Adaptive Multi-Agent Reinforcement Learning with Graph Neural Networks for Dynamic Optimization in Sports Buildings

The dynamic scheduling optimization of sports facilities faces challenges posed by real-time demand fluctuations and complex interdependencies between facilities. To address the adaptability limitations of traditional centralized approaches, this study proposes a decentralized multi-agent reinforcement learning framework based on graph neural networks (GNNs). Experimental results demonstrate that in a simulated environment comprising 12 heterogeneous sports facilities, the proposed method achieves an operational efficiency of 0.89 ± 0.02, representing a 13% improvement over Centralized PPO, while user satisfaction reaches 0.85 ± 0.03, a 9% enhancement. When confronted with a sudden 30% surge in demand, the system recovers in just 90 steps, 33% faster than centralized methods. The GNN attention mechanism successfully captures critical dependencies between facilities, such as the connection weight of 0.32 ± 0.04 between swimming pools and locker rooms. Computational efficiency tests show that the system maintains real-time decision-making capability within 800 ms even when scaled to 50 facilities. These results verify that the method effectively balances decentralized decision-making with global coordination while maintaining low communication overhead (0.09 ± 0.01), offering a scalable and practical solution for resource management in complex built environments.