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

TL;DR

This paper introduces an adaptive sparse attention mechanism and a graph neural network-based approach to learn sparse communication graphs in multiagent reinforcement learning, significantly improving scalability and efficiency in large systems.

Contribution

It proposes a novel adaptive sparse attention mechanism and a graph neural network framework to learn interpretable sparse communication structures in MARL, enhancing scalability.

Findings

Outperforms previous methods on large-scale multiagent tasks.

Learns interpretable sparse communication graphs.

Reduces sample complexity while maintaining performance.

Abstract

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.