Abstract :
Abstract Agents can use communication to coordinate their actions and achieve their goals. The agents in multi-agent reinforcement learning (MARL) have the ability to enhance their overall learning performance by acquiring communication skills. They can transmit various types of messages to either all agents or particular groups, utilizing diverse communication channels. Their study on MARL with communication (Comm-MARL) is expanding. Nonetheless, currently, there is no methodical approach to differentiate and categorize present Comm-MARL (Communication Multi-agent reinforcement learning) systems. This article surveys recent research in the Comm-MARL domain, scrutinizing diverse communication aspects that could be incorporated into MARL systems. Several dimensions are suggested to examine, establish, and contrast Comm-MARL systems. This paper presents a comprehensive review of the nine dimensions influencing communication in multi-agent collaboration. The dimensions explored include communication type, communication policy, communicated messages, message combination, inner integration, communication constraints, communication learning, training schemes, and controlled goals. By examining these dimensions, the study aims to shed light on the intricate dynamics of agent interaction in complex environments. This review emphasizes the significance of effective communication strategies in achieving common objectives among agents and highlights the importance of factors such as context awareness, adaptability, and learning from past experiences. The insights provided in this paper offer valuable guidance for enhancing collaboration and communication strategies across various multi-agent systems and applications.
Keyword :
N/A