检索结果-南通市图书馆

knowledge transfer in multi-agent reinforcement learning with incremental number of agents

Journal of Systems Engineering and Electronics 2022年第2期33卷 447-460页

作者： LIU Wenzhang DONG Lu LIU Jian SUN Changyin School of Automation Southeast UniversityNanjing 210096China School of Cyber Science and Engineering Southeast UniversityNanjing 211189China

In this paper, the reinforcement learning method for cooperative multi-agent systems(MAS) with incremental number of agents is studied. The existing multi-agent reinforcement learning approaches deal with the MAS with a specific number of agents, and can learn well-performed policies. However, if there is an increasing number of agents, the previously learned in may not perform well in the current scenario. The new agents need to learn from scratch to find optimal policies with others,which may slow down the learning speed of the whole team. To solve that problem, in this paper, we propose a new algorithm to take full advantage of the historical knowledge which was learned before, and transfer it from the previous agents to the new agents. Since the previous agents have been trained well in the source environment, they are treated as teacher agents in the target environment. Correspondingly, the new agents are called student agents. To enable the student agents to learn from the teacher agents, we first modify the input nodes of the networks for teacher agents to adapt to the current environment. Then, the teacher agents take the observations of the student agents as input, and output the advised actions and values as supervising information. Finally, the student agents combine the reward from the environment and the supervising information from the teacher agents, and learn the optimal policies with modified loss functions. By taking full advantage of the knowledge of teacher agents, the search space for the student agents will be reduced significantly, which can accelerate the learning speed of the holistic system. The proposed algorithm is verified in some multi-agent simulation environments, and its efficiency has been demonstrated by the experiment results.

关键词： knowledge transfer multi-agent reinforcement learning(MARL) new agents

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Scene image recognition with knowledge transfer for drone navigation

引用

Journal of Systems Engineering and Electronics 2023年第5期34卷 1309-1318页

作者： DU Hao WANG Wei WANG Xuerao ZUO Jingqiu WANG Yuanda School of Automation Southeast UniversityNanjing 210096China Autonomous Control Robot Laboratory Jiangsu Zhongke Institute of Applied Research on Intelligent Science and TechnologyChangzhou 213164China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology Nanjing University of Information Science and TechnologyNanjing 210044China

In this paper,we study scene image recognition with knowledge transfer for drone navigation.We divide navigation scenes into three macro-classes,namely outdoor special scenes(OSSs),the space from indoors to outdoors or from outdoors to indoors transitional scenes(TSs),and others.However,there are difficulties in how to recognize the TSs,to this end,we employ deep convolutional neural network(CNN)based on knowledge transfer,techniques for image augmentation,and fine tuning to solve the issue.Moreover,there is still a novelty detection prob-lem in the classifier,and we use global navigation satellite sys-tems(GNSS)to solve it in the prediction stage.Experiment results show our method,with a pre-trained model and fine tun-ing,can achieve 91.3196%top-1 accuracy on Scenes21 dataset,paving the way for drones to learn to understand the scenes around them autonomously.

关键词： scene recognition convolutional neural network knowledge transfer global navigation satellite systems(GNSS)-aided

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

TwinNet: Twin Structured knowledge transfer Network for Weakly Supervised Action Localization

引用

Machine Intelligence Research 2022年第3期19卷 227-246页

作者： Xiao-Yu Zhang Hai-Chao Shi Chang-Sheng Li Li-Xin Duan Institute of Information Engineering Chinese Academy of SciencesBeijing 100093China School of Computer Science Beijing Institute of TechnologyBeijing 100081China School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu 611731China

Action recognition and localization in untrimmed videos is important for many applications and have attracted a lot of attention. Since full supervision with frame-level annotation places an overwhelming burden on manual labeling effort, learning with weak video-level supervision becomes a potential solution. In this paper, we propose a novel weakly supervised framework to recognize actions and locate the corresponding frames in untrimmed videos simultaneously. Considering that there are abundant trimmed videos publicly available and well-segmented with semantic descriptions, the instructive knowledge learned on trimmed videos can be fully leveraged to analyze untrimmed videos. We present an effective knowledge transfer strategy based on inter-class semantic relevance. We also take advantage of the self-attention mechanism to obtain a compact video representation, such that the influence of background frames can be effectively eliminated. A learning architecture is designed with twin networks for trimmed and untrimmed videos, to facilitate transferable self-attentive representation learning. Extensive experiments are conducted on three untrimmed benchmark datasets (i.e., THUMOS14, ActivityNet1.3, and MEXaction2), and the experimental results clearly corroborate the efficacy of our method. It is especially encouraging to see that the proposed weakly supervised method even achieves comparable results to some fully supervised methods.

关键词： knowledge transfer weakly supervised learning self-attention mechanism representation learning action localization

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Solving Multi-Objective Vehicle Routing Problems with Time Windows: A Decomposition-Based Multiform Optimization Approach

引用

Tsinghua Science and Technology 2024年第2期29卷 305-324页

作者： Yiqiao Cai Zifan Lin Meiqin Cheng Peizhong Liu Ying Zhou Xiamen Key Laboratory of Data Security and Blockchain Technology College of Computer Science and TechnologyHuaqiao UniversityXiamen361021China College of Engineering Huaqiao UniversityQuanzhou362000China School of Computer Sciences Shenzhen Institute of Information TechnologyShenzhen518000China

In solving multi-objective vehicle routing problems with time windows (MOVRPTW),most existing algorithms focus on the optimization of a single problem formulation. However,little effort has been devoted to exploiting valuable knowledge from the alternate formulations of MOVRPTW for better optimization performance. Aiming at this insufficiency,this study proposes a decomposition-based multi-objective multiform evolutionary algorithm (MMFEA/D),which performs the evolutionary search on multiple alternate formulations of MOVRPTW simultaneously to complement each other. In particular,the main characteristics of MMFEA/D are three folds. First,a multiform construction (MFC) strategy is adopted to construct multiple alternate formulations,each of which is formulated by grouping several adjacent subproblems based on the decomposition of MOVRPTW. Second,a transfer reproduction (TFR) mechanism is designed to generate offspring for each formulation via transferring promising solutions from other formulations,making that the useful traits captured from different formulations can be shared and leveraged to guide the evolutionary search. Third,an adaptive local search (ALS) strategy is developed to invest search effort on different alternate formulations as per their usefulness for MOVRPTW,thus facilitating the efficient allocation of computational resources. Experimental studies have demonstrated the superior performance of MMFEA/D on the classical Solomon instances and the real-world instances.

关键词： MOVRPTW multiform optimization multiform construction knowledge transfer adaptive local search

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

An evolutionary multiobjective method based on dominance and decomposition for feature selection in classification

引用

Science China(Information Sciences) 2024年第2期67卷 5-19页

作者： Jing LIANG Yuyang ZHANG Ke CHEN Boyang QU Kunjie YU Caitong YUE Ponnuthurai Nagaratnam SUGANTHAN School of Electrical and Information Engineering Zhengzhou University State Key Laboratory of Intelligent Agricultural Power Equipment School of Electrical Engineering and Automation Henan Institute of Technology School of Electronics and Information Zhongyuan University of Technology KINDI Center for Computing Research College of EngineeringQatar University

Feature selection in classification can be considered a multiobjective problem with the objectives of increasing classification accuracy and decreasing the size of the selected feature subset. Dominance-based and decomposition-based multiobjective evolutionary algorithms(MOEAs) have been extensively used to address the feature selection problem due to their strong global search capability. However, most of them face the problem of not effectively balancing convergence and diversity during the evolutionary process. In addressing the aforementioned issue, this study proposes a unified evolutionary framework that combines two search forms of dominance and decomposition. The advantages of the two search methods assist one another in escaping the local optimum and inclining toward a balance of convergence and diversity. Specifically, an improved environmental selection strategy based on the distributions of individuals in the objective space is presented to avoid duplicate feature subsets. Furthermore, a novel knowledge transfer mechanism that considers evolutionary characteristics is developed, allowing for the effective implementation of positive knowledge transfer between dominance-based and decomposition-based feature selection methods. The experimental results demonstrate that the proposed algorithm can evolve feature subsets with good convergence and diversity in a shorter time compared with 9 state-of-the-art feature selection methods on 20 classification problems.

关键词： evolutionary algorithms feature selection multiobjective optimization knowledge transfer classification

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Progress and knowledge transfer from Science to Technology in the Research Frontier of CRISPR Based on the LDA Model

引用

Journal of Data and Information Science 2022年第1期7卷 1-19页

作者： Yushuang Lyu Muqi Yin Fangjie Xi Xiaojun Hu Medical Information Center and Department of Neurology of Affiliated Hospital 2Zhejiang University School of MedicineHangzhou 310058China Institute of Cyber-Systems and Control Zhejiang University School of Control Science and EngineeringHangzhou 310007China

Purpose:This study explores the underlying research topics regarding CRISPR based on the LDA model and figures out trends in knowledge transfer from science to technology in this area over the latest 10 years.Design/methodology/approach:We collected publications on CRISPR between 2011 and2020 from the Web of Science,and traced all the patents citing them from ***.15,904 articles and 18,985 patents in total are downloaded and analyzed.The LDA model was applied to identify underlying research topics in related research.In addition,some indicators were introduced to measure the knowledge transfer from research topics of scientific publications to IPC-4 classes of patents.Findings:The emerging research topics on CRISPR were identified and their evolution over time displayed.Furthermore,a big picture of knowledge transition from research topics to technological classes of patents was presented.We found that for all topics on CRISPR,the average first transition year,the ratio of articles cited by patents,the NPR transition rate are respectively 1.08,15.57%,and 1.19,extremely shorter and more intensive than those of general fields.Moreover,the transition patterns are different among research topics.Research limitations:Our research is limited to publications retrieved from the Web of Science and their citing patents indexed in ***.A limitation inherent with LDA analysis is in the manual interpretation and labeling of"topics".Practical implications:Our study provides good references for policy-makers on allocating scientific resources and regulating financial budgets to face challenges related to the transformative technology of CRISPR.Originality/value:The LDA model here is applied to topic identification in the area of transformative researches for the first time,as exemplified on CRISPR.Additionally,the dataset of all citing patents in this area helps to provide a full picture to detect the knowledge transition between S&T.

关键词： CRISPR LDA model knowledge transfer Transformative technology

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Linking elements to outcomes of knowledge transfer in the project environment: Current review and future direction

引用

Frontiers of Engineering Management 2022年第2期9卷 221-238页

作者： Qianwen ZHOU Xiaopeng DENG Ge WANG Amin MAHMOUDI Department of Construction and Real Estate School of Civil EngineeringSoutheast UniversityNanjing 211189China College of Public Administration Huazhong Agricultural UniversityWuhan 430070China Antai College of Economics and Management Shanghai Jiao Tong UniversityShanghai 200030China

A project is a specific effort to create a unique product,so it is a favorable place for knowledge creation and development.knowledge can be transferred inside and outside projects and their parent project-based organizations,thus affecting project performance and organizational competitiveness.However,the current research on the elements and outcomes of knowledge transfer(KT)in the project environment lacks completeness and clarity,and that on the different levels of KT is fragmented.This study aims to conduct comprehensive research to determine and link the elements and outcomes of KT in the project environment.The authors systematically analyzed the relevant literature from 2000 to 2021,which showed an increasing publication trend.They divided KT in the project environment into three levels according to the transfer scenario:Intra-project,cross-project,and cross-organizational KT.Five-dimensional transfer elements and two-dimensional transfer outcomes were then identified and analyzed from previous literature.Lastly,the relationships between the transfer elements and outcomes were gathered to create a comprehensive model.Importantly,the knowledge gap in the current literature was highlighted,and future research directions were put forward.This study builds a theoretical framework linking transfer elements to outcomes that can serve as a basis for scholars and practitioners to develop effective strategies for KT in the project environment.

关键词： knowledge transfer knowledge management project management project environment literature review

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

A model for knowledge transfer in a multi-agent organization based on lattice kinetic model

引用

系统工程与电子技术：英文版 2020年第1期31卷 156-167页

作者： WU Weiwei MA Qian LIU Yexin KIM Yongjun School of Management Harbin Institute of TechnologyHarbin 150001China School of Economics and Management Harbin Institute of Technology at WeihaiWeihai 264209China Beijing Institute of Aerospace Information Beijing 100854China

A study on knowledge transfer in a mutli-agent organization is performed by applying the basic principle in physics such as the kinetic theory.Based on the theoretical analysis of the knowledge accumulation process and knowledge transfer attributes,a special type of knowledge field(KF)is introduced and the knowledge diffusion equation(KDE)is developed.The evolution of knowledge potential is modeled by lattice kinetic equation and verified by numerical experiments.The new equation-based modeling developed in this paper is meaningful to simulate and predict the knowledge transfer process in firms.The development of the lattice kinetic model(LKM)for knowledge transfer can contribute to the knowledge management theory,and the managers can also simulate the knowledge accumulation process by using the LKM.

关键词： knowledge transfer multi-agent system knowledge field(KF) lattice kinetic model(LKM) knowledge diffusion equation(KDE)

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Learning implicit information in Bayesian games with knowledge transfer

引用

Control Theory and Technology 2020年第3期18卷 315-323页

作者： Guanpu CHEN Kai CAO Yiguang HONG Academy of Mathematics and Systems Science Chinese Academy of SciencesBeijing 100190China School of Mathematical Sciences University of Chinese Academy of SciencesBeijing 100049China

In this paper,we consider to learn the inherent probability distribution of types via knowledge transfer in a two-player repeated Bayesian game,which is a basic model in network security.In the Bayesian game,the attacker's distribution of types is unknown by the defender and the defender aims to reconstruct the distribution with historical actions.lt is dificult to calculate the distribution of types directly since the distribution is coupled with a prediction function of the attacker in the game model.Thus,we seek help from an interrelated complete-information game,based on the idea of transfer learning.We provide two different methods to estimate the prediction function in difftrent concrete conditions with knowledge transfer.After obtaining the estimated prediction function,the deiender can decouple the inherent distribution and the prediction function in the Bayesian game,and moreover,reconstruct the distribution of the attacker's types.Finally,we give numerical examples to illustrate the effectiveness of our methods.

关键词： Bayesian game repeated game knowledge transfer security

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A multilevel process view of organizational knowledge transfer: enablers versus barriers

引用

Journal of Management Analytics 2018年第1期5卷 1-17页

作者： Isaac Vaghefi Liette Lapointe Hamidreza Shahbaznezhad School of Management The State University of New York at BinghamtonBinghamtonNYUSA Desautels Faculty of Management McGill UniversityMontrealCanada Information Systems and Operations Management University of Auckland Business SchoolAucklandNew Zealand

The importance of knowledge as a strategic asset for organizations has been recognized by both researchers and practitioners.To gain a competitive advantage,firms are required to effectively manage their knowledge resources.The most central activity in managing knowledge is to ensure its transfer within and between organizations.knowledge transfer(KT)has thus been recognized as a key component of the knowledge management processes.The purpose of this research is to provide a holistic view of the KT barriers and enablers within an organization,from a multilevel and process-based perspectives.We first review the extant literature to identify the key enablers and barriers to KT.Second,we develop a multilevel conceptualization of enablers and barriers that can influence KT at different levels–individual,team/exchange and organization.The proposed model improves current understanding of KT by offering a holistic and integrated view of enablers and barriers.

关键词： knowledge transfer enablers barriers process model

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：