Agent-Based Explanations in AI: Towards an Abstract Framework

   page       BibTeX_logo.png       attach   
Giovanni Ciatto, Michael I. Schumacher, Andrea Omicini, Davide Calvaresi
Davide Calvaresi, Amro Najjar, Michael Winikoff, Kary Främling (eds.)
Explainable, Transparent Autonomous Agents and Multi-Agent Systems, pages 3-20
Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence) 12175
Springer, Cham
2020

Recently, the eXplainable AI (XAI) research community has focused on developing methods making Machine Learning (ML) predictors more interpretable or explainable. Unfortunately, researchers are struggling to converge towards an unambiguous definition of notions such as interpretation or explanation—which are often (and mistakenly) used interchangeably. Furthermore, in spite of the sound metaphors that Multi-Agent System (MAS) could easily provide to address such a challenge, an agent-oriented perspective on the topic is still missing. Thus, this paper proposes an abstract and formal framework for XAI-based MAS, reconciling notions and results from the literature.

keywordsExplainable artificial intelligence; Multi-agent systems; Understandability; Explainability; Interpretability
origin event
worldEXTRAAMAS 2020@AAMAS 2020
journal or series
book Lecture Notes in Computer Science (LNCS)
container publication
page_white_acrobatAn Abstract Framework for Agent-Based Explanations in AI (paper in proceedings, 2020) — Giovanni Ciatto, Davide Calvaresi, Michael I. Schumacher, Andrea Omicini
works as
reference publication for talk
page_white_powerpointAgent-Based Explanations in AI: Towards an Abstract Framework (EXTRAAMAS 2020@AAMAS 2020, 09/05/2020) — Davide Calvaresi (Giovanni Ciatto, Michael I. Schumacher, Andrea Omicini, Davide Calvaresi)