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

Research output: Contribution to journalArticlepeer-review

Abstract

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.

Original languageEnglish (US)
Article number103570
JournalArtificial Intelligence
Volume301
DOIs
StatePublished - Dec 2021

Keywords

  • Abstractions
  • Contrastive explanations
  • Explanations for plans

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Using state abstractions to compute personalized contrastive explanations for AI agent behavior'. Together they form a unique fingerprint.

Cite this