Keeping it "organized and logical": After-action review for AI (AAR/AI)

Theresa Mai, Roli Khanna, Jonathan Dodge, Jed Irvine, Kin Ho Lam, Zhengxian Lin, Nicholas Kiddle, Evan Newman, Sai Raja, Caleb Matthews, Christopher Perdriau, Margaret Burnett, Alan Fern

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Scopus citations

Abstract

Explainable AI (XAI) is growing in importance as AI pervades modern society, but few have studied how XAI can directly support people trying to assess an AI agent. Without a rigorous process, people may approach assessment in ad hoc ways - -leading to the possibility of wide variations in assessment of the same agent due only to variations in their processes. AAR, or After-Action Review, is a method some military organizations use to assess human agents, and it has been validated in many domains. Drawing upon this strategy, we derived an AAR for AI, to organize ways people assess reinforcement learning (RL) agents in a sequential decision-making environment. The results of our qualitative study revealed several strengths and weaknesses of the AAR/AI process and the explanations embedded within it.

Original languageEnglish (US)
Title of host publicationProceedings of the 25th International Conference on Intelligent User Interfaces, IUI 2020
PublisherAssociation for Computing Machinery
Pages465-476
Number of pages12
ISBN (Electronic)9781450371186
DOIs
StatePublished - Mar 17 2020
Event25th ACM International Conference on Intelligent User Interfaces, IUI 2020 - Cagliari, Italy
Duration: Mar 17 2020Mar 20 2020

Publication series

NameInternational Conference on Intelligent User Interfaces, Proceedings IUI

Conference

Conference25th ACM International Conference on Intelligent User Interfaces, IUI 2020
Country/TerritoryItaly
CityCagliari
Period3/17/203/20/20

All Science Journal Classification (ASJC) codes

  • Software
  • Human-Computer Interaction

Fingerprint

Dive into the research topics of 'Keeping it "organized and logical": After-action review for AI (AAR/AI)'. Together they form a unique fingerprint.

Cite this