A Survey of Explainable Reinforcement Learning
It addresses the need for clarity in AI decision-making for researchers and practitioners, but is incremental as it organizes existing literature rather than introducing new methods.
This survey tackles the problem of understanding decision-making in reinforcement learning by proposing a novel taxonomy for explainable reinforcement learning (XRL) and outlining future research directions, without presenting specific numerical results.
Explainable reinforcement learning (XRL) is an emerging subfield of explainable machine learning that has attracted considerable attention in recent years. The goal of XRL is to elucidate the decision-making process of learning agents in sequential decision-making settings. In this survey, we propose a novel taxonomy for organizing the XRL literature that prioritizes the RL setting. We overview techniques according to this taxonomy. We point out gaps in the literature, which we use to motivate and outline a roadmap for future work.