We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Applications of Multi-Agent Deep Reinforcement Learning: Models and Algorithms.
- Authors
Ibrahim, Abdikarim Mohamed; Yau, Kok-Lim Alvin; Chong, Yung-Wey; Wu, Celimuge
- Abstract
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.
- Subjects
MACHINE learning; DEEP learning; REINFORCEMENT learning; PROBLEM solving; TRAFFIC signs &; signals; QUALITY of service; ROUTING algorithms; DISTRIBUTED algorithms
- Publication
Applied Sciences (2076-3417), 2021, Vol 11, Issue 22, p10870
- ISSN
2076-3417
- Publication type
Article
- DOI
10.3390/app112210870