Research Area:  Machine Learning

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.

Keywords:  
Multi-Agent Deep Reinforcement Learning
Reinforcement Learning
Multi-Agent Reinforcement Learning
Deep Q-Network
Applied Reinforcement Learning

Author(s) Name:  Abdikarim Mohamed Ibrahim ,Kok-Lim Alvin Yau ,Yung-Wey Chong and Celimuge Wu

Publisher name:  MDPI

DOI:  10.3390/app112210870

Volume Information:  Volume 11,Issue 22

Paper Link:   https://www.mdpi.com/2076-3417/11/22/10870