检索结果-南通市图书馆

Efficient multiagent Policy Optimization Based on Weighted Estimators in Stochastic Cooperative Environments

在线全文

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2020年第2期35卷 268-280页

作者： Yan Zheng Jian-Ye Hao Zong-Zhang Zhang Zhao-Peng Meng Xiao-Tian Hao College of Intelligence and Computing Tianjin UniversityTianjin 300350China National Key Laboratory for Novel Software Technology Nanjing UniversityNanjing 210023China

multiagent deep reinforcement learning (MA-DRL) has received increasingly wide attention. Most of the existing MA-DRL algorithms, however, are still inefficient when faced with the non-stationarity due to agents changing behavior consistently in stochastic environments. This paper extends the weighted double estimator to multiagent domains and proposes an MA-DRL framework, named Weighted Double Deep Q-Network (WDDQN). By leveraging the weighted double estimator and the deep neural network, WDDQN can not only reduce the bias effectively but also handle scenarios with raw visual inputs. To achieve efficient cooperation in multiagent domains, we introduce a lenient reward network and scheduled replay strategy. Empirical results show that WDDQN outperforms an existing DRL algorithm (double DQN) and an MA-DRL algorithm (lenient Q-learning) regarding the averaged reward and the convergence speed and is more likely to converge to the Pareto-optimal Nash equilibrium in stochastic cooperative environments.

关键词： deep reinforcement learning multiagent system weighted double estimator lenient reinforcement learning cooperative Markov game

RAO Logic for multiagent Framework

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 Computer Science & Technology 1999年第4期14卷 393-400页

作者：史忠植田启家李云峰 InstituteofComputingTechnology ChineseAcademyofSciencesPR.China

In this paper, we deal with how agents reason about knowledgeof others in multiagent system. We first present a knowledge representation frame-work called reasoning about others (RAO) which is designed specifically to representconcepts and rules used in reasoning about knowledge of others. From a class ofsentences usually taken by people in daily life to reason about others, a rule calledposition exchange principle (PEP) is abstracted. PEP is described as an axiomscheme in RAO and regarded as a basic rule for agents to reason about others, andfurther it has the similar form and role to modus ponens and (K) axiom of knowl-edge logic. The relationship between speech acts and common sense is also discussedwhich is necessary for RAO. Based on ideas from situation calculus, this relationshipis characterized by an axiom schema in RAO. Our theories are also demonstrated byan example.

关键词： multiagent RAO logic position exchange principle (PFP)

A multiagent-based Organizational Decision Support System

在线全文

学校读者我要写书评

暂无评论

High Technology Letters 1998年第2期4卷 17-20页

作者：梁浩

１．ＩｎｔｒｏｄｕｃｔｉｏｎＤｕｒｉｎｇｔｈｅｒｅｃｅｎｔｄｅｃａｄｅｓ，ｔｈｅｐｈｉｌｏｓｏｐｈｙｏｆＣｏｎｃｕｒｅｎｔＥｎｇｉｎｅｅｒｉｎｇ（ＣＥ）ｈａｓｂｅｅｎａｐｐｌｉｅｄｉｎｍａｎｕｆａｃｔｕｒｉｎｇｅｎ... 详细信息

１．ＩｎｔｒｏｄｕｃｔｉｏｎＤｕｒｉｎｇｔｈｅｒｅｃｅｎｔｄｅｃａｄｅｓ，ｔｈｅｐｈｉｌｏｓｏｐｈｙｏｆＣｏｎｃｕｒｅｎｔＥｎｇｉｎｅｅｒｉｎｇ（ＣＥ）ｈａｓｂｅｅｎａｐｐｌｉｅｄｉｎｍａｎｕｆａｃｔｕｒｉｎｇｅｎｔｅｒｐｒｉｓｅｓａｌｏｖｅｒｔｈ...

关键词： ODSS multiagent system

基于multiagent技术的计算机市场协同咨询专家系统

在线全文

学校读者我要写书评

暂无评论

计算机工程与科学 1998年第2期20卷 40-45页

作者：杨福泉北京市外国企业服务总公司计算机中心

本文结合作者自己的体会，收集整理知名专家的经验和意见，利用Ｍｕｌｔｉａ－ｇｅｎｔ的新概念和技术成果，设计了一个基于因特网环境和Ｍｕｌｔｉａｇｅｎｔ技术的计算机市场协同咨询专家系统。

关键词： multiagent 市场咨询专家系统市场分析

基于multiagent的社交网络舆情传播模型

在线全文

学校读者我要写书评

暂无评论

青岛大学学报（工程技术版） 2021年第2期36卷 28-35页

作者：董田田李军王继荣青岛大学计算机科学技术学院山东青岛266071 青岛大学机电工程学院山东青岛266071

为分析与预测社交网络中舆情传播过程和演化趋势,本文基于multiagent分布式技术,建立了社交网络舆情传播模型,研究社交网络舆情传播方式,并根据Agent的行为和状态特性,对Agent进行分类,分析Agent的属性特征,通过剖析Agent个体之间的交... 详细信息

为分析与预测社交网络中舆情传播过程和演化趋势,本文基于multiagent分布式技术,建立了社交网络舆情传播模型,研究社交网络舆情传播方式,并根据Agent的行为和状态特性,对Agent进行分类,分析Agent的属性特征,通过剖析Agent个体之间的交互微观行为,依据信息价值时效性、信息源覆盖率和信息关注度,对转发行为的影响进行讨论,给出了Agent的决策规则,以网络结构方式体现Agent之间的内在联系。为验证模型的有效性,基于Agent的仿真平台,采用Netlogo 6.0.4进行模拟仿真分析。仿真结果表明,舆情信息的传播与信息价值呈正相关,信息价值越大,越有利于舆情信息的传播,且信息源的覆盖率与转发Agent数和中止Agent数成正相关,信息关注度对舆情传播影响甚大,说明该模型能准确分析和预测网络中舆情传播的演化趋势。该研究对相关人员了解社交网络中舆情的传播具有重要意义。

关键词： multiagent 社交网络舆情话题传播模型价值时效性信息源覆盖率

Systemic Risks: A Homomorphic Approach on the Basis of Complexity Science

在线全文

学校读者我要写书评

暂无评论

International Journal of Disaster Risk Science 2018年第3期9卷 292-305页

作者： Klaus Lucas Ortwin Renn Carlo Jaeger Saini Yang Institute of Technical Thermodynamics Aachen University Institute for Advanced Sustainability Studies (IASS) Economic and Social Science Department University of Stuttgart Academy of Disaster Reduction and Emergency Management School of Geography Beijing Normal University Global Climate Forum Key Laboratory of Environmental Change and Natural Disasters Ministry of Education Beijing Normal University

Although the notion of systemic risk gained prominence with respect to financial systems, it is a generic term that refers to risks of increasing importance in many domains—risks that cannot be tackled by conventional techniques of risk management and governance. We build on a domain-overarching definition of systemic risks by highlighting crucial properties that distinguish them from conventional risks and plain disasters. References to typical examples from various domains are included. Common features of systemic risks in different domains—such as the role of agents and emergence phenomena, tipping and cascading, parameters indicating instability, and historicity—turn out to be more than noncommittal empirical observations. Rather these features can be related to fundamental theory for relatively simple and well-understood systems in physics and chemistry. A crucial mechanism is the breakdown of macroscopic patterns of whole systems due to feedback reinforcing actions of agents on the microlevel, where the reinforcement is triggered by boundary conditions moving beyond critical tipping points.Throughout the whole article, emphasis is placed on the role of complexity science as a basis for unifying the phenomena of systemic risks in widely different domains.

关键词： Complexity science Integrated risk governance multiagent modeling Systemic risks

Autoregressive moving average model as a multi-agent routing protocol for wireless sensor networks

在线全文

学校读者我要写书评

暂无评论

Journal of Beijing Institute of Technology 2011年第3期20卷 421-426页

作者：黄如黄浩陈志华何兴勇 School of Information Science and Engineering East China University of Science and Technology Department of Information Science and Engineering Xinjiang University

A prediction-aided routing algorithm based on ant colony optimization mode （PRACO） to achieve energy-aware data-gathering routing structure in wireless sensor networks （WSN） is presented. We adopt autoregressive moving average model （ARMA） to predict dynamic tendency in data traffic and deduce the construction of load factor, which can help to reveal the future energy status of sensor in WSN. By checking the load factor in heuristic factor and guided by novel pheromone updating rule, multi-agent, i. e. , artificial ants, can adaptively foresee the local energy state of networks and the corresponding actions could be taken to enhance the energy efficiency in routing construction. Compared with some classic energy-saving routing schemes, the simulation results show that the proposed routing building scheme can ① effectively reinforce the robustness of routing structure by mining the temporal associability and introducing multi-agent optimization to balance the total energy cost for data transmission, ② minimize the total communication consumption, and ③prolong the lifetime of networks.

关键词： wireless sensor networks （WSN） autoregressive moving average ARMA） multiagent routing robustness

Towards a next-generation production system for industrial robots: A CPS-based hybrid architecture for smart assembly shop floors with closed-loop dynamic cyber physical interactions

在线全文

学校读者我要写书评

暂无评论

Frontiers of Mechanical Engineering 2020年第1期15卷 1-11页

作者： Qingmeng TAN Yifei TONG Shaofeng WU Dongbo LI School of Mechanical Engineering Nanjing University of Science&TechnologyNanjing 210094China

Given the multiple varieties and small batches,the production of industrial robots faces the ongoing challenges of flexibility,self-organization,self-configuration,and other“smart”requirements.Recently,cyber physical systems have provided a promising solution for the requirements mentioned above.Despite recent progress,some critical issues have not been fully addressed at the shop floor level,including dynamic reorganization and reconfiguration,ubiquitous networking,and time constrained computing.Toward the next generation production system for industrial robots,this study proposed a hybrid architecture for smart assembly shop floors with closed-loop dynamic cyber physical interactions.Aiming for dynamic reorganization and reconfiguration,the study also proposed modularized smart assembly units for the deployment of physical assembly processes.Enabling technologies,such as multiagent system(MAS),self-organized wireless sensor actuator networks,and edge computing,were discussed and then integrated into the proposed architecture.Furthermore,a multijoint robot assembly process was selected as a target scenario.Thus,an MAS was developed to simulate the coordination and negotiation mechanisms for the proposed architecture on the basis of the Java Agent Development Framework platform.

关键词： cyber physical system robot assembly multiagent system architecture

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

应用multiagent优化自主导航系统

微计算机应用 2005年第4期26卷 506-508,511页

作者：陈红英华南师范大学计算机学院

本文针对自主导航系统的多任务执行时容易产生的冲突问题,将系统进行功能分解,采用multiagent技术,由各个智能体共同执行完成系统功能。着重介绍了系统中各个代理的个体规划和社会规划,对各个Agent的可能产生的行为冲突和资源冲突进行... 详细信息

本文针对自主导航系统的多任务执行时容易产生的冲突问题,将系统进行功能分解,采用multiagent技术,由各个智能体共同执行完成系统功能。着重介绍了系统中各个代理的个体规划和社会规划,对各个Agent的可能产生的行为冲突和资源冲突进行了分析并提出相应避让策略。系统的实现采用了多线程技术,各个Agent之间的通信采用KQML的简化集。改进后的系统性能良好,无冲突现象。

关键词：自主导航系统 multiagent Agent技术优化应用多线程技术冲突问题功能分解系统功能社会规划资源冲突 KQML 系统性能多任务智能体无冲突执行代理