Efficient centralized traffic grid signal control based on meta-reinforcement learning

Dear Editor, This letter presents a novel method to tackle the two challenges of the centralized traffic control based on reinforcement learning (RL): the curse of dimensionality as the scale of traffic grid increases and the data-inefficiency problem that requires large amounts of samples to learn....

Full description

Saved in:
Bibliographic Details
Published in:IEEE/CAA journal of automatica sinica 2024, p.1-3
Main Authors: Wu, Jia, Lou, Yican
Format: Article
Language:English
Subjects:
Aerospace electronics
Context modeling
Decision making
Decoding
Task analysis
Traffic control
Training
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Dear Editor, This letter presents a novel method to tackle the two challenges of the centralized traffic control based on reinforcement learning (RL): the curse of dimensionality as the scale of traffic grid increases and the data-inefficiency problem that requires large amounts of samples to learn. First, we use a sequence-to-sequence (seq2seq) model and the attention mechanism to decompose the state-action space into sub-spaces, thus dealing with the first challenge. Second, we propose a new context-based meta-RL model that disentangles task inference and control, which improves the meta-training efficiency and accelerates the learning process in the new environment. We evaluate our approach on real-world datasets and the results demonstrate that our approach outperforms the state-of-the-art deep reinforcement learning (DRL)-based methods and the traditional control methods.
ISSN:2329-9266
2329-9274
DOI:10.1109/JAS.2023.123270