Contrastive Explanations of Plans Through Model Restrictions

TL;DR

This paper introduces a model restriction approach for explainable AI planning, enabling contrastive explanations during plan negotiation, supported by user studies and formal definitions in PDDL2.1.

Contribution

It formalizes a novel iterative model restriction method for contrastive explanations in AI planning, validated through user studies and complexity analysis.

Findings

User questions are often contrastive, asking 'why A rather than B'

The model restriction approach improves explanation clarity in plan negotiation

Empirical evaluation shows the approach's computational feasibility

Abstract

In automated planning, the need for explanations arises when there is a mismatch between a proposed plan and the user's expectation. We frame Explainable AI Planning in the context of the plan negotiation problem, in which a succession of hypothetical planning problems are generated and solved. The object of the negotiation is for the user to understand and ultimately arrive at a satisfactory plan. We present the results of a user study that demonstrates that when users ask questions about plans, those questions are contrastive, i.e. "why A rather than B?". We use the data from this study to construct a taxonomy of user questions that often arise during plan negotiation. We formally define our approach to plan negotiation through model restriction as an iterative process. This approach generates hypothetical problems and contrastive plans by restricting the model through constraints implied by user questions. We formally define model-based compilations in PDDL2.1 of each constraint derived from a user question in the taxonomy, and empirically evaluate the compilations in terms of computational complexity. The compilations were implemented as part of an explanation framework that employs iterative model restriction. We demonstrate its benefits in a second user study.