Generating Explanations Based on Markov Decision Processes
Generating Explanations Based on Markov Decision Processes
复制标题
基于马尔可夫决策过程生成解释
DOI：
--
复制
发表时间：
2009
期刊：
影响因子：
--
通讯作者：
A. Reyes
中科院分区：
文献类型：
--
作者：
F. Elizalde;L. Sucar;J. Noguez;A. Reyes
在本文中，我们解决的问题，解释马尔可夫决策过程（MDP）产生的建议。我们提出了一个自动解释生成机制，由两个主要阶段组成。在第一阶段中，基于MDP的因子化表示来获得给定当前状态的最相关变量。相关变量被定义为在给定的状态和动作下对效用影响最大的因素，是解释生成机制中的关键要素。在第二阶段，基于一个通用的模板，通过结合从MDP获得的信息与领域知识表示为一个框架系统生成的解释。由MDP给出的状态和动作以及相关变量被用作知识库的指针，以提取相关信息并填充解释模板。通过这种方式，MDP给出的建议的解释可以在线生成并合并到智能助理中。我们已经评估了这种机制，在智能助理发电厂操作员培训。实验结果表明，自动生成的解释是相似的领域专家。
In this paper we address the problem of explaining the recommendations generated by a Markov decision process (MDP). We propose an automatic explanation generation mechanism that is composed by two main stages. In the first stage, the most relevant variable given the current state is obtained, based on a factored representation of the MDP. The relevant variable is defined as the factor that has the greatest impact on the utility given certain state and action, and is a key element in the explanation generation mechanism. In the second stage, based on a general template, an explanation is generated by combing the information obtained from the MDP with domain knowledge represented as a frame system. The state and action given by the MDP, as well as the relevant variable, are used as pointers to the knowledge base to extract the relevant information and fill---in the explanation template. In this way, explanations of the recommendations given by the MDP can be generated on---line and incorporated to an intelligent assistant. We have evaluated this mechanism in an intelligent assistant for power plant operator training. The experimental results show that the automatically generated explanations are similar to those given by a domain expert.