This paper presents deep meta coordination graphs (DMCG) for learning cooperative policies in multi-agent reinforcement learning (MARL). Coordination graph formulations encode local interactions and accordingly factorize the joint value function of all agents to improve efficiency in MARL. However, existing approaches rely solely on pairwise relations between agents, which potentially oversimplifies complex multi-agent interactions. DMCG goes beyond these simple direct interactions by also capturing useful higher-order and indirect relationships among agents. It generates novel graph structures accommodating multiple types of interactions and arbitrary lengths of multi-hop connections in coordination graphs to model such interactions. It then employs a graph convolutional network module to learn powerful representations in an end-to-end manner. We demonstrate its effectiveness in multiple coordination problems in MARL where other state-of-the-art methods can suffer from sample inefficiency or fail entirely. All codes can be found here:this https URL.
View on arXiv@article{gupta2025_2502.04028,
title={ Deep Meta Coordination Graphs for Multi-agent Reinforcement Learning },
author={ Nikunj Gupta and James Zachary Hare and Rajgopal Kannan and Viktor Prasanna },
journal={arXiv preprint arXiv:2502.04028},
year={ 2025 }
}