Next Article in Journal
Fenton Reaction for Enhancing Polishing Rate and Protonated Amine Functional Group Polymer for Inhibiting Corrosion in Ge1Sb4Te5 Film Surface Chemical-Mechanical-Planarization
Previous Article in Journal
Building and Evaluating an Annotated Corpus for Automated Recognition of Chat-Based Social Engineering Attacks
Previous Article in Special Issue
Adaptation to Other Agent’s Behavior Using Meta-Strategy Learning by Collision Avoidance Simulation
Review

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

1
Department of Computing and Information Systems, School of Engineering and Technology, Sunway University, Petaling Jaya 47500, Selangor, Malaysia
2
National Advanced IPv6 Centre, Universiti Sains Malaysia (USM), Gelugor 11800, Penang, Malaysia
3
Graduate School of Informatics and Engineering, The University of Electro-Communications, Tokyo 182-8585, Japan
*
Authors to whom correspondence should be addressed.
Academic Editors: Andrea Omicini and Stefano Mariani
Appl. Sci. 2021, 11(22), 10870; https://doi.org/10.3390/app112210870
Received: 1 October 2021 / Revised: 21 October 2021 / Accepted: 25 October 2021 / Published: 17 November 2021
(This article belongs to the Special Issue Advances in Multi-Agent Systems)
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. View Full-Text
Keywords: multi-agent deep reinforcement learning; reinforcement learning; multi-agent reinforcement learning; deep Q-network; applied reinforcement learning multi-agent deep reinforcement learning; reinforcement learning; multi-agent reinforcement learning; deep Q-network; applied reinforcement learning
Show Figures

Figure 1

MDPI and ACS Style

Ibrahim, A.M.; Yau, K.-L.A.; Chong, Y.-W.; Wu, C. Applications of Multi-Agent Deep Reinforcement Learning: Models and Algorithms. Appl. Sci. 2021, 11, 10870. https://doi.org/10.3390/app112210870

AMA Style

Ibrahim AM, Yau K-LA, Chong Y-W, Wu C. Applications of Multi-Agent Deep Reinforcement Learning: Models and Algorithms. Applied Sciences. 2021; 11(22):10870. https://doi.org/10.3390/app112210870

Chicago/Turabian Style

Ibrahim, Abdikarim M., Kok-Lim A. Yau, Yung-Wey Chong, and Celimuge Wu. 2021. "Applications of Multi-Agent Deep Reinforcement Learning: Models and Algorithms" Applied Sciences 11, no. 22: 10870. https://doi.org/10.3390/app112210870

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop