Applications of Multi-Agent Deep Reinforcement Learning: Models and Algorithms

Recent advancements in deep reinforcement learning (DRL) have led to its application in multi-agent scenarios to solve complex real-world problems, such as network resource allocation and sharing, network routing, and traffic signal controls. Multi-agent DRL (MADRL) enables multiple agents to intera...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Applied Sciences Ročník 11; číslo 22; s. 10870
Hlavní autoři: Ibrahim, Abdikarim Mohamed, Yau, Kok-Lim Alvin, Chong, Yung-Wey, Wu, Celimuge
Médium: Journal Article
Jazyk:angličtina
Vydáno: Basel MDPI AG 17.11.2021
Témata:
Algorithms
applied reinforcement learning
Biology (General)
Chemistry
Cooperative learning
Decision making
Deep learning
deep Q-network
Engineering (General). Civil engineering (General)
Knowledge
Markov analysis
multi-agent deep reinforcement learning
multi-agent reinforcement learning
Physics
QC1-999
QD1-999
QH301-705.5
reinforcement learning
T
TA1-2040
Taxonomy
Technology
Wireless networks
ISSN:2076-3417, 2076-3417
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Recent advancements in deep reinforcement learning (DRL) have led to its application in multi-agent scenarios to solve complex real-world problems, such as network resource allocation and sharing, network routing, and traffic signal controls. Multi-agent DRL (MADRL) enables multiple agents to interact with each other and with their operating environment, and learn without the need for external critics (or teachers), thereby solving complex problems. Significant performance enhancements brought about by the use of MADRL have been reported in multi-agent domains; for instance, it has been shown to provide higher quality of service (QoS) in network resource allocation and sharing. This paper presents a survey of MADRL models that have been proposed for various kinds of multi-agent domains, in a taxonomic approach that highlights various aspects of MADRL models and applications, including objectives, characteristics, challenges, applications, and performance measures. Furthermore, we present open issues and future directions of MADRL.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2076-3417
2076-3417
DOI:10.3390/app112210870