Explainability in deep reinforcement learning

Alexandre Heuillet

doi:10.1016/j.knosys.2020.106685

Return

Explainability in deep reinforcement learning

2021-02-01

183

Alexandre Heuillet

Fabien Couthouis

Natalia Díaz-Rodríguez *

DOI：10.1016/j.knosys.2020.106685

Original

Save

View PDF

Abstract

En 中文

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.

Keywords:

Reinforcement Learning

Explainable artificial intelligence

Machine Learning

Deep Learning

Responsible artificial intelligence

Representation learning

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.