0


通过多代理组织缩放人工智能

Scaling AI Through Multi-Agent Organizations
课程网址: http://videolectures.net/ijcai09_lesser_saitmao/  
主讲教师: Victor Lesser
开课单位: 马萨诸塞大学
开课时间: 2009-07-22
课程语种: 英语
中文简介:
规模化仍然是人工智能面临的一大挑战。Lesser一直在使用组织控制来构建具有数百到数千个智能代理的多代理系统。这种方法也可以用来构建具有广泛和异构知识的复杂人工智能系统。组织控制是一种多层次的方法,在这种方法中,组织目标、角色和职责是动态开发、分配和维护的,以作为单个代理做出详细的操作控制决策的指导方针。Less将说明组织控制在三个分布式应用领域的应用:(1)自适应传感器和解释车辆跟踪网络,(2)点对点信息搜索和检索系统,以及(3)自我改进的任务分配系统。他将强调在不确定和动态环境中,外部导向和自我导向代理活动之间的重要平衡。然后,他将提出持续不断的研究挑战,包括如何自动化组织的设计,并随着条件的变化不断发展,创建一个组织定位的代理,以及评估和预测组织的绩效。
课程简介: Scaling remains one of the grand challenges for AI. Lesser has been using organizational control to build multiagent systems with hundreds to thousands of intelligent agents. This approach can also be used to structure complex AI systems with extensive and heterogeneous knowledge. Organizational control is a multi-level approach in which organizational goals, roles, and responsibilities are dynamically developed, distributed, and maintained to serve as guidelines for making detailed operational control decisions by the individual agents. Lesser will illustrate the use of organizational control in three distributed application areas: (1) an adaptive sensor and interpretation vehicle-tracking network, (2) a peer-to-peer information search and retrieval system, and (3) a self-improving task allocation system. He will highlight the important balance between externally-directed and self-directed agent activities in uncertain and dynamic environments. Then he will present the continuing research challenges, including how to automate the design of an organization and evolve it as conditions change, create an organizationally situated agent, and evaluate and predict an organization’s performance.
关 键 词: 缩放; 人工智能; 信息搜索; 检索系统; 自主代理活动
课程来源: 视频讲座网
最后编审: 2020-07-13:yumf
阅读次数: 48