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...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Abdikarim Mohamed Ibrahim, Kok-Lim Alvin Yau, Yung-Wey Chong, Celimuge Wu
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	multi-agent deep reinforcement learning reinforcement learning multi-agent reinforcement learning deep Q-network applied reinforcement learning Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/f3c7b1961f864e5a94614c615dbe262a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:f3c7b1961f864e5a94614c615dbe262a
record_format	dspace
spelling	oai:doaj.org-article:f3c7b1961f864e5a94614c615dbe262a2021-11-25T16:39:37ZApplications of Multi-Agent Deep Reinforcement Learning: Models and Algorithms10.3390/app1122108702076-3417https://doaj.org/article/f3c7b1961f864e5a94614c615dbe262a2021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/22/10870https://doaj.org/toc/2076-3417Recent 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.Abdikarim Mohamed IbrahimKok-Lim Alvin YauYung-Wey ChongCelimuge WuMDPI AGarticlemulti-agent deep reinforcement learningreinforcement learningmulti-agent reinforcement learningdeep Q-networkapplied reinforcement learningTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10870, p 10870 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	multi-agent deep reinforcement learning reinforcement learning multi-agent reinforcement learning deep Q-network applied reinforcement learning Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	multi-agent deep reinforcement learning reinforcement learning multi-agent reinforcement learning deep Q-network applied reinforcement learning Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Abdikarim Mohamed Ibrahim Kok-Lim Alvin Yau Yung-Wey Chong Celimuge Wu Applications of Multi-Agent Deep Reinforcement Learning: Models and Algorithms
description	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.
format	article
author	Abdikarim Mohamed Ibrahim Kok-Lim Alvin Yau Yung-Wey Chong Celimuge Wu
author_facet	Abdikarim Mohamed Ibrahim Kok-Lim Alvin Yau Yung-Wey Chong Celimuge Wu
author_sort	Abdikarim Mohamed Ibrahim
title	Applications of Multi-Agent Deep Reinforcement Learning: Models and Algorithms
title_short	Applications of Multi-Agent Deep Reinforcement Learning: Models and Algorithms
title_full	Applications of Multi-Agent Deep Reinforcement Learning: Models and Algorithms
title_fullStr	Applications of Multi-Agent Deep Reinforcement Learning: Models and Algorithms
title_full_unstemmed	Applications of Multi-Agent Deep Reinforcement Learning: Models and Algorithms
title_sort	applications of multi-agent deep reinforcement learning: models and algorithms
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/f3c7b1961f864e5a94614c615dbe262a
work_keys_str_mv	AT abdikarimmohamedibrahim applicationsofmultiagentdeepreinforcementlearningmodelsandalgorithms AT koklimalvinyau applicationsofmultiagentdeepreinforcementlearningmodelsandalgorithms AT yungweychong applicationsofmultiagentdeepreinforcementlearningmodelsandalgorithms AT celimugewu applicationsofmultiagentdeepreinforcementlearningmodelsandalgorithms
_version_	1718413114266877952

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

Ejemplares similares