A community-aware hierarchical reinforcement learning framework for resource allocation in service networks

In this paper, we propose a novel community-aware hierarchical reinforcement learning (CHRL) framework with GNN-enhanced state representations, specifically designed to address the complex resource allocation challenges in service networks. The framework leverages the power of graph neural networks to model community structures within service networks and uses hierarchical reinforcement learning to optimize resource allocation across different levels of the network. The experimental results validate the effectiveness of the proposed method in capturing the structural characteristics and internal collaboration mechanisms of community networks, thereby enabling more efficient resource allocation in larger-scale service resource environments.