Using state abstractions to compute personalized contrastive explanations for AI agent behavior

Using state abstractions to compute personalized contrastive explanations for AI agent behavior
复制标题

使用状态抽象来计算人工智能代理行为的个性化对比解释

DOI:
10.1016/j.artint.2021.103570
复制
发表时间:
2021
影响因子:
14.4
通讯作者:
Kambhampati, Subbarao
Kambhampati, Subbarao
中科院分区:
计算机科学2区
文献类型:
--
作者:
Sreedharan, Sarath;Srivastava, Siddharth;Kambhampati, Subbarao

文献摘要

参考文献

被引文献

相似文献

人工智能研究界对开发能够向用户解释其行为的自主系统越来越感兴趣。然而,为不同专业水平的用户提供计算解释的问题却很少受到研究关注。我们提出了一种解决此问题的方法,将用户对任务的理解表示为规划者使用的领域模型的抽象。我们提出了在这种抽象人类模型未知的情况下生成最小解释的算法。我们减少了对抽象模型空间的搜索生成解释的问题,并表明虽然完整的问题是 NP 困难的,但贪心算法可以提供最佳解决方案的良好近似。我们的经验表明,我们的方法可以有效地计算各种问题的解释,并且还可以进行用户研究来测试状态抽象在解释中的效用。
There is a growing interest within the AI research community in developing autonomous systems capable of explaining their behavior to users. However, the problem of computing explanations for users of different levels of expertise has received little research attention. We propose an approach for addressing this problem by representing the user's understanding of the task as an abstraction of the domain model that the planner uses. We present algorithms for generating minimal explanations in cases where this abstract human model is not known. We reduce the problem of generating an explanation to a search over the space of abstract models and show that while the complete problem is NP-hard, a greedy algorithm can provide good approximations of the optimal solution. We empirically show that our approach can efficiently compute explanations for a variety of problems and also perform user studies to test the utility of state abstractions in explanations.
DOI: --
发表时间: 2019
期刊: International Joint Conference on Artificial Intelligence
影响因子: --
作者:
Sreedharan, Sarath;Srivastava, Siddharth;Smith, David;Kambhampati, Subbarao.
通讯作者: Kambhampati, Subbarao.
可解释人工智能(XAI)中的反事实:来自人类推理的证据
DOI: --
发表时间: 2019
期刊: International Joint Conference on Artificial Intelligence
影响因子: --
作者:
R. Byrne
通讯作者: R. Byrne
解释性概括,第二部分:管道解释深度
DOI: --
发表时间: 2003
期刊:
影响因子: --
作者:
Christopher R. Hitchcock;J. Woodward
通讯作者: J. Woodward
DOI: --
发表时间: --
期刊: 2012 7th ACM/IEEE International Conference on Human-Robot Interaction (HRI)
影响因子: --
作者:
通讯作者: --
DOI: 10.1080/00213624.1983.11504161
发表时间: 1983
影响因子: 0.7
作者:
James Webb
通讯作者: James Webb