Explainability in Deep Reinforcement Learning: A Review into Current Methods and Applications-Reference-Cited by-同舟云学术

Explainability in Deep Reinforcement Learning: A Review into Current Methods and Applications

Published:2023-12-08 Issue:5 Volume:56 Page:1-35
ISSN:0360-0300
Container-title:ACM Computing Surveys
language:en
Short-container-title:ACM Comput. Surv.

Author:

Hickling Thomas¹^ORCID,Zenati Abdelhafid¹^ORCID,Aouf Nabil¹^ORCID,Spencer Phillippa²^ORCID

Affiliation:

1. Department of Electrical Engineering, City University of London, UK

2. Defence, Science and Technology Laboratory (Dstl), UK

Abstract

The use of Deep Reinforcement Learning (DRL) schemes has increased dramatically since their first introduction in 2015. Though uses in many different applications are being found, they still have a problem with the lack of interpretability. This has bread a lack of understanding and trust in the use of DRL solutions from researchers and the general public. To solve this problem, the field of Explainable Artificial Intelligence has emerged. This entails a variety of different methods that look to open the DRL black boxes, ranging from the use of interpretable symbolic Decision Trees to numerical methods like Shapley Values. This review looks at which methods are being used and for which applications. This is done to identify which models are the best suited to each application or if a method is being underutilised.

Publisher

Association for Computing Machinery (ACM)

Subject

General Computer Science,Theoretical Computer Science

Link

https://dl.acm.org/doi/pdf/10.1145/3623377

Reference68 articles.

1. Andrew Anderson, Jonathan Dodge, Amrita Sadarangani, Zoe Juozapaitis, Evan Newman, Jed Irvine, Souti Chattopadhyay, Alan Fern, and Margaret Burnett. 2019. Explaining reinforcement learning to mere mortals: an empirical study. In Proceedings of the 28th International Joint Conference on Artificial Intelligence. 1328–1334.

2. Wentao Bao, Qi Yu, and Yu Kong. 2021. DRIVE: Deep reinforced accident anticipation with visual explanation. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV’21). IEEE, 7599–7608.

3. Pablo Barros, Ana Tanevska, Francisco Cruz, and Alessandra Sciutti. 2020. Moody learners-explaining competitive behaviour of reinforcement learning agents. In Proceedings of the Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob’20). IEEE, 1–8.

4. Nicolas Blystad Carbone. 2020. Explainable AI for Path Following with Model Trees. Master’s thesis. NTNU.

5. Coactive design of explainable agent-based task planning and deep reinforcement learning for human-UAVs teamwork;Chinese J. Aeronaut.,2020

Cited by 8 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Explainability of deep reinforcement learning algorithms in robotic domains by using Layer-wise Relevance Propagation;Engineering Applications of Artificial Intelligence;2024-11

2. Analyzing deep reinforcement learning model decisions with Shapley additive explanations for counter drone operations;Applied Intelligence;2024-09-10

3. A survey on computation offloading in edge systems: From the perspective of deep reinforcement learning approaches;Computer Science Review;2024-08

4. A Review of Symbolic, Subsymbolic and Hybrid Methods for Sequential Decision Making;ACM Computing Surveys;2024-06-28

5. Blocklength Allocation and Power Control in UAV-Assisted URLLC System via Multi-agent Deep Reinforcement Learning;International Journal of Computational Intelligence Systems;2024-06-03