Open Access Repository

Explainable AI and reinforcement learning - a systematic review of current approaches and trends


Downloads per month over past year

Wells, L ORCID: 0000-0002-0195-5648 and Bednarz, T 2021 , 'Explainable AI and reinforcement learning - a systematic review of current approaches and trends' , Frontiers in Artificial Intelligence, vol. 4 , p. 48 .

PDF (Published version)
143220 - Explai...pdf | Download (2MB)

| Preview


Research into Explainable Artificial Intelligence (XAI) has been increasing in recent years as a response to the need for increased transparency and trust in AI. This is particularly important as AI is used in sensitive domains with societal, ethical, and safety implications. Work in XAI has primarily focused on Machine Learning (ML) for classification, decision, or action, with detailed systematic reviews already undertaken. This review looks to explore current approaches and limitations for XAI in the area of Reinforcement Learning (RL). From 520 search results, 25 studies (including 5 snowball sampled) are reviewed, highlighting visualization, query-based explanations, policy summarization, human-in-the-loop collaboration, and verification as trends in this area. Limitations in the studies are presented, particularly a lack of user studies, and the prevalence of toy-examples and difficulties providing understandable explanations. Areas for future study are identified, including immersive visualization, and symbolic representation.

Item Type: Article
Authors/Creators:Wells, L and Bednarz, T
Keywords: explainable AI, reinforcement learning, artificial intelligence, visualization, machine learning
Journal or Publication Title: Frontiers in Artificial Intelligence
Publisher: Frontiers Research Foundation
ISSN: 2624-8212
Copyright Information:

Copyright © 2021 Wells and Bednarz. This is an open-access article distributed under the terms of the Creative Commons Attribution 4.0 International (CC BY 4.0) License (

Item Statistics: View statistics for this item

Actions (login required)

Item Control Page Item Control Page