Learning Thresholds to Select Cooperative Partners by Applying Deep Reinforcement Learning in Distributed Traffic Signal Control

Shinya Matsuta; Naoki Kodama; Taku Harada

doi:10.29007/fqdm

Download PDF Open PDF in browser

Learning Thresholds to Select Cooperative Partners by Applying Deep Reinforcement Learning in Distributed Traffic Signal Control

10 pages•Published: March 22, 2023

Shinya Matsuta, Naoki Kodama and Taku Harada

Abstract

One method to reduce vehicle congestion in a road traffic network is to appropriately control traffic signals. One control scheme for traffic signals is a distributed control scheme in which individual traffic signals cooperate locally with other geographically close traffic signals. Deep reinforcement learning has been actively studied to appropriately control traffic signals. In distributed control, it is important to select appropriate cooperative partners. In this study, we propose a method for selecting appropriate cooperative partners using deep reinforcement learning to the distributed traffic signal control.

Keyphrases: cooperation, Deep Q-Network, Deep Reinforcement Learning, traffic signal control

In: Ajay Bandi, Mohammad Hossain and Ying Jin (editors). Proceedings of 38th International Conference on Computers and Their Applications, vol 91, pages 56--65

Links:	https://easychair.org/publications/paper/TjGs
	https://doi.org/10.29007/fqdm

BibTeX entry

@inproceedings{CATA2023:Learning_Thresholds_to_Select,
  author    = {Shinya Matsuta and Naoki Kodama and Taku Harada},
  title     = {Learning Thresholds to Select Cooperative Partners by Applying Deep Reinforcement Learning in Distributed Traffic Signal Control},
  booktitle = {Proceedings of 38th International Conference on Computers and Their Applications},
  editor    = {Ajay Bandi and Mohammad Hossain and Ying Jin},
  series    = {EPiC Series in Computing},
  volume    = {91},
  pages     = {56--65},
  year      = {2023},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2398-7340},
  url       = {https://easychair.org/publications/paper/TjGs},
  doi       = {10.29007/fqdm}}

Download PDF Open PDF in browser