TY - GEN
T1 - Keeping it "organized and logical"
T2 - 25th ACM International Conference on Intelligent User Interfaces, IUI 2020
AU - Mai, Theresa
AU - Khanna, Roli
AU - Dodge, Jonathan
AU - Irvine, Jed
AU - Lam, Kin Ho
AU - Lin, Zhengxian
AU - Kiddle, Nicholas
AU - Newman, Evan
AU - Raja, Sai
AU - Matthews, Caleb
AU - Perdriau, Christopher
AU - Burnett, Margaret
AU - Fern, Alan
N1 - Publisher Copyright:
© ACM.
PY - 2020/3/17
Y1 - 2020/3/17
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85082484443&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85082484443&partnerID=8YFLogxK
U2 - 10.1145/3377325.3377525
DO - 10.1145/3377325.3377525
M3 - Conference contribution
AN - SCOPUS:85082484443
T3 - International Conference on Intelligent User Interfaces, Proceedings IUI
SP - 465
EP - 476
BT - Proceedings of the 25th International Conference on Intelligent User Interfaces, IUI 2020
PB - Association for Computing Machinery
Y2 - 17 March 2020 through 20 March 2020
ER -