Smart City Gnosys

Smart city article details

Title	The Intersection Of Companions: Differential Traffic Signal Control In Multi-Agent Systems
ID_Doc	55970
Authors	Yilin L.; Jinglin L.
Year	2022
Published	Proceedings of 2022 8th IEEE International Conference on Cloud Computing and Intelligence Systems, CCIS 2022
DOI	http://dx.doi.org/10.1109/CCIS57298.2022.10016412
Abstract	Traffic signal control (TSC) is a classic application scenario in multi-agent systems. There are thousands of traffic lights in a city. In the training of a multi-agent system, it takes a lot of resources to make a model for each agent, and the training is very difficult. At present, most schemes use only one model for all agents and obtain actions by inputting the current state of the agent. Such a method in the actual intersection will be difficult to reflect on their differences. Therefore, we propose a method to classify intersections. GCN and Q-learning are combined to find its partner for the same type of intersection and share a model. Different models are used for different types of intersections. This not only maintains the difference between intersections, but also saves the cost of resources. The experiment proves that our scheme is superior. © 2022 IEEE.
Author Keywords	Agents and multi-agent systems; Deep learning; Smart city; Traffic light control

Similar Articles

Id	Similarity	Authors	Title	Published
31510	0.889	Antes T.D.O.; Bazzan A.L.C.; Tavares A.R.	Information Upwards, Recommendation Downwards: Reinforcement Learning With Hierarchy For Traffic Signal Control	Procedia Computer Science, 201, C (2022)
33264	0.888	Reda M.; Mountassir F.; Mohamed B.	Introduction To Coordinated Deep Agents For Traffic Signal	2019 International Conference on Wireless Technologies, Embedded and Intelligent Systems, WITS 2019 (2019)
6267	0.885	Wang M.; Wang H.; Wei S.; Zhang D.	Adaptive Joint Control Of Intersection Traffic Signals And Variable Lanes Using Multi-Agent Learning	IET Intelligent Transport Systems, 19, 1 (2025)
38103	0.882	Sabit H.	Multi-Agent Reinforcement Learning For Smart City Automated Traffic Light Control	Proceedings - 2023 IEEE International Conference on High Performance Computing and Communications, Data Science and Systems, Smart City and Dependability in Sensor, Cloud and Big Data Systems and Application, HPCC/DSS/SmartCity/DependSys 2023 (2023)
21559	0.86	Chen J.-Y.; Wei F.-F.; Chen T.-Y.; Hu X.-M.; Jeon S.-W.; Wang Y.; Chen W.-N.	Earl-Light: An Evolutionary Algorithm-Assisted Reinforcement Learning For Traffic Signal Control	Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics (2024)
34880	0.859	Zhang Y.; Yu Z.; Zhang J.; Wang L.; Luan T.H.; Guo B.; Yuen C.	Learning Decentralized Traffic Signal Controllers With Multi-Agent Graph Reinforcement Learning	IEEE Transactions on Mobile Computing, 23, 6 (2024)
2760	0.857	Qin B.; He W.; Zhang B.; Li J.	A Multi-Agent Reinforcement Learning Framework With Recurrent Communication Module For Traffic Light Control	2021 IEEE 4th International Conference on Information Systems and Computer Aided Education, ICISCAE 2021 (2021)
21434	0.855	Miao S.; Wang B.; Li Y.; Pan Q.	Dynamic Traffic Signal Control Based On Multi-Agent Curricular Transfer Learning	Proceedings of SPIE - The International Society for Optical Engineering, 12943 (2023)
40923	0.853	Zhang Z.; Zhou B.; Zhang B.; Cheng P.; Lee D.-H.; Hu S.	Optimizing Traffic Signal Control In Mixed Traffic Scenarios: A Predictive Traffic Information-Based Deep Reinforcement Learning Approach	2024 Forum for Innovative Sustainable Transportation Systems, FISTS 2024 (2024)
57625	0.853	Ait Ouallane A.; Bahnasse A.; Bakali A.; Talea M.	Toward A Smart City: Reinforcement Learning For Traffic Light Control	Lecture Notes in Networks and Systems, 629 LNNS (2023)