UAV-Assisted Dynamic Avatar Task Migration for Vehicular Metaverse Services: A Multi-Agent Deep Reinforcement Learning Approach

Avatars, as promising digital representations and service assistants of users in Metaverses, can enable drivers and passengers to immerse themselves in 3D virtual services and spaces of UAV-assisted vehicular Metaverses. However, avatar tasks include a multitude of human-to-avatar and avatar-to-avatar interactive applications, e.g., augmented reality navigation,which consumes intensive computing resources. It is inefficient and impractical for vehicles to process avatar tasks locally. Fortunately, migrating avatar tasks to the nearest roadside units(RSU)or unmanned aerial vehicles(UAV) for execution is a promising solution to decrease computation overhead and reduce task processing latency, while the high mobility of vehicles brings challenges for vehicles to independently perform avatar migration decisions depending on current and future vehicle status. To address these challenges, in this paper, we propose a novel avatar task migration system based on multi-agent deep reinforcement learning(MADRL) to execute immersive vehicular avatar tasks dynamically. Specifically, we first formulate the problem of avatar task migration from vehicles to RSUs/UAVs as a partially observable Markov decision process that can be solved by MADRL algorithms. We then design the multi-agent proximal policy optimization(MAPPO) approach as the MADRL algorithm for the avatar task migration problem. To overcome slow convergence resulting from the curse of dimensionality and non-stationary issues caused by shared parameters in MAPPO, we further propose a transformer-based MAPPO approach via sequential decision-making models for the efficient representation of relationships among agents. Finally, to motivate terrestrial or non-terrestrial edge servers(e.g., RSUs or UAVs) to share computation resources and ensure traceability of the sharing records, we apply smart contracts and blockchain technologies to achieve secure sharing management. Numerical results demonstrate that the proposed approach outperforms the MAPPO approach by around 2% and effectively reduces approximately 20% of the latency of avatar task execution in UAV-assisted vehicular Metaverses.

Cognitive interference decision method for air defense missile fuze based on reinforcement learning

To solve the problem of the low interference success rate of air defense missile radio fuzes due to the unified interference form of the traditional fuze interference system,an interference decision method based Q-learning algorithm is proposed.First,dividing the distance between the missile and the target into multiple states to increase the quantity of state spaces.Second,a multidimensional motion space is utilized,and the search range of which changes with the distance of the projectile,to select parameters and minimize the amount of ineffective interference parameters.The interference effect is determined by detecting whether the fuze signal disappears.Finally,a weighted reward function is used to determine the reward value based on the range state,output power,and parameter quantity information of the interference form.The effectiveness of the proposed method in selecting the range of motion space parameters and designing the discrimination degree of the reward function has been verified through offline experiments involving full-range missile rendezvous.The optimal interference form for each distance state has been obtained.Compared with the single-interference decision method,the proposed decision method can effectively improve the success rate of interference.

A Comparative Study on the Post-Buckling Behavior of Reinforced Thermoplastic Pipes(RTPs)Under External Pressure Considering Progressive Failure

The collapse pressure is a key parameter when RTPs are applied in harsh deep-water environments.To investigate the collapse of RTPs,numerical simulations and hydrostatic pressure tests are conducted.For the numerical simulations,the eigenvalue analysis and Riks analysis are combined,in which the Hashin failure criterion and fracture energy stiffness degradation model are used to simulate the progressive failure of composites,and the“infinite”boundary conditions are applied to eliminate the boundary effects.As for the hydrostatic pressure tests,RTP specimens were placed in a hydrostatic chamber after filled with water.It has been observed that the cross-section of the middle part collapses when it reaches the maximum pressure.The collapse pressure obtained from the numerical simulations agrees well with that in the experiment.Meanwhile,the applicability of NASA SP-8007 formula on the collapse pressure prediction was also discussed.It has a relatively greater difference because of the ignorance of the progressive failure of composites.For the parametric study,it is found that RTPs have much higher first-ply-failure pressure when the winding angles are between 50°and 70°.Besides,the effect of debonding and initial ovality,and the contribution of the liner and coating are also discussed.

Recent Progress in Reinforcement Learning and Adaptive Dynamic Programming for Advanced Control Applications

Reinforcement learning(RL) has roots in dynamic programming and it is called adaptive/approximate dynamic programming(ADP) within the control community. This paper reviews recent developments in ADP along with RL and its applications to various advanced control fields. First, the background of the development of ADP is described, emphasizing the significance of regulation and tracking control problems. Some effective offline and online algorithms for ADP/adaptive critic control are displayed, where the main results towards discrete-time systems and continuous-time systems are surveyed, respectively.Then, the research progress on adaptive critic control based on the event-triggered framework and under uncertain environment is discussed, respectively, where event-based design, robust stabilization, and game design are reviewed. Moreover, the extensions of ADP for addressing control problems under complex environment attract enormous attention. The ADP architecture is revisited under the perspective of data-driven and RL frameworks,showing how they promote ADP formulation significantly.Finally, several typical control applications with respect to RL and ADP are summarized, particularly in the fields of wastewater treatment processes and power systems, followed by some general prospects for future research. Overall, the comprehensive survey on ADP and RL for advanced control applications has d emonstrated its remarkable potential within the artificial intelligence era. In addition, it also plays a vital role in promoting environmental protection and industrial intelligence.

Anti-explosion performance and dynamic response of an innovative multi-layer composite explosion containment vessel

An innovative multi-layer composite explosion containment vessel(CECV)utilizing a sliding steel platealuminum honeycomb-fiber cloth sandwich is put forward to improve the anti-explosion capacity of a conventional single-layer explosion containment vessel(SECV).Firstly,a series of experiments and finite element(FE)simulations of internal explosions are implemented to understand the basic anti-explosion characteristics of a SECV and the rationality of the computational models and methods is verified by the comparison between the experimental results and simulation results.Based on this,the CECV is designed in detail and a variety of FE simulations are carried out to investigate effects of the sandwich structure,the explosive quantity and the laying mode of the fiber cloth on anti-explosion performance and dynamic response of the CECV under internal explosions.Simulation results indicate that the end cover is the critical position for both the SECV and CECV.The maximum pressure of the explosion shock wave and the maximum strain of the CECV can be extremely declined compared to those of the SECV.As a result,the explosive quantity the CECV can sustain is up to 20 times of that the SECV can sustain.Besides,as the explosive quantity increases,the internal pressure of the CECV keeps growing and the plastic deformation and failure of the sandwich structure become more and more severe,yielding plastic strain of the CECV in addition to elastic strain.The results also reveal that the laying angles of the fiber cloth's five layers have an impact on the anti-explosion performance of the CECV.For example,the CECV with fiber cloth layered in 0°/45°/90°/45°/0°mode has the optimal anti-capacity,compared to 0°/0°/0°/0°/0°and 0°/30°/60°/30°/0°modes.Overall,owing to remarkable anti-explosion capacity,this CECV can be regarded as a promising candidate for explosion resistance.

Analysis model for damage of reinforced bars in RC beams under contact explosion

The load-bearing capacity of reinforced concrete(RC) beams primarily relies on internal reinforced bars.However, limited research has been conducted on the dynamic response of these bars. To address this gap, this study has established an analytical model using dimensional analysis for calculating the deformation of reinforced bars within RC beams subjected to contact explosion. Comparison with experimental data reveals that the model has a relative error of 5.22%, effectively reflecting the deformation of reinforced bars. Additionally, based on this model, the study found that while concrete does influence the deformation of reinforced bars, this influence can be disregarded in comparison to the material properties of the bars themselves. The findings of this study have implications for calculating the residual load-bearing capacity of damaged RC beams, evaluating the extent of damage to RC beams after blast loading, and providing guidance for the blast-resistant design of RC structures.

Bridge Bidding via Deep Reinforcement Learning and Belief Monte Carlo Search

Contract Bridge,a four-player imperfect information game,comprises two phases:bidding and playing.While computer programs excel at playing,bidding presents a challenging aspect due to the need for information exchange with partners and interference with communication of opponents.In this work,we introduce a Bridge bidding agent that combines supervised learning,deep reinforcement learning via self-play,and a test-time search approach.Our experiments demonstrate that our agent outperforms WBridge5,a highly regarded computer Bridge software that has won multiple world championships,by a performance of 0.98 IMPs(international match points)per deal over 10000 deals,with a much cost-effective approach.The performance significantly surpasses previous state-of-the-art(0.85 IMPs per deal).Note 0.1 IMPs per deal is a significant improvement in Bridge bidding.

Distributed Graph Database Load Balancing Method Based on Deep Reinforcement Learning

This paper focuses on the scheduling problem of workflow tasks that exhibit interdependencies.Unlike indepen-dent batch tasks,workflows typically consist of multiple subtasks with intrinsic correlations and dependencies.It necessitates the distribution of various computational tasks to appropriate computing node resources in accor-dance with task dependencies to ensure the smooth completion of the entire workflow.Workflow scheduling must consider an array of factors,including task dependencies,availability of computational resources,and the schedulability of tasks.Therefore,this paper delves into the distributed graph database workflow task scheduling problem and proposes a workflow scheduling methodology based on deep reinforcement learning(DRL).The method optimizes the maximum completion time(makespan)and response time of workflow tasks,aiming to enhance the responsiveness of workflow tasks while ensuring the minimization of the makespan.The experimental results indicate that the Q-learning Deep Reinforcement Learning(Q-DRL)algorithm markedly diminishes the makespan and refines the average response time within distributed graph database environments.In quantifying makespan,Q-DRL achieves mean reductions of 12.4%and 11.9%over established First-fit and Random scheduling strategies,respectively.Additionally,Q-DRL surpasses the performance of both DRL-Cloud and Improved Deep Q-learning Network(IDQN)algorithms,with improvements standing at 4.4%and 2.6%,respectively.With reference to average response time,the Q-DRL approach exhibits a significantly enhanced performance in the scheduling of workflow tasks,decreasing the average by 2.27%and 4.71%when compared to IDQN and DRL-Cloud,respectively.The Q-DRL algorithm also demonstrates a notable increase in the efficiency of system resource utilization,reducing the average idle rate by 5.02%and 9.30%in comparison to IDQN and DRL-Cloud,respectively.These findings support the assertion that Q-DRL not only upholds a lower average idle rate but also effectively curtails the average response time,thereby substantially improving processing efficiency and optimizing resource utilization within distributed graph database systems.

Nano-scale Reinforcements and Properties of Al-Si-Cu Alloy Processed by High-Pressure Torsion

To improve the comprehensive mechanical properties of Al-Si-Cu alloy,it was treated by a high-pressure torsion process,and the effect of the deformation degree on the microstructure and properties of the Al-Si-Cu alloy was studied.The results show that the reinforcements(β-Si andθ-CuAl_(2)phases)of the Al-Si-Cu alloy are dispersed in theα-Al matrix phase with finer phase size after the treatment.The processed samples exhibit grain sizes in the submicron or even nanometer range,which effectively improves the mechanical properties of the material.The hardness and strength of the deformed alloy are both significantly raised to 268 HV and 390.04 MPa by 10 turns HPT process,and the fracture morphology shows that the material gradually transits from brittle to plastic before and after deformation.The elements interdiffusion at the interface between the phases has also been effectively enhanced.In addition,it is found that the severe plastic deformation at room temperature induces a ternary eutectic reaction,resulting in the formation of ternary Al+Si+CuAl_(2)eutectic.

QoS Routing Optimization Based on Deep Reinforcement Learning in SDN

To enhance the efficiency and expediency of issuing e-licenses within the power sector, we must confront thechallenge of managing the surging demand for data traffic. Within this realm, the network imposes stringentQuality of Service (QoS) requirements, revealing the inadequacies of traditional routing allocation mechanismsin accommodating such extensive data flows. In response to the imperative of handling a substantial influx of datarequests promptly and alleviating the constraints of existing technologies and network congestion, we present anarchitecture forQoS routing optimizationwith in SoftwareDefinedNetwork (SDN), leveraging deep reinforcementlearning. This innovative approach entails the separation of SDN control and transmission functionalities, centralizingcontrol over data forwardingwhile integrating deep reinforcement learning for informed routing decisions. Byfactoring in considerations such as delay, bandwidth, jitter rate, and packet loss rate, we design a reward function toguide theDeepDeterministic PolicyGradient (DDPG) algorithmin learning the optimal routing strategy to furnishsuperior QoS provision. In our empirical investigations, we juxtapose the performance of Deep ReinforcementLearning (DRL) against that of Shortest Path (SP) algorithms in terms of data packet transmission delay. Theexperimental simulation results show that our proposed algorithm has significant efficacy in reducing networkdelay and improving the overall transmission efficiency, which is superior to the traditional methods.

Role Dynamic Allocation of Human-Robot Cooperation Based on Reinforcement Learning in an Installation of Curtain Wall

A real-time adaptive roles allocation method based on reinforcement learning is proposed to improve humanrobot cooperation performance for a curtain wall installation task.This method breaks the traditional idea that the robot is regarded as the follower or only adjusts the leader and the follower in cooperation.In this paper,a self-learning method is proposed which can dynamically adapt and continuously adjust the initiative weight of the robot according to the change of the task.Firstly,the physical human-robot cooperation model,including the role factor is built.Then,a reinforcement learningmodel that can adjust the role factor in real time is established,and a reward and actionmodel is designed.The role factor can be adjusted continuously according to the comprehensive performance of the human-robot interaction force and the robot’s Jerk during the repeated installation.Finally,the roles adjustment rule established above continuously improves the comprehensive performance.Experiments of the dynamic roles allocation and the effect of the performance weighting coefficient on the result have been verified.The results show that the proposed method can realize the role adaptation and achieve the dual optimization goal of reducing the sum of the cooperator force and the robot’s Jerk.

Reinforcement Learning in Process Industries:Review and Perspective

This survey paper provides a review and perspective on intermediate and advanced reinforcement learning(RL)techniques in process industries. It offers a holistic approach by covering all levels of the process control hierarchy. The survey paper presents a comprehensive overview of RL algorithms,including fundamental concepts like Markov decision processes and different approaches to RL, such as value-based, policy-based, and actor-critic methods, while also discussing the relationship between classical control and RL. It further reviews the wide-ranging applications of RL in process industries, such as soft sensors, low-level control, high-level control, distributed process control, fault detection and fault tolerant control, optimization,planning, scheduling, and supply chain. The survey paper discusses the limitations and advantages, trends and new applications, and opportunities and future prospects for RL in process industries. Moreover, it highlights the need for a holistic approach in complex systems due to the growing importance of digitalization in the process industries.

Reinforcement learning based edge computing in B5G

The development of communication technology will promote the application of Internet of Things,and Beyond 5G will become a new technology promoter.At the same time,Beyond 5G will become one of the important supports for the development of edge computing technology.This paper proposes a communication task allocation algorithm based on deep reinforcement learning for vehicle-to-pedestrian communication scenarios in edge computing.Through trial and error learning of agent,the optimal spectrum and power can be determined for transmission without global information,so as to balance the communication between vehicle-to-pedestrian and vehicle-to-infrastructure.The results show that the agent can effectively improve vehicle-to-infrastructure communication rate as well as meeting the delay constraints on the vehicle-to-pedestrian link.

Toward Trustworthy Decision-Making for Autonomous Vehicles:A Robust Reinforcement Learning Approach with Safety Guarantees

While autonomous vehicles are vital components of intelligent transportation systems,ensuring the trustworthiness of decision-making remains a substantial challenge in realizing autonomous driving.Therefore,we present a novel robust reinforcement learning approach with safety guarantees to attain trustworthy decision-making for autonomous vehicles.The proposed technique ensures decision trustworthiness in terms of policy robustness and collision safety.Specifically,an adversary model is learned online to simulate the worst-case uncertainty by approximating the optimal adversarial perturbations on the observed states and environmental dynamics.In addition,an adversarial robust actor-critic algorithm is developed to enable the agent to learn robust policies against perturbations in observations and dynamics.Moreover,we devise a safety mask to guarantee the collision safety of the autonomous driving agent during both the training and testing processes using an interpretable knowledge model known as the Responsibility-Sensitive Safety Model.Finally,the proposed approach is evaluated through both simulations and experiments.These results indicate that the autonomous driving agent can make trustworthy decisions and drastically reduce the number of collisions through robust safety policies.

Reinforced tissue matrix to strengthen the abdominal wall following reversal of temporary ostomies or to treat incisional hernias

BACKGROUND Abdominal wall deficiencies or weakness are a common complication of tem-porary ostomies,and incisional hernias frequently develop after colostomy or ileostomy takedown.The use of synthetic meshes to reinforce the abdominal wall has reduced hernia occurrence.Biologic meshes have also been used to enhance healing,particularly in contaminated conditions.Reinforced tissue matrices(R-TMs),which include a biologic scaffold of native extracellular matrix and a syn-thetic component for added strength/durability,are designed to take advantage of aspects of both synthetic and biologic materials.To date,RTMs have not been reported to reinforce the abdominal wall following stoma reversal.METHODS Twenty-eight patients were selected with a parastomal and/or incisional hernia who had received a temporary ileostomy or colostomy for fecal diversion after rectal cancer treatment or trauma.Following hernia repair and proximal stoma closure,RTM(OviTex®1S permanent or OviTex®LPR)was placed to reinforce the abdominal wall using a laparoscopic,robotic,or open surgical approach.Post-operative follow-up was performed at 1 month and 1 year.Hernia recurrence was determined by physical examination and,when necessary,via computed tomo-graphy scan.Secondary endpoints included length of hospital stay,time to return to work,and hospital readmissions.Evaluated complications of the wound/repair site included presence of surgical site infection,seroma,hematoma,wound dehiscence,or fistula formation.RESULTS The observational study cohort included 16 male and 12 female patients with average age of 58.5 years±16.3 years and average body mass index of 26.2 kg/m^(2)±4.1 kg/m^(2).Patients presented with a parastomal hernia(75.0%),in-cisional hernia(14.3%),or combined parastomal/incisional hernia(10.7%).Using a laparoscopic(53.6%),robotic(35.7%),or open(10.7%)technique,RTMs(OviTex®LPR:82.1%,OviTex®1S:17.9%)were placed using sublay(82.1%)or intraperitoneal onlay(IPOM;17.9%)mesh positioning.At 1-month and 1-year follow-ups,there were no hernia recurrences(0%).Average hospital stays were 2.1 d±1.2 d and return to work occurred at 8.3 post-operative days±3.0 post-operative days.Three patients(10.7%)were readmitted before the 1-month follow up due to mesh infection and/or gastrointestinal issues.Fistula and mesh infection were observed in two patients each(7.1%),leading to partial mesh removal in one patient(3.6%).There were no complications between 1 month and 1 year(0%).CONCLUSION RTMs were used successfully to treat parastomal and incisional hernias at ileostomy reversal,with no hernia recurrences and favorable outcomes after 1-month and 1-year.

Combining reinforcement learning with mathematical programming:An approach for optimal design of heat exchanger networks

Heat integration is important for energy-saving in the process industry.It is linked to the persistently challenging task of optimal design of heat exchanger networks(HEN).Due to the inherent highly nonconvex nonlinear and combinatorial nature of the HEN problem,it is not easy to find solutions of high quality for large-scale problems.The reinforcement learning(RL)method,which learns strategies through ongoing exploration and exploitation,reveals advantages in such area.However,due to the complexity of the HEN design problem,the RL method for HEN should be dedicated and designed.A hybrid strategy combining RL with mathematical programming is proposed to take better advantage of both methods.An insightful state representation of the HEN structure as well as a customized reward function is introduced.A Q-learning algorithm is applied to update the HEN structure using theε-greedy strategy.Better results are obtained from three literature cases of different scales.

Deep Reinforcement Learning Based Joint Cooperation Clustering and Downlink Power Control for Cell-Free Massive MIMO

In recent times,various power control and clustering approaches have been proposed to enhance overall performance for cell-free massive multipleinput multiple-output(CF-mMIMO)networks.With the emergence of deep reinforcement learning(DRL),significant progress has been made in the field of network optimization as DRL holds great promise for improving network performance and efficiency.In this work,our focus delves into the intricate challenge of joint cooperation clustering and downlink power control within CF-mMIMO networks.Leveraging the potent deep deterministic policy gradient(DDPG)algorithm,our objective is to maximize the proportional fairness(PF)for user rates,thereby aiming to achieve optimal network performance and resource utilization.Moreover,we harness the concept of“divide and conquer”strategy,introducing two innovative methods termed alternating DDPG(A-DDPG)and hierarchical DDPG(H-DDPG).These approaches aim to decompose the intricate joint optimization problem into more manageable sub-problems,thereby facilitating a more efficient resolution process.Our findings unequivo-cally showcase the superior efficacy of our proposed DDPG approach over the baseline schemes in both clustering and downlink power control.Furthermore,the A-DDPG and H-DDPG obtain higher performance gain than DDPG with lower computational complexity.

Task Offloading and Resource Allocation in NOMA-VEC:A Multi-Agent Deep Graph Reinforcement Learning Algorithm

Vehicular edge computing(VEC)is emerging as a promising solution paradigm to meet the requirements of compute-intensive applications in internet of vehicle(IoV).Non-orthogonal multiple access(NOMA)has advantages in improving spectrum efficiency and dealing with bandwidth scarcity and cost.It is an encouraging progress combining VEC and NOMA.In this paper,we jointly optimize task offloading decision and resource allocation to maximize the service utility of the NOMA-VEC system.To solve the optimization problem,we propose a multiagent deep graph reinforcement learning algorithm.The algorithm extracts the topological features and relationship information between agents from the system state as observations,outputs task offloading decision and resource allocation simultaneously with local policy network,which is updated by a local learner.Simulation results demonstrate that the proposed method achieves a 1.52%∼5.80%improvement compared with the benchmark algorithms in system service utility.

Knowledge Reasoning Method Based on Deep Transfer Reinforcement Learning:DTRLpath

In recent years,with the continuous development of deep learning and knowledge graph reasoning methods,more and more researchers have shown great interest in improving knowledge graph reasoning methods by inferring missing facts through reasoning.By searching paths on the knowledge graph and making fact and link predictions based on these paths,deep learning-based Reinforcement Learning(RL)agents can demonstrate good performance and interpretability.Therefore,deep reinforcement learning-based knowledge reasoning methods have rapidly emerged in recent years and have become a hot research topic.However,even in a small and fixed knowledge graph reasoning action space,there are still a large number of invalid actions.It often leads to the interruption of RL agents’wandering due to the selection of invalid actions,resulting in a significant decrease in the success rate of path mining.In order to improve the success rate of RL agents in the early stages of path search,this article proposes a knowledge reasoning method based on Deep Transfer Reinforcement Learning path(DTRLpath).Before supervised pre-training and retraining,a pre-task of searching for effective actions in a single step is added.The RL agent is first trained in the pre-task to improve its ability to search for effective actions.Then,the trained agent is transferred to the target reasoning task for path search training,which improves its success rate in searching for target task paths.Finally,based on the comparative experimental results on the FB15K-237 and NELL-995 datasets,it can be concluded that the proposed method significantly improves the success rate of path search and outperforms similar methods in most reasoning tasks.

Electrochemical Study of the Corrosion Inhibitory Capacity of Calcined Attapulgite in Reinforced Concrete Medium

The durability of reinforced concrete structures is greatly influenced by the corrosion of the reinforcement. In addition to air pollution related to the repair of corroded structures, chloride ions are the main factors of corrosion of reinforced concrete structures. This study aims to valorize a clay inhibitor against reinforcement corrosion in reinforced concrete. This clay (Attapulgite) was incorporated into reinforced concretes at different percentages of substitution of calcined attapulgite (0%, 5% and 10%) to cement in the formulation. The corrosion inhibitory power of attapulgite is evaluated in reinforced concretes subjected to the action of chloride ions at different intervals in the NaCl solution (1 day, 21 days and 45 days) by electrochemical methods (zero current chronopotentiometry, polarization curves and electrochemical impedance spectroscopy). This study showed that in the presence of chloride ions, the composition based on 10% attapulgite has an appreciable inhibitory effect with an average inhibitory efficiency of 82%.