# Scaling Up Multiagent Reinforcement Learning for Robotic Systems: Learn an Adaptive Sparse Communication Graph

arXiv: https://arxiv.org/abs/2003.01040 · HTML: https://mlsanity.com/paper/2003.01040/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Mar 2020.

## Built on by (most cited first, 7 of 7)

- [Graph learning in robotics: a survey](https://mlsanity.com/paper/2310.04294/) (2023)
- [SPECTra: Scalable Multi-Agent Reinforcement Learning with Permutation-Free Networks](https://mlsanity.com/paper/2503.11726/) (2025)
- [A Recipe for Stable Offline Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2603.08399/) (2026)
- [Value-Based Deep Multi-Agent Reinforcement Learning with Dynamic Sparse Training](https://mlsanity.com/paper/2409.19391/) (2024)
- [Low Entropy Communication in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2302.05055/) (2023)
- [Achieving Collective Welfare in Multi-Agent Reinforcement Learning via Suggestion Sharing](https://mlsanity.com/paper/2412.12326/) (2024)
- [IMAGINE: Intelligent Multi-Agent Godot-based Indoor Networked Exploration](https://mlsanity.com/paper/2602.02858/) (2026)

## Abstract (arXiv)

The complexity of multiagent reinforcement learning (MARL) in multiagent systems increases exponentially with respect to the agent number. This scalability issue prevents MARL from being applied in large-scale multiagent systems. However, one critical feature in MARL that is often neglected is that the interactions between agents are quite sparse. Without exploiting this sparsity structure, existing works aggregate information from all of the agents and thus have a high sample complexity. To address this issue, we propose an adaptive sparse attention mechanism by generalizing a sparsity-inducing activation function. Then a sparse communication graph in MARL is learned by graph neural networks based on this new attention mechanism. Through this sparsity structure, the agents can communicate in an effective as well as efficient way via only selectively attending to agents that matter the most and thus the scale of the MARL problem is reduced with little optimality compromised. Comparative results show that our algorithm can learn an interpretable sparse structure and outperforms previous works by a significant margin on applications involving a large-scale multiagent system.