Daniele Melloni

A survey on explainable reinforcement learning: state of the art, challenges and opportunities

From this literature review, it becomes evident, in face of a series of preliminary and promising studies, the field of XRL still lacks a proper accounting towards full explainability and it emerges that more effort should be devolved into developing paradigms with a human-in-the-loop factor and standardized metrics should be adopted to allow a fair comparison of different explanation methods.