0


用有限的信息解决决策问题

Solving Decision Problems with Limited Information
课程网址: http://videolectures.net/nips2011_maua_information/  
主讲教师: Denis D. Mauá
开课单位: Dalle-Molle感知人工智能研究所
开课时间: 2012-01-19
课程语种: 英语
中文简介:
我们提出了一种新算法,用于精确解决作为影响图表示的决策问题。我们不需要通常的假设,即不遗忘和规律,这使我们能够解决有限信息的问题。该算法实现了复杂的变量消除过程,经验证明,在随机生成的多达150个变量和$ 10 ^ {64} $策略的问题中,它优于现有技术的算法。
课程简介: We present a new algorithm for exactly solving decision-making problems represented as an influence diagram. We do not require the usual assumptions of no forgetting and regularity, which allows us to solve problems with limited information. The algorithm, which implements a sophisticated variable elimination procedure, is empirically shown to outperform a state-of-the-art algorithm in randomly generated problems of up to 150 variables and $10^{64}$ strategies.
关 键 词: 变量消除; 随机生成; 新算法
课程来源: 视频讲座网
最后编审: 2019-07-26:cwx
阅读次数: 24