Social Structures and Artifacts for Intelligent Agent Systems

智能代理系统的社会结构和工件

• 批准号: 9872062
• 负责人: Nicholas Findler
• 金额: $ 13.27万
• 依托单位: Arizona State University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 1998
• 资助国家: 美国
• 起止时间: 1998-09-15 至 2000-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9872062&HistoricalAwards=false
• 关键词: Social; Structures; Artifacts; Intelligent; Agent

This award supports research into the definition and development of a pattern language and pattern book for multi-agent systems, and the development of formal social structures and generalized social software artifacts for agent-based systems. The artifacts implementing the social structures are software-embodied entities existing separately from the intelligent agents that interact with them. Coordination and control tasks are divided between agents and the social artifacts with which they interact. This division of labor allows the use of coordination mechanisms designed to control the combinatorial explosions of coordination costs that are expected in systems with large numbers of agents. It also enables explicit control of emergent social behavior in agent-based systems. The pattern language will improve expertise transfer between developers and researchers in intelligent agent systems, and the social structures and artifacts will allow creation of coordination algorithms scalable to systems with large numbers of agents. http://www.eas.asu.edu/~gcss/

该奖项支持对多代理系统的模式语言和模式书的定义和开发的研究，以及基于代理的系统的正式社会结构和通用社会软件工件的开发。 实现社会结构的工件是软件实体，与与其交互的智能代理分开存在。 协调和控制任务在代理和与其交互的社交工件之间划分。这种分工允许使用协调机制，旨在控制具有大量代理的系统中预期的协调成本的组合爆炸。它还可以对基于代理的系统中出现的社交行为进行显式控制。 模式语言将改善智能代理系统中开发人员和研究人员之间的专业知识转移，而社交结构和工件将允许创建可扩展到具有大量代理的系统的协调算法。 http://www.eas.asu.edu/~gcss/