如何对信息进行折扣：传感代理系统中的信息流与体系结构的出现][How to discount Information: Information flow in sensing-acting systems and the emergence of heirarchies]

如何对信息进行折扣：传感代理系统中的信息流与体系结构的出现 How to discount Information: Information flow in sensing-acting systems and the emergence of heirarchies


课程网址:	http://videolectures.net/cyberstat2012_tishby_bellman_equation/
主讲教师:	Naftali Tishby
开课单位:	希伯来大学
开课时间:	2012-10-16
课程语种:	英语
中文简介:	我们认为，最佳传感和控制的一致表述必须包括信息术语，从而产生标准POMDP设置的扩展。为了使标准奖励/成本条款与信息术语一致，同时仍允许易于计算，必须改变标准的时间均匀性。我们认为，这可以通过对信息价值权衡进行连续改进来实现，这也会导致层次结构和反向层次结构的出现，从而产生感知和规划。
课程简介:	We argue that consistent formulation of optimal sensing and control must include information terms, yielding an extension of the standard POMDP setting. To make the standard reward/costs terms consistent with the information terms, while still allowing tractable computation, the standard uniformity of time must be altered. We argue that this can be done by successive refinement of the information-value tradeoff, which also leads to the emergence of hierarchies and reverse-hierarchies for both perception and planning.
关键词:	传感; 控制; 时间均匀性
课程来源:	视频讲座网
最后编审:	2019-03-16：lxf
阅读次数:	46

境外开放课程导航