Author:
Wells Lindsay,Bednarz Tomasz
Abstract
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.
Reference48 articles.
1. Sanity checks for saliency maps;Adebayo;arXiv [Preprint] arXiv:,2018
2. Summarizing agent strategies;Amir;Autonomous Agents Multi Agent Syst,2019
3. Explainable agents and robots: results from a systematic literature review;Anjomshoae,2019
4. Safe and trustworthy human-robot interaction;Araiza-Illan,2019
5. Emergent tool use from multi-agent autocurricula;Baker;arXiv [Preprint] arXiv:,2019
Cited by
63 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献