Explainability in deep reinforcement learning

作者：

Highlights：

• We review concepts related to the explainability of Deep Reinforcement Learning models.

• We provide a comprehensive analysis of the Explainable Reinforcement Learning literature.

• We propose a categorization of existing Explainable Reinforcement Learning methods.

• We discuss ideas emerging from the literature and provide insights for future work.

摘要

•We review concepts related to the explainability of Deep Reinforcement Learning models.•We provide a comprehensive analysis of the Explainable Reinforcement Learning literature.•We propose a categorization of existing Explainable Reinforcement Learning methods.•We discuss ideas emerging from the literature and provide insights for future work.

论文关键词：Reinforcement Learning,Explainable artificial intelligence,Machine Learning,Deep Learning,Responsible artificial intelligence,Representation learning

论文评审过程：Received 1 September 2020, Revised 25 October 2020, Accepted 11 December 2020, Available online 25 December 2020, Version of Record 20 January 2021.

论文官网地址：https://doi.org/10.1016/j.knosys.2020.106685