'Why did my AI agent lose?': Visual Analytics for Scaling Up After-Action Review

Delyar Tabatabai, Anita Ruangrotsakun, Jed Irvine, Jonathan Dodge, Zeyad Shureih, Kin Ho Lam, Margaret Burnett, Alan Fern, Minsuk Kahng

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

3 Scopus citations

Abstract

How can we help domain-knowledgeable users who do not have expertise in AI analyze why an AI agent failed? Our research team previously developed a new structured process for such users to assess AI, called After-Action Review for AI (AAR/AI), consisting of a series of steps a human takes to assess an AI agent and formalize their understanding. In this paper, we investigate how the AAR/AI process can scale up to support reinforcement learning (RL) agents that operate in complex environments. We augment the AAR/AI process to be performed at three levels - episode-level, decision-level, and explanation-level - and integrate it into our redesigned visual analytics interface. We illustrate our approach through a usage scenario of analyzing why a RL agent lost in a complex real-time strategy game built with the StarCraft 2 engine. We believe integrating structured processes like AAR/AI into visualization tools can help visualization play a more critical role in AI interpretability.

Original languageEnglish (US)
Title of host publicationProceedings - 2021 IEEE Visualization Conference - Short Papers, VIS 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages16-20
Number of pages5
ISBN (Electronic)9781665433358
DOIs
StatePublished - 2021
Event2021 IEEE Visualization Conference, VIS 2021 - Virtual, Online, United States
Duration: Oct 24 2021Oct 29 2021

Publication series

NameProceedings - 2021 IEEE Visualization Conference - Short Papers, VIS 2021

Conference

Conference2021 IEEE Visualization Conference, VIS 2021
Country/TerritoryUnited States
CityVirtual, Online
Period10/24/2110/29/21

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Media Technology
  • Modeling and Simulation

Fingerprint

Dive into the research topics of ''Why did my AI agent lose?': Visual Analytics for Scaling Up After-Action Review'. Together they form a unique fingerprint.

Cite this