Abstract
The advances in reinforcement learning have recorded sublime success in various domains. Although the multi-agent domain has been overshadowed by its single-agent counterpart during this progress, multi-agent reinforcement learning gains rapid traction, and the latest accomplishments address problems with real-world complexity. This article provides an overview of the current developments in the field of multi-agent deep reinforcement learning. We focus primarily on literature from recent years that combines deep reinforcement learning methods with a multi-agent scenario. To survey the works that constitute the contemporary landscape, the main contents are divided into three parts. First, we analyze the structure of training schemes that are applied to train multiple agents. Second, we consider the emergent patterns of agent behavior in cooperative, competitive and mixed scenarios. Third, we systematically enumerate challenges that exclusively arise in the multi-agent domain and review methods that are leveraged to cope with these challenges. To conclude this survey, we discuss advances, identify trends, and outline possible directions for future work in this research area.
Highlights
A multi-agent system describes multiple distributed entities—so-called agents—which take decisions autonomously and interact within a shared environment (Weiss 1999)
The most common framework to address learning in an interactive environment is reinforcement learning (RL), which describes the change of behavior through a trial-and-error approach
We provide an extensive review of the recent advances in the area of multiagent deep reinforcement learning (MADRL)
Summary
A multi-agent system describes multiple distributed entities—so-called agents—which take decisions autonomously and interact within a shared environment (Weiss 1999). The most common framework to address learning in an interactive environment is reinforcement learning (RL), which describes the change of behavior through a trial-and-error approach. We start with the Markov decision process as a framework for single-agent learning in Sect. We pose pathologies that arise in the multi-agent domain such as the non-stationarity of the environment from the perspective of a single learner, relative over-generalization, and the credit assignment problem in Sect. 5. We provide the formal concepts behind these MARL pathologies in order to drive our discussion about the state-of-the-art approaches in Sect. The scope of this background section is deliberately focusing on classical MARL works to reveal the roots of the domain and to give the reader insights into the early works on which modern MADRL approaches rest
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
