Journal of Artificial Intelligence Research· 2026Q1· Review
A Survey of Explainable Reinforcement Learning: Targets, Methods and Needs
- 2citations
- Q1SCImago
- 2026year
Short summary
This survey categorizes over 250 eXplainable Reinforcement Learning (XRL) methods based on 'What' (the explanation target) and 'How' (the explanation method), identifying key research needs.
AI-generated from the title and abstract; the full text is not read.
Key points
- The paper surveys eXplainable Reinforcement Learning (XRL), a subfield of eXplainable AI (XAI).
- A novel taxonomy is proposed, categorizing XRL methods by explanation target ('What') and explanation method ('How').
- Over 250 XRL papers are reviewed using this taxonomy.
- The survey identifies related domains and outlines current needs within the XRL field.
AI-generated from the title and abstract; the full text is not read.
Abstract
The success of recent Artificial Intelligence (AI) models has been accompanied by the opacity of their internal mechanisms, due notably to the use of deep neural networks. In order to understand these internal mechanisms and explain the output of these AI models, a set of methods have been proposed, grouped under the domain of eXplainable AI (XAI). This paper focuses on a sub-domain of XAI, called eXplainable Reinforcement Learning (XRL), which aims to explain the actions of an agent that has learned by reinforcement learning. We propose an intuitive taxonomy based on two questions ‘What’ and ‘How’. The first question focuses on the target that the method explains, while the second relates to the way the explanation is provided. We use this taxonomy to provide a state-of-the-art review of over 250 papers. In addition, we present a set of domains close to XRL, which we believe should get attention from the community. Finally, we identify some needs for the field of XRL.
The authors' abstract, as published at the source. Journal of Artificial Intelligence Research, 2026 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Artificial Intelligence
Artificial IntelligenceComputer Science