PLEASE: Generating Personalized Explanations in Human-Aware Planning
PLEASE: Generating Personalized Explanations in Human-Aware Planning
复制标题
DOI：
10.3233/faia230543
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
S. Vasileiou;William Yeoh
中科院分区：
文献类型：
--
作者：
S. Vasileiou;William Yeoh
． 模型协调问题（MRPs）及其变体，基于逻辑的MRPs (L-MRPs)，已经成为解决可解释计划问题的流行方法。MRP和L-MRP方法都假设解释代理可以访问接受解释的人类用户的假设模型，并且它将自己的模型与人类模型进行协调，以找到差异，以便当它们作为解释提供给人类时，他们会理解它们。然而，在实际应用中，代理可能对人类的实际模型相当不确定，错误的假设可能导致不连贯或难以理解的解释。在本文中，我们提出了一个不太严格的要求：代理可以访问人类已知的特定于任务的词汇表，如果可用，可以访问捕获机密信息的人类模型。我们的目标是找到一种个性化的解释，这是一种相对于人类的词汇和模型处于适当抽象层次的解释。我们使用一种基于逻辑的知识遗忘方法来生成抽象，提出了一个与L-MRP方法兼容的简单框架，并通过计算和人类用户实验来评估其有效性。
. Model Reconciliation Problems (MRPs) and their variant, Logic-based MRPs (L-MRPs), have emerged as popular meth-ods for explainable planning problems. Both MRP and L-MRP approaches assume that the explaining agent has access to an assumed model of the human user receiving the explanation, and it reconciles its own model with the human model to find the differences such that when they are provided as explanations to the human, they will understand them. However, in practical applications, the agent is likely to be fairly uncertain on the actual model of the human and wrong assumptions can lead to incoherent or unintelligible explanations. In this paper, we propose a less stringent requirement: The agent has access to a task-specific vocabulary known by the human and, if available, a human model capturing confidently-known information. Our goal is to find a personalized explanation , which is an explanation that is at an appropriate abstraction level with respect to the human’s vocabulary and model. Using a logic-based method called knowledge forgetting for generating abstractions, we propose a simple framework compatible with L-MRP approaches, and evaluate its efficacy through computational and human user experiments.