From Local to Global: A Curriculum Learning Approach for Reinforcement Learning-based Traffic Signal Control

Nianzhao Zheng, Jialong Li, Zhenyu Mao, Kenji Tei

研究成果: Conference contribution

抄録

Traffic signal control (TSC) is one of the effective ways to mitigate traffic congestion, a growing problem causing significant economic loss to urban areas. In recent years, there is an increasing interest in using reinforcement learning (RL) in TSC since RL shows great potential in optimizing control policy for complex real-world traffic conditions. However, one concerning problem is the huge computing time/resources required to train the control policy for large-scale TSC. To address this problem, this paper proposes a method that utilizes a curriculum to help speed up the training process. Control policies of different single-intersection maps are learned first and then referenced to a large-scale map consisting of a certain number of different intersections. The preliminary evaluation demonstrates that our method achieves a jump-start compared to that of learning the target task from scratch.

本文言語English
ホスト出版物のタイトル2022 2nd IEEE International Conference on Software Engineering and Artificial Intelligence, SEAI 2022
出版社Institute of Electrical and Electronics Engineers Inc.
ページ253-258
ページ数6
ISBN(電子版)9781665482233
DOI
出版ステータスPublished - 2022
イベント2nd IEEE International Conference on Software Engineering and Artificial Intelligence, SEAI 2022 - Xiamen, China
継続期間: 2022 6月 102022 6月 12

出版物シリーズ

名前2022 2nd IEEE International Conference on Software Engineering and Artificial Intelligence, SEAI 2022

Conference

Conference2nd IEEE International Conference on Software Engineering and Artificial Intelligence, SEAI 2022
国/地域China
CityXiamen
Period22/6/1022/6/12

ASJC Scopus subject areas

  • 人工知能
  • コンピュータ サイエンスの応用
  • コンピュータ ビジョンおよびパターン認識
  • ソフトウェア
  • 制御と最適化

フィンガープリント

「From Local to Global: A Curriculum Learning Approach for Reinforcement Learning-based Traffic Signal Control」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル