A Survey of Multi-Agent Deep Reinforcement Learning with Graph Neural Network-Based Communication
For researchers in multi-agent reinforcement learning, this survey provides a structured overview of GNN-based communication methods, but it is an incremental contribution as it does not introduce new algorithms or results.
This survey categorizes and explains multi-agent deep reinforcement learning methods that use graph neural networks for agent communication, proposing a generalized framework to clarify underlying concepts.
In multi-agent reinforcement learning (MARL), the integration of a communication mechanism, allowing agents to better learn to coordinate their actions and converge on their objectives by sharing information. Based on an interaction graph, a subclass of methods employs graph neural networks (GNNs) to learn the communication, enabling agents to improve their internal representations by enriching them with information exchanged. With growing research, we note a lack of explicit structure and framework to distinguish and classify MARL approaches with communication based on GNNs. Thus, this paper surveys recent works in this field. We propose a generalized GNN-based communication process with the goal of making the underlying concepts behind the methods more obvious and accessible.