skip to main content
Language:

Explainability in Deep Reinforcement Learning

Knowledge-based systems, 2021-02 [Peer Reviewed Journal]

Distributed under a Creative Commons Attribution 4.0 International License ;ISSN: 0950-7051 ;EISSN: 1872-7409 ;DOI: 10.1016/j.knosys.2020.106685

Digital Resources/Online E-Resources

Citations Cited by
  • Title:
    Explainability in Deep Reinforcement Learning
  • Author: Heuillet, Alexandre ; Couthouis, Fabien ; Díaz-Rodríguez, Natalia
  • Subjects: Artificial Intelligence ; Computer Science ; Computer Vision and Pattern Recognition ; Multiagent Systems ; Neural and Evolutionary Computing
  • Is Part Of: Knowledge-based systems, 2021-02
  • Description: 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 explainaility. 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.
  • Publisher: Elsevier
  • Language: English
  • Identifier: ISSN: 0950-7051
    EISSN: 1872-7409
    DOI: 10.1016/j.knosys.2020.106685
  • Source: Hyper Article en Ligne (HAL) (Open Access)
Back to results list
INSPIRE LIBRARY - TON DUC THANG UNIVERSITY (84-028) 37 755 057 Feedback
19 Nguyen Huu Tho St. Dist.7, HCM thuvien@tdtu.edu.vn

Copyright © 2017 INSPIRE LIBRARY - TON DUC THANG UNIVERSITY

Searching Remote Databases, Please Wait