, multi-object images and movies is challenging. This difficulty results from different areas and objects/people having varying pixel distributions, contrast, and intensity properties. This work introduces a new region-focused feature detection (RFD) method to tackle this problem and improve target detection accuracy. The RFD method divides the input image into several smaller ones so that as much of the image as possible is processed. Each of these zones has its own contrast and intensity attributes computed. Deep recurrent learning is then used to iteratively extract these features using a similarity measure from training inputs corresponding to various regions. The target can be located by combining features from many locations that overlap. The recognized target is compared to the inputs used during training, with the help of contrast and intensity attributes, to increase accuracy. The feature distribution across regions is also used for repeated training of the learning paradigm. This method efficiently lowers false rates during region selection and pattern matching with numerous extraction instances. Therefore, the suggested method provides greater accuracy by singling out distinct regions and filtering out misleading rate-generating features. The accuracy, similarity index, false rate, extraction ratio, processing time, and others are used to assess the effectiveness of the proposed approach. The proposed RFD improves the similarity index by 10.69%, extraction ratio by 9.04%, and precision by 13.27%. The false rate and processing time are reduced by 7.78% and 9.19%, respectively.

Mobile robots are playing an increasingly significant role in social life and industrial production, such as searching and rescuing robots, autonomous exploration of sweeping robots, and so on. Improving the accuracy of autonomous navigation of mobile robots is a hot issue to be solved. However, traditional navigation methods are unable to realize crash-free navigation in an environment with dynamic obstacles, more and more scholars are gradually using autonomous navigation based on deep reinforcement learning (DRL) to replace overly conservative traditional methods. But on the other hand, DRL\'s training time is too long, and the lack of long-term memory easily leads the robot to a dead end, which makes its application in the actual scene more difficult. To shorten training time and prevent mobile robots from getting stuck and spinning around, we design a new robot autonomous navigation framework which combines the traditional global planning and the local planning based on DRL. Therefore, the entire navigation process can be transformed into first using traditional navigation algorithms to find the global path, then searching for several high-value landmarks on the global path, and then using the DRL algorithm to move the mobile robot toward the designated landmarks to complete the final navigation, which makes the robot training difficulty greatly reduced. Furthermore, in order to improve the lack of long-term memory in deep reinforcement learning, we design a feature extraction network containing memory modules to preserve the long-term dependence of input features. Through comparing our methods with traditional navigation methods and reinforcement learning based on end-to-end depth navigation methods, it shows that while the number of dynamic obstacles is large and obstacles are rapidly moving, our proposed method is, on average, 20% better than the second ranked method in navigation efficiency (navigation time and navigation paths\' length), 34% better than the second ranked method in safety (collision times), 26.6% higher than the second ranked method in success rate, and shows strong robustness.

With the development of ocean exploration technology, the exploration of the ocean has become a hot research field involving the use of autonomous underwater vehicles (AUVs). In complex underwater environments, the fast, safe, and smooth arrival of target points is key for AUVs to conduct underwater exploration missions. Most path-planning algorithms combine deep reinforcement learning (DRL) and path-planning algorithms to achieve obstacle avoidance and path shortening. In this paper, we propose a method to improve the local minimum in the artificial potential field (APF) to make AUVs out of the local minimum by constructing a traction force. The improved artificial potential field (IAPF) method is combined with DRL for path planning while optimizing the reward function in the DRL algorithm and using the generated path to optimize the future path. By comparing our results with the experimental data of various algorithms, we found that the proposed method has positive effects and advantages in path planning. It is an efficient and safe path-planning method with obvious potential in underwater navigation devices.

With the coverage of sensor-rich smart devices (smartphones, iPads, etc.), combined with the need to collect large amounts of data, mobile crowd sensing (MCS) has gradually attracted the attention of academics in recent years. MCS is a new and promising model for mass perception and computational data collection. The main function is to recruit a large group of participants with mobile devices to perform sensing tasks in a given area. Task assignment is an important research topic in MCS systems, which aims to efficiently assign sensing tasks to recruited workers. Previous studies have focused on greedy or heuristic approaches, whereas the MCS task allocation problem is usually an NP-hard optimisation problem due to various resource and quality constraints, and traditional greedy or heuristic approaches usually suffer from performance loss to some extent. In addition, the platform-centric task allocation model usually considers the interests of the platform and ignores the feelings of other participants, to the detriment of the platform\'s development. Therefore, in this paper, deep reinforcement learning methods are used to find more efficient task assignment solutions, and a weighted approach is adopted to optimise multiple objectives. Specifically, we use a double deep Q network (D3QN) based on the dueling architecture to solve the task allocation problem. Since the maximum travel distance of the workers, the reward value, and the random arrival and time sensitivity of the sensing tasks are considered, this is a dynamic task allocation problem under multiple constraints. For dynamic problems, traditional heuristics (eg, pso, genetics) are often difficult to solve from a modeling and practical perspective. Reinforcement learning can obtain sub-optimal or optimal solutions in a limited time by means of sequential decision-making. Finally, we compare the proposed D3QN-based solution with the standard baseline solution, and experiments show that it outperforms the baseline solution in terms of platform profit, task completion rate, etc., the utility and attractiveness of the platform are enhanced.

In this paper, we consider reconfigurable intelligent surface (RIS)-assisted integrated satellite high-altitude platform terrestrial networks (IS-HAP-TNs) that can improve network performance by exploiting the HAP stability and RIS reflection. Specifically, the reflector RIS is installed on the side of HAP to reflect signals from the multiple ground user equipment (UE) to the satellite. To aim at maximizing the system sum rate, we jointly optimize the transmit beamforming matrix at the ground UEs and RIS phase shift matrix. Due to the limitation of the unit modulus of the RIS reflective elements constraint, the combinatorial optimization problem is difficult to tackle effectively by traditional solving methods. Based on this, this paper studies the deep reinforcement learning (DRL) algorithm to achieve online decision making for this joint optimization problem. In addition, it is verified through simulation experiments that the proposed DRL algorithm outperforms the standard scheme in terms of system performance, execution time, and computing speed, making real-time decision making truly feasible.

Uncertainty of target motion, limited perception ability of onboard cameras, and constrained control have brought new challenges to unmanned aerial vehicle (UAV) dynamic target tracking control. In virtue of the powerful fitting ability and learning ability of the neural network, this paper proposes a new deep reinforcement learning (DRL)-based end-to-end control method for UAV dynamic target tracking. Firstly, a DRL-based framework using onboard camera image is established, which simplifies the traditional modularization paradigm. Secondly, neural network architecture, reward functions, and soft actor-critic (SAC)-based speed command perception algorithm are designed to train the policy network. The output of the policy network is denormalized and directly used as speed control command, which realizes the UAV dynamic target tracking. Finally, the feasibility of the proposed end-to-end control method is demonstrated by numerical simulation. The results show that the proposed DRL-based framework is feasible to simplify the traditional modularization paradigm. The UAV can track the dynamic target with rapidly changing of speed and direction.