A survey of multi-modal learning theory

Deep multi-modal learning,a rapidly growing field with a wide range of practical applications,aims to effectively utilize and integrate information from multiple sources,known as modalities.Despite its impressive empirical performance,the theoretical foundations of deep multi-modal learning have yet to be fully explored.In this paper,we will undertake a comprehensive survey of recent developments in multi-modal learning theories,focusing on the fundamental properties that govern this field.Our goal is to provide a thorough collection of current theoretical tools for analyzing multi-modal learning,to clarify their implications for practitioners,and to suggest future directions for the establishment of a solid theoretical foundation for deep multi-modal learning.

Early identification of stroke through deep learning with multi-modal human speech and movement data

Early identification and treatment of stroke can greatly improve patient outcomes and quality of life.Although clinical tests such as the Cincinnati Pre-hospital Stroke Scale(CPSS)and the Face Arm Speech Test(FAST)are commonly used for stroke screening,accurate administration is dependent on specialized training.In this study,we proposed a novel multimodal deep learning approach,based on the FAST,for assessing suspected stroke patients exhibiting symptoms such as limb weakness,facial paresis,and speech disorders in acute settings.We collected a dataset comprising videos and audio recordings of emergency room patients performing designated limb movements,facial expressions,and speech tests based on the FAST.We compared the constructed deep learning model,which was designed to process multi-modal datasets,with six prior models that achieved good action classification performance,including the I3D,SlowFast,X3D,TPN,TimeSformer,and MViT.We found that the findings of our deep learning model had a higher clinical value compared with the other approaches.Moreover,the multi-modal model outperformed its single-module variants,highlighting the benefit of utilizing multiple types of patient data,such as action videos and speech audio.These results indicate that a multi-modal deep learning model combined with the FAST could greatly improve the accuracy and sensitivity of early stroke identification of stroke,thus providing a practical and powerful tool for assessing stroke patients in an emergency clinical setting.

Multi-task Learning of Semantic Segmentation and Height Estimation for Multi-modal Remote Sensing Images

Deep learning based methods have been successfully applied to semantic segmentation of optical remote sensing images.However,as more and more remote sensing data is available,it is a new challenge to comprehensively utilize multi-modal remote sensing data to break through the performance bottleneck of single-modal interpretation.In addition,semantic segmentation and height estimation in remote sensing data are two tasks with strong correlation,but existing methods usually study individual tasks separately,which leads to high computational resource overhead.To this end,we propose a Multi-Task learning framework for Multi-Modal remote sensing images(MM_MT).Specifically,we design a Cross-Modal Feature Fusion(CMFF)method,which aggregates complementary information of different modalities to improve the accuracy of semantic segmentation and height estimation.Besides,a dual-stream multi-task learning method is introduced for Joint Semantic Segmentation and Height Estimation(JSSHE),extracting common features in a shared network to save time and resources,and then learning task-specific features in two task branches.Experimental results on the public multi-modal remote sensing image dataset Potsdam show that compared to training two tasks independently,multi-task learning saves 20%of training time and achieves competitive performance with mIoU of 83.02%for semantic segmentation and accuracy of 95.26%for height estimation.

PowerDetector:Malicious PowerShell Script Family Classification Based on Multi-Modal Semantic Fusion and Deep Learning

Power Shell has been widely deployed in fileless malware and advanced persistent threat(APT)attacks due to its high stealthiness and live-off-theland technique.However,existing works mainly focus on deobfuscation and malicious detection,lacking the malicious Power Shell families classification and behavior analysis.Moreover,the state-of-the-art methods fail to capture fine-grained features and semantic relationships,resulting in low robustness and accuracy.To this end,we propose Power Detector,a novel malicious Power Shell script detector based on multimodal semantic fusion and deep learning.Specifically,we design four feature extraction methods to extract key features from character,token,abstract syntax tree(AST),and semantic knowledge graph.Then,we intelligently design four embeddings(i.e.,Char2Vec,Token2Vec,AST2Vec,and Rela2Vec) and construct a multi-modal fusion algorithm to concatenate feature vectors from different views.Finally,we propose a combined model based on transformer and CNN-Bi LSTM to implement Power Shell family detection.Our experiments with five types of Power Shell attacks show that PowerDetector can accurately detect various obfuscated and stealth PowerShell scripts,with a 0.9402 precision,a 0.9358 recall,and a 0.9374 F1-score.Furthermore,through singlemodal and multi-modal comparison experiments,we demonstrate that PowerDetector’s multi-modal embedding and deep learning model can achieve better accuracy and even identify more unknown attacks.

DCRL-KG: Distributed Multi-Modal Knowledge Graph Retrieval Platform Based on Collaborative Representation Learning

The knowledge graph with relational abundant information has been widely used as the basic data support for the retrieval platforms.Image and text descriptions added to the knowledge graph enrich the node information,which accounts for the advantage of the multi-modal knowledge graph.In the field of cross-modal retrieval platforms,multi-modal knowledge graphs can help to improve retrieval accuracy and efficiency because of the abundant relational infor-mation provided by knowledge graphs.The representation learning method is sig-nificant to the application of multi-modal knowledge graphs.This paper proposes a distributed collaborative vector retrieval platform(DCRL-KG)using the multi-modal knowledge graph VisualSem as the foundation to achieve efficient and high-precision multimodal data retrieval.Firstly,use distributed technology to classify and store the data in the knowledge graph to improve retrieval efficiency.Secondly,this paper uses BabelNet to expand the knowledge graph through multi-ple filtering processes and increase the diversification of information.Finally,this paper builds a variety of retrieval models to achieve the fusion of retrieval results through linear combination methods to achieve high-precision language retrieval and image retrieval.The paper uses sentence retrieval and image retrieval experi-ments to prove that the platform can optimize the storage structure of the multi-modal knowledge graph and have good performance in multi-modal space.

A Multi-Modal Deep Learning Approach for Emotion Recognition

In recent years,research on facial expression recognition(FER)under mask is trending.Wearing a mask for protection from Covid 19 has become a compulsion and it hides the facial expressions that is why FER under the mask is a difficult task.The prevailing unimodal techniques for facial recognition are not up to the mark in terms of good results for the masked face,however,a multi-modal technique can be employed to generate better results.We proposed a multi-modal methodology based on deep learning for facial recognition under a masked face using facial and vocal expressions.The multimodal has been trained on a facial and vocal dataset.We have used two standard datasets,M-LFW for the masked dataset and CREMA-D and TESS dataset for vocal expressions.The vocal expressions are in the form of audio while the faces data is in image form that is why the data is heterogenous.In order to make the data homogeneous,the voice data is converted into images by taking spectrogram.A spectrogram embeds important features of the voice and it converts the audio format into the images.Later,the dataset is passed to the multimodal for training.neural network and the experimental results demonstrate that the proposed multimodal algorithm outsets unimodal methods and other state-of-the-art deep neural network models.

Visual Entity Linking via Multi-modal Learning

Existing visual scene understanding methods mainly focus on identifying coarse-grained concepts about the visual objects and their relationships,largely neglecting fine-grained scene understanding.In fact,many data-driven applications on the Web(e.g.,news-reading and e-shopping)require accurate recognition of much less coarse concepts as entities and proper linking them to a knowledge graph(KG),which can take their performance to the next level.In light of this,in this paper,we identify a new research task:visual entity linking for fine-grained scene understanding.To accomplish the task,we first extract features of candidate entities from different modalities,i.e.,visual features,textual features,and KG features.Then,we design a deep modal-attention neural network-based learning-to-rank method which aggregates all features and maps visual objects to the entities in KG.Extensive experimental results on the newly constructed dataset show that our proposed method is effective as it significantly improves the accuracy performance from 66.46%to 83.16%compared with baselines.

改进Q-Learning的路径规划算法研究

针对Q-Learning算法学习效率低、收敛速度慢且在动态障碍物的环境下路径规划效果不佳的问题,本文提出一种改进Q-Learning的移动机器人路径规划算法.针对该问题,算法根据概率的突变性引入探索因子来平衡探索和利用以加快学习效率;通过在更新函数中设计深度学习因子以保证算法探索概率;融合遗传算法,避免陷入局部路径最优同时按阶段探索最优迭代步长次数,以减少动态地图探索重复率;最后提取输出的最优路径关键节点采用贝塞尔曲线进行平滑处理,进一步保证路径平滑度和可行性.实验通过栅格法构建地图,对比实验结果表明,改进后的算法效率相较于传统算法在迭代次数和路径上均有较大优化,且能够较好的实现动态地图下的路径规划,进一步验证所提方法的有效性和实用性.

Machine learning applications in stroke medicine:advancements,challenges,and future prospectives

Stroke is a leading cause of disability and mortality worldwide,necessitating the development of advanced technologies to improve its diagnosis,treatment,and patient outcomes.In recent years,machine learning techniques have emerged as promising tools in stroke medicine,enabling efficient analysis of large-scale datasets and facilitating personalized and precision medicine approaches.This abstract provides a comprehensive overview of machine learning’s applications,challenges,and future directions in stroke medicine.Recently introduced machine learning algorithms have been extensively employed in all the fields of stroke medicine.Machine learning models have demonstrated remarkable accuracy in imaging analysis,diagnosing stroke subtypes,risk stratifications,guiding medical treatment,and predicting patient prognosis.Despite the tremendous potential of machine learning in stroke medicine,several challenges must be addressed.These include the need for standardized and interoperable data collection,robust model validation and generalization,and the ethical considerations surrounding privacy and bias.In addition,integrating machine learning models into clinical workflows and establishing regulatory frameworks are critical for ensuring their widespread adoption and impact in routine stroke care.Machine learning promises to revolutionize stroke medicine by enabling precise diagnosis,tailored treatment selection,and improved prognostication.Continued research and collaboration among clinicians,researchers,and technologists are essential for overcoming challenges and realizing the full potential of machine learning in stroke care,ultimately leading to enhanced patient outcomes and quality of life.This review aims to summarize all the current implications of machine learning in stroke diagnosis,treatment,and prognostic evaluation.At the same time,another purpose of this paper is to explore all the future perspectives these techniques can provide in combating this disabling disease.

Low-Cost Federated Broad Learning for Privacy-Preserved Knowledge Sharing in the RIS-Aided Internet of Vehicles

High-efficiency and low-cost knowledge sharing can improve the decision-making ability of autonomous vehicles by mining knowledge from the Internet of Vehicles(IoVs).However,it is challenging to ensure high efficiency of local data learning models while preventing privacy leakage in a high mobility environment.In order to protect data privacy and improve data learning efficiency in knowledge sharing,we propose an asynchronous federated broad learning(FBL)framework that integrates broad learning(BL)into federated learning(FL).In FBL,we design a broad fully connected model(BFCM)as a local model for training client data.To enhance the wireless channel quality for knowledge sharing and reduce the communication and computation cost of participating clients,we construct a joint resource allocation and reconfigurable intelligent surface(RIS)configuration optimization framework for FBL.The problem is decoupled into two convex subproblems.Aiming to improve the resource scheduling efficiency in FBL,a double Davidon–Fletcher–Powell(DDFP)algorithm is presented to solve the time slot allocation and RIS configuration problem.Based on the results of resource scheduling,we design a reward-allocation algorithm based on federated incentive learning(FIL)in FBL to compensate clients for their costs.The simulation results show that the proposed FBL framework achieves better performance than the comparison models in terms of efficiency,accuracy,and cost for knowledge sharing in the IoV.

Assessment of compressive strength of jet grouting by machine learning

Jet grouting is one of the most popular soil improvement techniques,but its design usually involves great uncertainties that can lead to economic cost overruns in construction projects.The high dispersion in the properties of the improved material leads to designers assuming a conservative,arbitrary and unjustified strength,which is even sometimes subjected to the results of the test fields.The present paper presents an approach for prediction of the uniaxial compressive strength(UCS)of jet grouting columns based on the analysis of several machine learning algorithms on a database of 854 results mainly collected from different research papers.The selected machine learning model(extremely randomized trees)relates the soil type and various parameters of the technique to the value of the compressive strength.Despite the complex mechanism that surrounds the jet grouting process,evidenced by the high dispersion and low correlation of the variables studied,the trained model allows to optimally predict the values of compressive strength with a significant improvement with respect to the existing works.Consequently,this work proposes for the first time a reliable and easily applicable approach for estimation of the compressive strength of jet grouting columns.

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.

Significant risk factors for intensive care unit-acquired weakness:A processing strategy based on repeated machine learning

BACKGROUND Intensive care unit-acquired weakness(ICU-AW)is a common complication that significantly impacts the patient's recovery process,even leading to adverse outcomes.Currently,there is a lack of effective preventive measures.AIM To identify significant risk factors for ICU-AW through iterative machine learning techniques and offer recommendations for its prevention and treatment.METHODS Patients were categorized into ICU-AW and non-ICU-AW groups on the 14th day post-ICU admission.Relevant data from the initial 14 d of ICU stay,such as age,comorbidities,sedative dosage,vasopressor dosage,duration of mechanical ventilation,length of ICU stay,and rehabilitation therapy,were gathered.The relationships between these variables and ICU-AW were examined.Utilizing iterative machine learning techniques,a multilayer perceptron neural network model was developed,and its predictive performance for ICU-AW was assessed using the receiver operating characteristic curve.RESULTS Within the ICU-AW group,age,duration of mechanical ventilation,lorazepam dosage,adrenaline dosage,and length of ICU stay were significantly higher than in the non-ICU-AW group.Additionally,sepsis,multiple organ dysfunction syndrome,hypoalbuminemia,acute heart failure,respiratory failure,acute kidney injury,anemia,stress-related gastrointestinal bleeding,shock,hypertension,coronary artery disease,malignant tumors,and rehabilitation therapy ratios were significantly higher in the ICU-AW group,demonstrating statistical significance.The most influential factors contributing to ICU-AW were identified as the length of ICU stay(100.0%)and the duration of mechanical ventilation(54.9%).The neural network model predicted ICU-AW with an area under the curve of 0.941,sensitivity of 92.2%,and specificity of 82.7%.CONCLUSION The main factors influencing ICU-AW are the length of ICU stay and the duration of mechanical ventilation.A primary preventive strategy,when feasible,involves minimizing both ICU stay and mechanical ventilation duration.

A Hand Features Based Fusion Recognition Network with Enhancing Multi-Modal Correlation

Fusing hand-based features in multi-modal biometric recognition enhances anti-spoofing capabilities.Additionally,it leverages inter-modal correlation to enhance recognition performance.Concurrently,the robustness and recognition performance of the system can be enhanced through judiciously leveraging the correlation among multimodal features.Nevertheless,two issues persist in multi-modal feature fusion recognition:Firstly,the enhancement of recognition performance in fusion recognition has not comprehensively considered the inter-modality correlations among distinct modalities.Secondly,during modal fusion,improper weight selection diminishes the salience of crucial modal features,thereby diminishing the overall recognition performance.To address these two issues,we introduce an enhanced DenseNet multimodal recognition network founded on feature-level fusion.The information from the three modalities is fused akin to RGB,and the input network augments the correlation between modes through channel correlation.Within the enhanced DenseNet network,the Efficient Channel Attention Network(ECA-Net)dynamically adjusts the weight of each channel to amplify the salience of crucial information in each modal feature.Depthwise separable convolution markedly reduces the training parameters and further enhances the feature correlation.Experimental evaluations were conducted on four multimodal databases,comprising six unimodal databases,including multispectral palmprint and palm vein databases from the Chinese Academy of Sciences.The Equal Error Rates(EER)values were 0.0149%,0.0150%,0.0099%,and 0.0050%,correspondingly.In comparison to other network methods for palmprint,palm vein,and finger vein fusion recognition,this approach substantially enhances recognition performance,rendering it suitable for high-security environments with practical applicability.The experiments in this article utilized amodest sample database comprising 200 individuals.The subsequent phase involves preparing for the extension of the method to larger databases.

Multi-modal knowledge graph inference via media convergence and logic rule

Media convergence works by processing information from different modalities and applying them to different domains.It is difficult for the conventional knowledge graph to utilise multi-media features because the introduction of a large amount of information from other modalities reduces the effectiveness of representation learning and makes knowledge graph inference less effective.To address the issue,an inference method based on Media Convergence and Rule-guided Joint Inference model(MCRJI)has been pro-posed.The authors not only converge multi-media features of entities but also introduce logic rules to improve the accuracy and interpretability of link prediction.First,a multi-headed self-attention approach is used to obtain the attention of different media features of entities during semantic synthesis.Second,logic rules of different lengths are mined from knowledge graph to learn new entity representations.Finally,knowledge graph inference is performed based on representing entities that converge multi-media features.Numerous experimental results show that MCRJI outperforms other advanced baselines in using multi-media features and knowledge graph inference,demonstrating that MCRJI provides an excellent approach for knowledge graph inference with converged multi-media features.

Generative Multi-Modal Mutual Enhancement Video Semantic Communications

Recently,there have been significant advancements in the study of semantic communication in single-modal scenarios.However,the ability to process information in multi-modal environments remains limited.Inspired by the research and applications of natural language processing across different modalities,our goal is to accurately extract frame-level semantic information from videos and ultimately transmit high-quality videos.Specifically,we propose a deep learning-basedMulti-ModalMutual Enhancement Video Semantic Communication system,called M3E-VSC.Built upon a VectorQuantized Generative AdversarialNetwork(VQGAN),our systemaims to leverage mutual enhancement among different modalities by using text as the main carrier of transmission.With it,the semantic information can be extracted fromkey-frame images and audio of the video and performdifferential value to ensure that the extracted text conveys accurate semantic information with fewer bits,thus improving the capacity of the system.Furthermore,a multi-frame semantic detection module is designed to facilitate semantic transitions during video generation.Simulation results demonstrate that our proposed model maintains high robustness in complex noise environments,particularly in low signal-to-noise ratio conditions,significantly improving the accuracy and speed of semantic transmission in video communication by approximately 50 percent.

Use of machine learning models for the prognostication of liver transplantation: A systematic review

BACKGROUND Liver transplantation(LT)is a life-saving intervention for patients with end-stage liver disease.However,the equitable allocation of scarce donor organs remains a formidable challenge.Prognostic tools are pivotal in identifying the most suitable transplant candidates.Traditionally,scoring systems like the model for end-stage liver disease have been instrumental in this process.Nevertheless,the landscape of prognostication is undergoing a transformation with the integration of machine learning(ML)and artificial intelligence models.AIM To assess the utility of ML models in prognostication for LT,comparing their performance and reliability to established traditional scoring systems.METHODS Following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines,we conducted a thorough and standardized literature search using the PubMed/MEDLINE database.Our search imposed no restrictions on publication year,age,or gender.Exclusion criteria encompassed non-English studies,review articles,case reports,conference papers,studies with missing data,or those exhibiting evident methodological flaws.RESULTS Our search yielded a total of 64 articles,with 23 meeting the inclusion criteria.Among the selected studies,60.8%originated from the United States and China combined.Only one pediatric study met the criteria.Notably,91%of the studies were published within the past five years.ML models consistently demonstrated satisfactory to excellent area under the receiver operating characteristic curve values(ranging from 0.6 to 1)across all studies,surpassing the performance of traditional scoring systems.Random forest exhibited superior predictive capabilities for 90-d mortality following LT,sepsis,and acute kidney injury(AKI).In contrast,gradient boosting excelled in predicting the risk of graft-versus-host disease,pneumonia,and AKI.CONCLUSION This study underscores the potential of ML models in guiding decisions related to allograft allocation and LT,marking a significant evolution in the field of prognostication.

Astrocytic endothelin-1 overexpression impairs learning and memory ability in ischemic stroke via altered hippocampal neurogenesis and lipid metabolism

Vascular etiology is the second most prevalent cause of cognitive impairment globally.Endothelin-1,which is produced and secreted by endothelial cells and astrocytes,is implicated in the pathogenesis of stroke.However,the way in which changes in astrocytic endothelin-1 lead to poststroke cognitive deficits following transient middle cerebral artery occlusion is not well understood.Here,using mice in which astrocytic endothelin-1 was overexpressed,we found that the selective overexpression of endothelin-1 by astrocytic cells led to ischemic stroke-related dementia(1 hour of ischemia;7 days,28 days,or 3 months of reperfusion).We also revealed that astrocytic endothelin-1 overexpression contributed to the role of neural stem cell proliferation but impaired neurogenesis in the dentate gyrus of the hippocampus after middle cerebral artery occlusion.Comprehensive proteome profiles and western blot analysis confirmed that levels of glial fibrillary acidic protein and peroxiredoxin 6,which were differentially expressed in the brain,were significantly increased in mice with astrocytic endothelin-1 overexpression in comparison with wild-type mice 28 days after ischemic stroke.Moreover,the levels of the enriched differentially expressed proteins were closely related to lipid metabolism,as indicated by Kyoto Encyclopedia of Genes and Genomes pathway analysis.Liquid chromatography-mass spectrometry nontargeted metabolite profiling of brain tissues showed that astrocytic endothelin-1 overexpression altered lipid metabolism products such as glycerol phosphatidylcholine,sphingomyelin,and phosphatidic acid.Overall,this study demonstrates that astrocytic endothelin-1 overexpression can impair hippocampal neurogenesis and that it is correlated with lipid metabolism in poststroke cognitive dysfunction.

Selective and Adaptive Incremental Transfer Learning with Multiple Datasets for Machine Fault Diagnosis

The visions of Industry 4.0 and 5.0 have reinforced the industrial environment.They have also made artificial intelligence incorporated as a major facilitator.Diagnosing machine faults has become a solid foundation for automatically recognizing machine failure,and thus timely maintenance can ensure safe operations.Transfer learning is a promising solution that can enhance the machine fault diagnosis model by borrowing pre-trained knowledge from the source model and applying it to the target model,which typically involves two datasets.In response to the availability of multiple datasets,this paper proposes using selective and adaptive incremental transfer learning(SA-ITL),which fuses three algorithms,namely,the hybrid selective algorithm,the transferability enhancement algorithm,and the incremental transfer learning algorithm.It is a selective algorithm that enables selecting and ordering appropriate datasets for transfer learning and selecting useful knowledge to avoid negative transfer.The algorithm also adaptively adjusts the portion of training data to balance the learning rate and training time.The proposed algorithm is evaluated and analyzed using ten benchmark datasets.Compared with other algorithms from existing works,SA-ITL improves the accuracy of all datasets.Ablation studies present the accuracy enhancements of the SA-ITL,including the hybrid selective algorithm(1.22%-3.82%),transferability enhancement algorithm(1.91%-4.15%),and incremental transfer learning algorithm(0.605%-2.68%).These also show the benefits of enhancing the target model with heterogeneous image datasets that widen the range of domain selection between source and target domains.

基于softmax的加权Double Q-Learning算法

强化学习作为机器学习的一个分支,用于描述和解决智能体在与环境的交互过程中,通过学习策略以达成回报最大化的问题。Q-Learning作为无模型强化学习的经典方法,存在过估计引起的最大化偏差问题,并且在环境中奖励存在噪声时表现不佳。Double Q-Learning(DQL)的出现解决了过估计问题,但同时造成了低估问题。为解决以上算法的高低估问题,提出了基于softmax的加权Q-Learning算法,并将其与DQL相结合,提出了一种新的基于softmax的加权Double Q-Learning算法(WDQL-Softmax)。该算法基于加权双估计器的构造,对样本期望值进行softmax操作得到权重,使用权重估计动作价值,有效平衡对动作价值的高估和低估问题,使估计值更加接近理论值。实验结果表明,在离散动作空间中,相比于Q-Learning算法、DQL算法和WDQL算法,WDQL-Softmax算法的收敛速度更快且估计值与理论值的误差更小。