Survey of Explainable Reinforcement Learning: Methods, Targets and Gaps
In brief
- Intuitive two-axis taxonomy to classify explainability methods in RL
- Review of over 250 scientific papers on the topic
- Identification of future needs for the XRL field
This paper provides a comprehensive review of explainability methods for reinforcement learning, organized around an intuitive taxonomy. It covers over 250 research works and outlines key areas for future research in the field.
This summary gives you the essentials. The full article, its figures and quotes are on cs.AI updates on arXiv.org.
Read the original articleAI-generated summary of the source, checked by rules. Report an error