检索结果-南通市图书馆

Discovering Latent Variables for the Tasks With Confounders in Multi-Agent Reinforcement Learning

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第7期11卷 1591-1604页

作者： Kun Jiang Wenzhang Liu Yuanda Wang lu dong Changyin Sun the School of Automation Southeast UniversityNanjing 210096China the School of Artificial Intelligence Anhui UniversityHefei 230601China IEEE the School of Cyber Science and Engineering Southeast UniversityNanjing 211189China the Engineering Research Center of Autonomous Unmanned System Technology Ministry of EducationHefei 230601China

Efficient exploration in complex coordination tasks has been considered a challenging problem in multi-agent reinforcement learning(MARL). It is significantly more difficult for those tasks with latent variables that agents cannot directly observe. However, most of the existing latent variable discovery methods lack a clear representation of latent variables and an effective evaluation of the influence of latent variables on the agent. In this paper, we propose a new MARL algorithm based on the soft actor-critic method for complex continuous control tasks with confounders. It is called the multi-agent soft actor-critic with latent variable(MASAC-LV) algorithm, which uses variational inference theory to infer the compact latent variables representation space from a large amount of offline experience.Besides, we derive the counterfactual policy whose input has no latent variables and quantify the difference between the actual policy and the counterfactual policy via a distance function. This quantified difference is considered an intrinsic motivation that gives additional rewards based on how much the latent variable affects each agent. The proposed algorithm is evaluated on two collaboration tasks with confounders, and the experimental results demonstrate the effectiveness of MASAC-LV compared to other baseline algorithms.

关键词： Latent variable model maximum entropy multi-agent reinforcement learning(MARL) multi-agent system

New roles of research data infrastructure in research paradigm evolution

同方期刊数据库博看期刊评论

在线全文

学校读者我要写书评

暂无评论

Journal of Data and Information Science 2024年第2期9卷 104-119页

作者： Yizhan Li lu dong Xiaoxiao Fan Ren Wei Shijie Guo Wenzhen Ma Zexia Li National Library Science Chinese Academy of SciencesBeijing 100190China Department of Information Resources Management School of Economics and ManagementUniversity of Chinese Academy of SciencesBeijing100190China Bureau of Facility Support and Budget Chinese Academy of SciencesBeijing 100864China

Research data infrastructures form the cornerstone in both cyber and physical spaces,driving the progression of the data-intensive scientific research paradigm.This opinion paper presents an overview of global research data infrastructure,drawing insights from national roadmaps and strategic documents related to research data infrastructure.It emphasizes the pivotal role of research data infrastructures by delineating four new missions aimed at positioning them at the core of the current scientific research and communication ecosystem.The four new missions of research data infrastructures are:(1)as a pioneer,to transcend the disciplinary border and address complex,cutting-edge scientific and social challenges with problem-and data-oriented insights;(2)as an architect,to establish a digital,intelligent,flexible research and knowledge services environment;(3)as a platform,to foster the high-end academic communication;(4)as a coordinator,to balance scientific openness with ethics needs.

关键词： Research data infrastructure Landscape Data-centric Problem-oriented

Prolonged Consumption of Dietary Advanced Lipoxidation End Products contributes to renal impairment in mice through Dysregulated Intestinal homeostasis

在线全文

学校读者我要写书评

暂无评论

Food Science and Human Wellness 2024年

作者： Yaya Wang lu dong Yaozhong Hu Tianchang Zhang Ruican Wang Linqing Nie Junping Wang Yan Zhang Shuo Wang Tianjin Key Laboratory of Food Science and Health School of Medicine Nankai University State Key Laboratory of Food Nutrition and Safety Key Laboratory of Food Nutrition and Safety College of Food Engineering and Biotechnology Tianjin University of Science and Technology

Heat processing of food has been well validated as the trigger to generate heat-processing side product of advanced lipoxidation end products (ALEs)， which potentially engenders the threat on systemic health or progression of diseases， especially the accumulated effect after long-term intake. Thus， the study was proposed to evaluate the effect of dietary ALEs on health after long-term ingestion， specifically through simulating the intake of dietary ALE in mice within 9 months to investigate the intervention effect and underlying mechanism. The unexpected observation of renal insufficiency or impairment after long-term intake of dietary ALEs indicated the negative impact on renal health， which has been verified by the pathological analysis. Further studies revealed that a high-ALEs diet disrupted the intestinal barrier， with enhanced impact after disturbing the gut microbiota to potentially lower the abundance of beneficial microbiome through producing nephrotoxic metabolites. Correlation analysis showed that the proliferation of harmful bacteria and the reduction of beneficial bacteria were strongly correlated with intestinal barrier damage and the development of renal insufficiency. Furthermore， the underlying mechanism was unveiled as that ALEs could inhibit AMPK/SIRT1 signaling to fundamentally induce renal inflammation and oxidative stress. Thus， it was revealed that long-term intake of dietary ALE could result in renal impairment， and the results emphasized the control or intervention on dietary ALE to decrease to accumulated impairment on systemic health.

关键词：

A state-of-the-art review of the development of self-healing concrete for resilient infrastructure

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Structural and Civil Engineering 2024年第2期18卷 151-169页

作者： dong lu Xi JIANG Yao ZHANG Shaowei ZHANG Guoyang lu Zhen LENG Department of Civil and Environmental Engineering The Hong Kong Polytechnic UniversityHong Kong 999077China Laboratory of Fire Safety School of Safety Engineering and Emergency ManagementShijiazhuang Tiedao UniversityShijiazhuang 050043China Department of Architecture and Civil Engineering City University of Hong KongHong Kong 999077China

The brittleness of cement composites makes cracks almost inevitable,producing a serious limitation on the lifespan,resilience,and safety of concrete infrastructure.To address this brittleness,self-healing concrete has been developed for regaining its mechanical and durability properties after becoming cracked,thereby promising sustainable development of concrete infrastructure.This paper provides a comprehensive review of the latest developments in self-healing concrete.It begins by summarizing the methods used to evaluate the self-healing efficiency of concrete.Next,it compares strategies for achieving healing concrete.It then discusses the typical approaches for developing self-healing concrete.Finally,critical insights are proposed to guide future studies on the development of novel self-healing concrete.This review will be useful for researchers and practitioners interested in the field of self-healing concrete and its potential to improve the durability,resilience,and safety of concrete infrastructure.

关键词： resilient infrastructure sustainable concrete self-healing cracks

Polysaccharides from Chinese herbal medicine:a review on the hepatoprotective and molecular mechanism

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

Chinese Journal of Natural Medicines 2024年第1期22卷 4-14页

作者： LI Jifeng GUO Haolin dong Ying YUAN Shuo WEI Xiaotong ZHANG Yuxin dong lu WANG Fei BAI Ting YANG Yong Dalian Key Laboratory of Chronic Disease Research Center Dalian UniversityDalian 116622China Key Laboratory of Natural Medicines of the Changbai Mountain Ministry of EducationCollege of PharmacyYanbian UniversityYanji 133002China

Polysaccharides,predominantly extracted from traditional Chinese medicinal herbs such as Lycium barbarum,Angelica sinensis,Astragalus membranaceus,Dendrobium officinale,Ganoderma lucidum,and Poria cocos,represent principal bioactive constituents extensively utilized in Chinese medicine.These compounds have demonstrated significant anti-inflammatory capabilities,especially anti-liver injury activities,while exhibiting minimal adverse effects.This review summarized recent studies to elucidate the hepatoprotective efficacy and underlying molecular mechanisms of these herbal polysaccharides.It underscored the role of these polysaccharides in regulating hepatic function,enhancing immunological responses,and improving antioxidant capacities,thus contributing to the attenuation of hepatocyte apoptosis and liver protection.Analyses of molecular pathways in these studies revealed the intricate and indispensable functions of traditional Chinese herbal polysaccharides in liver injury management.Therefore,this review provides a thorough examination of the hepatoprotective attributes and molecular mechanisms of these medicinal polysaccharides,thereby offering valuable insights for the advancement of polysaccharide-based therapeutic research and their potential clinical applications in liver disease treatment.

关键词： Polysaccharides Hepatoprotective Chinese herbal medicine Mechanism

Real-time digital data of international passengers will shine in the precaution of epidemics

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

Intelligent Medicine 2023年第1期3卷 44-45页

作者： Naizhe Li lu dong MOE Key Laboratory For Biodiversity Science And Ecological Engineering College of Life SciencesBeijing Normal UniversityBeijing 100091China State Key Laboratory of Remote Sensing Science Center for Global Change and Public HealthCollege of Global Change and Earth System ScienceBeijing Normal UniversityBeijing 100091China

International movement plays an important role in spatial spread of infectious diseases.Here,we share two successful COVID-19 interventions based on real-time digital information collected from international passengers,which have been performed in Greece and China respectively.Both of the interventions demonstrated good performance and showed the potential of real-time digital data in containing the spread.However,several key points should not be ignored when we promote similar strategies.

关键词： Digital data Border surveillance strategy International movement Real-time

Solving Multivariate Polynomial Matrix Diophantine Equations with Gr?bner Basis Method

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

Journal of Systems Science & Complexity 2022年第1期35卷 413-426页

作者： XIAO Fanghui lu dong WANG Dingkang College of Mathematics and Statistics Hunan Normal UniversityChangsha 410006China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang UniversityBeijing 100191China School of Mathematical Sciences Beihang UniversityBeijing 100191China. KLMM Academy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China School of Mathematical Sciences University of Chinese Academy of SciencesBeijing 100049China

Different from previous viewpoints,multivariate polynomial matrix Diophantine equations are studied from the perspective of modules in this paper,that is,regarding the columns of matrices as elements in modules.A necessary and sufficient condition of the existence for the solution of equations is derived.Using powerful features and theoretical foundation of Gr?bner bases for modules,the problem for determining and computing the solution of matrix Diophantine equations can be solved.Meanwhile,the authors make use of the extension on modules for the GVW algorithm that is a signature-based Gr?bner basis algorithm as a powerful tool for the computation of Gr?bner basis for module and the representation coefficients problem directly related to the particular solution of equations.As a consequence,a complete algorithm for solving multivariate polynomial matrix Diophantine equations by the Gr?bner basis method is presented and has been implemented on the computer algebra system Maple.

关键词： Gr?bner basis matrix Diophantine equation module multivariate polynomial

Efficient Exploration for Multi-Agent Reinforcement Learning via Transferable Successor Features

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2022年第9期9卷 1673-1686页

作者： Wenzhang Liu lu dong Dan Niu Changyin Sun the School of Artificial Intelligence Anhui UniversityHefei 230039and also with the Peng Cheng LaboratoryShenzhen 518055China the School of Cyber Science and Engineering Southeast UniversityNanjing 211189China the School of Automation Southeast UniversityNanjing 210096China the School of Automation Southeast UniversityNanjing 210096and also with the Peng Cheng LaboratoryShenzhen 518055China

In multi-agent reinforcement learning(MARL),the behaviors of each agent can influence the learning of others,and the agents have to search in an exponentially enlarged joint-action space.Hence,it is challenging for the multi-agent teams to explore in the environment.Agents may achieve suboptimal policies and fail to solve some complex tasks.To improve the exploring efficiency as well as the performance of MARL tasks,in this paper,we propose a new approach by transferring the knowledge across tasks.Differently from the traditional MARL algorithms,we first assume that the reward functions can be computed by linear combinations of a shared feature function and a set of taskspecific weights.Then,we define a set of basic MARL tasks in the source domain and pre-train them as the basic knowledge for further use.Finally,once the weights for target tasks are available,it will be easier to get a well-performed policy to explore in the target domain.Hence,the learning process of agents for target tasks is speeded up by taking full use of the basic knowledge that was learned previously.We evaluate the proposed algorithm on two challenging MARL tasks:cooperative boxpushing and non-monotonic predator-prey.The experiment results have demonstrated the improved performance compared with state-of-the-art MARL algorithms.

关键词： Knowledge transfer multi-agent systems reinforcement learning successor features

New Results on the Equivalence of Bivariate Polynomial Matrices

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Science & Complexity 2023年第1期36卷 77-95页

作者： ZHENG Xiaopeng lu dong WANG Dingkang XIAO Fanghui KLMM Academy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China School of Mathematical Sciences University of Chinese Academy of SciencesBeijing 100049China School of Mathematics Southwest Jiaotong UniversityChengdu 610031China MOE-LCSM School of Mathematics and StatisticsHunan Normal UniversityChangsha 410081China

This paper investigates the equivalence problem of bivariate polynomial matrices.A necessary and sufficient condition for the equivalence of a square matrix with the determinant being some power of a univariate irreducible polynomial and its Smith form is proposed.Meanwhile,the authors present an algorithm that reduces this class of bivariate polynomial matrices to their Smith forms,and an example is given to illustrate the effectiveness of the algorithm.In addition,the authors generalize the main result to the non-square case.

关键词： Bivariate polynomial matrix matrix equivalence smith form