Redefining Counterfactual Explanations for Reinforcement Learning: Overview, Challenges and Opportunities
ACM Computing Surveys · 31.10.2024 · 56 (9) · 1-33
DOI: 10.1145/3648472 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 24.04.2024. Verfasst von Jasmina Gajcin und 1 weiteren Autor:innen. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 102 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science Foundation Ireland, SFI Frontiers for the Future.
Abstract (Originalsprache)
While AI algorithms have shown remarkable success in various fields, their lack of transparency hinders their application to real-life tasks. Although explanations targeted at non-experts are necessary for user trust and human-AI collaboration, the majority of explanation methods for AI are focused on developers and expert users. Counterfactual explanations are local explanations that offer users advice on what can be changed in the input for the output of the black-box model to change. Counterfactuals are user-friendly and provide actionable advice for achieving the desired output from the AI system. While extensively researched in supervised learning, there are few methods applying them to reinforcement learning (RL). In this work, we explore the reasons for the underrepresentation of a powerful explanation method in RL. We start by reviewing the current work in counterfactual explanations in supervised learning. Additionally, we explore the differences between counterfactual explanations in supervised learning and RL and identify the main challenges that prevent the adoption of methods from supervised in reinforcement learning. Finally, we redefine counterfactuals for RL and propose research directions for implementing counterfactuals in RL.
Förderung
- Science Foundation Ireland
- SFI Frontiers for the Future
Zitieren
APA
Gajcin, J., & Dusparic, I. (2024). Redefining Counterfactual Explanations for Reinforcement Learning: Overview, Challenges and Opportunities. ACM Computing Surveys, 56(9), 1-33. https://doi.org/10.1145/3648472
Vancouver
Gajcin J, Dusparic I. Redefining Counterfactual Explanations for Reinforcement Learning: Overview, Challenges and Opportunities. ACM Computing Surveys. 2024;56(9):1-33. doi:10.1145/3648472
BibTeX
@article{Gajcin2024,
author = {Gajcin, Jasmina and Dusparic, Ivana},
title = {Redefining Counterfactual Explanations for Reinforcement Learning: Overview, Challenges and Opportunities},
journal = {ACM Computing Surveys},
year = {2024},
volume = {56},
number = {9},
pages = {1--33},
doi = {10.1145/3648472}
}
EUVIMED