Simulation optimization of highway hard shoulder running based on multi-agent deep deterministic policy gradient algorithm
Published in Alexandria Engineering Journal, 2025
Recommended citation: Hu, L., Tang, J., Zou, G., Li, Z., Zeng, J., & Li, M. (2025). Simulation optimization of highway hard shoulder running based on multi-agent deep deterministic policy gradient algorithm. Alexandria Engineering Journal, 117(November 2024), 99–115. https://doi.org/10.1016/j.aej.2024.12.110. https://www.sciencedirect.com/science/article/pii/S1110016824017095
To alleviate traffic congestion and reduce vehicle emissions, the use of hard shoulder running (HSR) has emerged as a sustainable and cost-effective active traffic management technology. However, optimizing the utilization of HSR remains a critical challenge for improving highway traffic congestion. To tackle this issue, the Multi-Agent Deep Deterministic Policy Gradient with spatio-temporal constraints (STC-MADDPG) algorithm based on multi-agent reinforcement learning is proposed in this paper. … This comprehensive evaluation of the algorithm’s effectiveness covers three key aspects: driving efficiency, driving safety, and environmental protection. The findings conclusively demonstrate the positive impact of the proposed algorithm on all three fronts.
Recommended citation: Hu, L., Tang, J., Zou, G., Li, Z., Zeng, J., & Li, M. (2025). Simulation optimization of highway hard shoulder running based on multi-agent deep deterministic policy gradient algorithm. Alexandria Engineering Journal, 117(November 2024), 99–115. https://doi.org/10.1016/j.aej.2024.12.110.