C-MAPPO-TSC: A Collaborative Multi-Agent Reinforcement Learning Framework for Urban Traffic Signal Control and Congestion Mitigation
DOI:
https://doi.org/10.66238/fsrma103Keywords:
Multi-agent reinforcement learning, Traffic signal control, MAPPO, Urban congestion mitigation, Intelligent transportation systemsAbstract
Urban traffic congestion poses a persistent challenge to smart city development and public transportation system efficiency, largely due to fragmented traffic signal control strategies, complex congestion propagation mechanisms, and limited coordination among intersections. In large-scale urban road networks, isolated signal optimization often leads to local optimality, aggravating network-level congestion and reducing the reliability of public transport operations. To address these challenges, this paper proposes C-MAPPO-TSC, a Collaborative Multi-Agent Proximal Policy Optimization framework for urban traffic signal control and congestion mitigation. In the proposed framework, each signalized intersection is modeled as an autonomous AI agent that makes real-time control decisions based on local traffic observations and shared neighborhood information, enabling coordinated control across the network. A centralized training and decentralized execution paradigm is adopted to stabilize learning while preserving scalability, and a hybrid reward mechanism is designed to jointly optimize local intersection performance and global traffic efficiency. Furthermore, the proposed framework supports adaptive decision-making under disruptive scenarios, such as traffic accidents and demand surges, which are critical for public transportation operation and decision support platforms. Extensive experiments in a microscopic traffic simulation demonstrate that C-MAPPO-TSC substantially outperforms fixed-time control, actuated control, and single-agent reinforcement learning methods. Specifically, it reduces average vehicle waiting time by 54.1%, average queue length by 51.6%, and network-wide travel time by 33.3% under peak-hour traffic conditions. These results confirm that C-MAPPO-TSC is an effective, robust, and scalable framework for cooperative traffic signal control and congestion mitigation in urban networks.
References
[1] Webster F V. Traffic signal settings[R]. 1958.
[2] Hunt P B, Robertson D I, Bretherton R D, et al. A traffic responsive method of coordinating signals[J]. Berkshire: Transport and Road Research Laboratory, 1981.
[3] Lowrie P R. Scats, sydney co-ordinated adaptive traffic system: A traffic responsive method of controlling urban traffic[J]. 1990.
[4] Abdulhai B, Pringle R, Karakoulas G J. Reinforcement learning for true adaptive traffic signal control[J]. Journal of transportation engineering, 2003, 129(3): 278-285.
[5] Li L, Lv Y, Wang F Y. Traffic signal timing via deep reinforcement learning[J]. IEEE/CAA Journal of Automatica Sinica, 2016, 3(3): 247-254.
[6] Van der Pol E, Oliehoek F A. Coordinated deep reinforcement learners for traffic light control[J]. Proceedings of learning, inference and control of multi-agent systems (at NIPS 2016), 2016, 8: 21-38.
[7] Wiering M A. Multi-agent reinforcement learning for traffic light control[C]//Machine Learning: Proceedings of the Seventeenth International Conference (ICML'2000). 2000: 1151-1158.
[8] Zhang K, Yang Z, Başar T. Multi-agent reinforcement learning: A selective overview of theories and algorithms[J]. Handbook of reinforcement learning and control, 2021: 321-384.
[9] Rashid T, Samvelyan M, De Witt C S, et al. Monotonic value function factorisation for deep multi-agent reinforcement learning[J]. Journal of Machine Learning Research, 2020, 21(178): 1-51.
[10] Lowe R, Wu Y I, Tamar A, et al. Multi-agent actor-critic for mixed cooperative-competitive environments[J]. Advances in neural information processing systems, 2017, 30.
[11] Yu C, Velu A, Vinitsky E, et al. The surprising effectiveness of ppo in cooperative multi-agent games[J]. Advances in neural information processing systems, 2022, 35: 24611-24624.
[12] Chu T, Wang J, Codecà L, et al. Multi-agent deep reinforcement learning for large-scale traffic signal control[J]. IEEE transactions on intelligent transportation systems, 2019, 21(3): 1086-1095.
[13] Huang Y, Zhang K, Wang Y, et al. Enhancing Open-Vocabulary Panoptic Segmentation with Semantic-Guided Q-Tuning[C]//2025 IEEE International Conference on Multimedia and Expo (ICME). IEEE, 2025: 1-6.
[14] Han Z, Meng L, Zhang J. A Distributed Hierarchical Spatio-Temporal Edge-Enhanced Graph Neural Network for City-Scale Dynamic Logistics Routing[J]. arXiv preprint arXiv:2512.18441, 2025.
[15] Zhong Z, Yang S, Wei L. Privacy-enhanced federated learning via asynchronous aggregation and local differential perturbation[C]//Third International Conference on Big Data, Computational Intelligence, and Applications (BDCIA 2025). SPIE, 2026, 14128: 1156-1165.
[16] Yao Y, Zhang W, Li M. Cloud-Edge Federated Incremental Learning Framework for PMSM Efficiency Optimization with Lightweight CNN-LSTM Models and OTA Differential Deployment[J]. Journal of Computer Science and Frontier Technologies, 2026, 3(1): 98-111.
[17] Li Z, Hao Y, Zeng P. CLASNet: A Cognitive Load–Aware CNN-LSTM-Attention Framework for Supply Chain Demand Forecasting and Adaptive Human–Computer Interaction[J]. Journal of Computer Science and Frontier Technologies, 2026, 3(2): 44-57.
[18] Ling Y, Liu W. SR-DTMA: A Digital Twin-Driven LLM Multi-Agent Framework for Systemic Risk Simulation and Coordinated Decision-Making in Supply Chains[J]. Journal of Computer, Signal, and System Research, 2026, 3(1): 123-132.
[19] Yao H, Ding J, Wang Z. CloudPayGuard: Hardware-Aware Real-Time Fraud Detection for Cloud-Native Credit Systems with OoO CPU Microarchitecture Optimization[J]. Journal of Computer Science and Frontier Technologies, 2026, 3(2): 154-166.
Toor, M. J., Shabbir, S., Rauf, A., Nisar, A., Safdar, S., & Zaib-Un-Nisa. (n.d.). The role of structured-communication-technique in developing pragmatic language capability among ASD-children. https://doi.org/10.63878/cjssr.v3i2.785
Toor, M. J., Mehmood, H., Yasmeen, A., Honey, Q., Waseem, M., & Wasif, M. (n.d.). Exploring the effect of verbal encouraging phrases (VEP) on Chinese language learners’ academic achievement at university level.
Toor, M. J., Arafat, M., Ayoub, M., Ali, M., & Alessi Longa, F. E. (n.d.). From coherent self to fragmented persona: Digital identity fragmentation and academic self-concept among Generation Z, with comparative insights from Generation Alpha. https://doi.org/10.63878/cjssr.v4i2.2318
Katsitadze, N., Kharadze, N., & Pirtskhalaishvili, D. (2025). The impact of social media on students’ effective time management. Baltic Journal of Economic Studies, 11(1), 200–210. https://doi.org/10.30525/2256-0742/2025-11-1-200-210
Toor, M. J., Zafar, S., Omer, F., Sarwar, M., & Hussain, A. K. (n.d.). Teachers’ perspectives on effectiveness of translanguaging in enhancing English language learning at secondary school level.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Pinghao Luo, Xiaotong Ding
This work is licensed under a Creative Commons Attribution 4.0 International License.
License Terms (Recommended – CC BY 4.0)
All articles published in Fundamental Scientific Reports in Multidisciplinary Areas are licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author(s) and source are properly cited. Users are allowed to copy, redistribute, remix, transform, and build upon the material for any purpose, including commercial use, as long as appropriate credit is given.
Authors retain copyright of their work while granting the journal the right of first publication. The journal provides immediate open access to its content on the principle that making research freely available supports a greater global exchange of knowledge.
For more information about this license, visit:
https://creativecommons.org/licenses/by/4.0/
