Provenance-Based Assessment of Plans in Context

Autor:	Friedman, Scott E., Goldman, Robert P., Freedman, Richard G., Kuter, Ugur, Geib, Christopher, Rye, Jeffrey
Rok vydání:	2020
Předmět:	Computer Science - Artificial Intelligence Computer Science - Human-Computer Interaction
Zdroj:	Proceedings of the 2020 ICAPS Workshop on Explainable AI Planning
Druh dokumentu:	Working Paper
Popis:	Many real-world planning domains involve diverse information sources, external entities, and variable-reliability agents, all of which may impact the confidence, risk, and sensitivity of plans. Humans reviewing a plan may lack context about these factors; however, this information is available during the domain generation, which means it can also be interwoven into the planner and its resulting plans. This paper presents a provenance-based approach to explaining automated plans. Our approach (1) extends the SHOP3 HTN planner to generate dependency information, (2) transforms the dependency information into an established PROV-O representation, and (3) uses graph propagation and TMS-inspired algorithms to support dynamic and counter-factual assessment of information flow, confidence, and support. We qualified our approach's explanatory scope with respect to explanation targets from the automated planning literature and the information analysis literature, and we demonstrate its ability to assess a plan's pertinence, sensitivity, risk, assumption support, diversity, and relative confidence. Comment: 9 pages, 7 figures, including in Proceedings of the 2020 ICAPS Workshop on Explainable AI Planning (XAIP)
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2011.01774 Zobrazit plný text záznamu View this record from Arxiv