Explainability in deep reinforcement learning

A large set of the explainable Artificial Intelligence (XAI) literature is emerging on feature relevance techniques to explain a deep neural network (DNN) output or explaining models that ingest image source data. However, assessing how XAI techniques can help understand models beyond classification tasks, e.g. for reinforcement learning (RL), has not been extensively studied. We review recent works in the direction to attain Explainable Reinforcement Learning (XRL), a relatively new subfield of Explainable Artificial Intelligence, intended to be used in general public applications, with diverse audiences, requiring ethical, responsible and trustable algorithms. In critical situations where it is essential to justify and explain the agent's behaviour, better explainability and interpretability of RL models could help gain scientific insight on the inner workings of what is still considered a black box. We evaluate mainly studies directly linking explainability to RL, and split these into two categories according to the way the explanations are generated: transparent algorithms and post-hoc explainability. We also review the most prominent XAI works from the lenses of how they could potentially enlighten the further deployment of the latest advances in RL, in the demanding present and future of everyday problems. (C) 2020 Elsevier B.V. All rights reserved.

Automated summary

The study explores the development of Explainable Reinforcement Learning (XRL) and the application of XAI techniques in helping to understand the behavior and internal workings of models in reinforcement learning. The evaluation focuses on studies directly linking explainability to RL, categorizing the explanation generation into transparent algorithms and post-hoc explainability. Furthermore, it reviews prominent XAI works and their potential impact on the latest advances in RL, addressing present and future everyday problems.