# Deep Multi-Agent Reinforcement Learning with Relevance Graphs

arXiv: https://arxiv.org/abs/1811.12557 · HTML: https://mlsanity.com/paper/1811.12557/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Nov 2018.

## Built on by (most cited first, 13 of 13)

- [A Survey of Multi-Agent Deep Reinforcement Learning with Communication](https://mlsanity.com/paper/2203.08975/) (2022)
- [Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunities](https://mlsanity.com/paper/2506.18019/) (2025)
- [Learning Efficient Multi-Agent Cooperative Visual Exploration](https://mlsanity.com/paper/2110.05734/) (2021)
- [Learning to Optimize Industry-Scale Dynamic Pickup and Delivery Problems](https://mlsanity.com/paper/2105.12899/) (2021)
- [The Five Ws of Multi-Agent Communication: Who Talks to Whom, When, What, and Why -- A Survey from MARL to Emergent Language and LLMs](https://mlsanity.com/paper/2602.11583/) (2026)
- [DAIR: Disentangled Attention Intrinsic Regularization for Safe and Efficient Bimanual Manipulation](https://mlsanity.com/paper/2106.05907/) (2021)
- [Universally Expressive Communication in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2206.06758/) (2022)
- [Developing a Successful Bomberman Agent](https://mlsanity.com/paper/2203.09608/) (2022)
- [Graph Convolutional Reinforcement Learning for Collaborative Queuing Agents](https://mlsanity.com/paper/2205.12009/) (2022)
- [Q-MARL: A quantum-inspired algorithm using neural message passing for large-scale multi-agent reinforcement learning](https://mlsanity.com/paper/2503.07397/) (2025)
- [SACHI: Structured Agent Coordination via Holistic Information Integration in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2605.08391/) (2026)
- [SIGMA: Structured Noise-Effect-Aware Grouped Multi-Agent Aggregation](https://mlsanity.com/paper/2608.26683/) (2026)
- [HySTAR: Anchored Hypergraphs for Stable Credit Assignment in Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2609.31531/) (2026)

## Abstract (arXiv)

Over recent years, deep reinforcement learning has shown strong successes in complex single-agent tasks, and more recently this approach has also been applied to multi-agent domains. In this paper, we propose a novel approach, called MAGnet, to multi-agent reinforcement learning (MARL) that utilizes a relevance graph representation of the environment obtained by a self-attention mechanism, and a message-generation technique inspired by the NerveNet architecture. We applied our MAGnet approach to the Pommerman game and the results show that it significantly outperforms state-of-the-art MARL solutions, including DQN, MADDPG, and MCTS.