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

被引：15

作者：

Hickling, Thomas ^{[1
]}

Zenati, Abdelhafid ^{[1
]}

Aouf, Nabil ^{[1
]}

Spencer, Phillippa ^{[2
]}

机构：

[1] City Univ London, Dept Elect Engn, Northampton Sq, London EC1V 0HB, England

[2] Def Sci & Technol Lab Dstl, Porton Down, Salisbury SP40JQ, Wilts, England

来源：

ACM COMPUTING SURVEYS | 2024年 / 56卷 / 05期

关键词：

Deep reinforcement learning; DRL; Explainable AI; XAI; neural networks; Survey; Review;

D O I：

10.1145/3623377

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

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.

引用

页数：35

共 50 条

[41] Coevolutionary Deep Reinforcement Learning [J].

Cotton, David ;

Traish, Jason ;

Chaczko, Zenon .

2020 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (SSCI), 2020, :2600-2607

[42] Explainability of deep reinforcement learning algorithms in robotic domains by using Layer-wise Relevance Propagation [J].

Taghian, Mehran ;

Miwa, Shotaro ;

Mitsuka, Yoshihiro ;

Gunther, Johannes ;

Golestan, Shadan ;

Zaiane, Osmar .

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2024, 137

[43] UAV collection methods for the farmland nodes data based on deep reinforcement learning [J].

Jie H. ;

Yali Z. ;

Tuan W. ;

Mengcheng W. ;

Yubin L. ;

Zhixun Z. .

Nongye Gongcheng Xuebao/Transactions of the Chinese Society of Agricultural Engineering, 2022, 38 (22) :41-51

[44] Deep reinforcement learning and its applications in medical imaging and radiation therapy: a survey [J].

Xu, Lanyu ;

Zhu, Simeng ;

Wen, Ning .

PHYSICS IN MEDICINE AND BIOLOGY, 2022, 67 (22)

[45] Demystifying the black box: an overview of explainability methods in machine learning [J].

Kinger S. ;

Kulkarni V. .

International Journal of Computers and Applications, 2024, 46 (02) :90-100

[46] Challenges and Opportunities in Deep Reinforcement Learning With Graph Neural Networks: A Comprehensive Review of Algorithms and Applications [J].

Munikoti, Sai ;

Agarwal, Deepesh ;

Das, Laya ;

Halappanavar, Mahantesh ;

Natarajan, Balasubramaniam .

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024, 35 (11) :15051-15071

[47] Beyond Human: Deep Learning, Explainability and Representation [J].

Fazi, M. Beatrice .

THEORY CULTURE & SOCIETY, 2021, 38 (7-8) :55-77

[48] Stock Market Prediction Using Deep Reinforcement Learning [J].

Awad, Alamir Labib ;

Elkaffas, Saleh Mesbah ;

Fakhr, Mohammed Waleed .

APPLIED SYSTEM INNOVATION, 2023, 6 (06)

[49] A survey on deep learning and deep reinforcement learning in robotics with a tutorial on deep reinforcement learning [J].

Morales, Eduardo F. ;

Murrieta-Cid, Rafael ;

Becerra, Israel ;

Esquivel-Basaldua, Marco A. .

INTELLIGENT SERVICE ROBOTICS, 2021, 14 (05) :773-805

[50] A survey on deep learning and deep reinforcement learning in robotics with a tutorial on deep reinforcement learning [J].

Eduardo F. Morales ;

Rafael Murrieta-Cid ;

Israel Becerra ;

Marco A. Esquivel-Basaldua .

Intelligent Service Robotics, 2021, 14 :773-805

← 1 2 3 4 5 →