Multi-agent reinforcement learning for traffic signal control through universal communication method
Publication Type
Conference Proceeding Article
Version
acceptedVersion
Publication Date
7-2022
Abstract
How to coordinate the communication among intersections effectively in real complex traffic scenarios with multi-intersection is challenging. Existing approaches only enable the communication in a heuristic manner without considering the content/importance of information to be shared. In this paper, we propose a universal communication form UniComm between intersections. UniComm embeds massive observations collected at one agent into crucial predictions of their impact on its neighbors, which improves the communication efficiency and is universal across existing methods. We also propose a concise network UniLight to make full use of communications enabled by UniComm. Experimental results on real datasets demonstrate that UniComm universally improves the performance of existing state-of-the-art methods, and UniLight significantly outperforms existing methods on a wide range of traffic situations. Source codes are available at https://github.com/ zyr17/UniLight.
Keywords
Transportation, traffic control, UniComm
Discipline
Databases and Information Systems | Operations Research, Systems Engineering and Industrial Engineering | Transportation
Research Areas
Data Science and Engineering
Publication
Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI-ECAI '22): Vienna, July 23-29
First Page
3854
Last Page
3860
Publisher
AAAI Press
City or Country
Vienna, Austria
Citation
JIANG, Qize; QIN, Minhao; SHI, Shengmin; SUN, Weiwei Sun; and ZHENG, Baihua.
Multi-agent reinforcement learning for traffic signal control through universal communication method. (2022). Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI-ECAI '22): Vienna, July 23-29. 3854-3860.
Available at: https://ink.library.smu.edu.sg/sis_research/7193
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://www.ijcai.org/proceedings/2022/535
Included in
Databases and Information Systems Commons, Operations Research, Systems Engineering and Industrial Engineering Commons, Transportation Commons