期刊
ACM TRANSACTIONS ON INTERACTIVE INTELLIGENT SYSTEMS
卷 11, 期 3-4, 页码 -出版社
ASSOC COMPUTING MACHINERY
DOI: 10.1145/3453173
关键词
Explainable AI; after-action review
资金
- DARPA [N66001-17-2-4030]
Explainable AI is important in assessing AI agents, and the After-Action Review approach can help individuals think logically and organize their thoughts when evaluating agents, leading to increased accuracy and consistency in assessments.
Explainable AI is growing in importance as AI pervades modern society, but few have studied how explainable AI 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 After-Action Review for AI (AAR/AI), to organize ways people assess reinforcement learning agents in a sequential decision-making environment. We then investigated what AAR/AI brought to human assessors in two qualitative studies. The first investigated AAR/AI to gather formative information, and the second built upon the results, and also varied the type of explanation (model-free vs. model-based) used in the AAR/AI process. Among the results were the following: (1) participants reporting that AAR/AI helped to organize their thoughts and think logically about the agent, (2) AAR/AI encouraged participants to reason about the agent from a wide range of perspectives, and (3) participants were able to leverage AAR/AI with the model-based explanations to falsify the agent's predictions.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据