Contrastive Explanations of Plans through Model Restrictions
| Autor: | Daniele Magazzeni, Senka Krivic, David E. Smith, Michael Cashmore, Derek Long, Benjamin Krarup |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Iterative and incremental development Operations research Computer Science - Artificial Intelligence Computer science media_common.quotation_subject Context (language use) 02 engineering and technology Plan (drawing) Constraint (information theory) 03 medical and health sciences Negotiation Artificial Intelligence (cs.AI) 0302 clinical medicine Artificial Intelligence Taxonomy (general) Automated planning and scheduling 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Construct (philosophy) 030217 neurology & neurosurgery media_common |
| Zdroj: | Journal of Artificial Intelligence Research. 72:533-612 |
| ISSN: | 1076-9757 |
| DOI: | 10.1613/jair.1.12813 |
| Popis: | 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. Comment: 80 pages, 32 figures, 7 tables |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|