Efficient Policy Generation in Multi-Agent Systems via Hypergraph Neural Network

TL;DR

This paper introduces a novel multi-agent reinforcement learning approach that uses hypergraph neural networks to adaptively model agent interactions, enhancing cooperation in complex multi-agent systems.

Contribution

It proposes two hypergraph-based MARL algorithms, HGAC and ATT-HGAC, which improve agent collaboration through adaptive hypergraph structure learning.

Findings

Our methods outperform existing MARL approaches in various experiments.

Hypergraph convolution enhances information extraction for better cooperation.

Adaptive hypergraph modeling improves multi-agent collaboration efficiency.

Abstract

The application of deep reinforcement learning in multi-agent systems introduces extra challenges. In a scenario with numerous agents, one of the most important concerns currently being addressed is how to develop sufficient collaboration between diverse agents. To address this problem, we consider the form of agent interaction based on neighborhood and propose a multi-agent reinforcement learning (MARL) algorithm based on the actor-critic method, which can adaptively construct the hypergraph structure representing the agent interaction and further implement effective information extraction and representation learning through hypergraph convolution networks, leading to effective cooperation. Based on different hypergraph generation methods, we present two variants: Actor Hypergraph Convolutional Critic Network (HGAC) and Actor Attention Hypergraph Critic Network (ATT-HGAC). Experiments with different settings demonstrate the advantages of our approach over other existing methods.