Deep Q learning-based traffic signal control algorithms: Model development and evaluation with field data

2022 ◽  
pp. 1-21
Author(s):  
Hao Wang ◽  
Yun Yuan ◽  
Xianfeng Terry Yang ◽  
Tian Zhao ◽  
Yang Liu
Keyword(s):  
Field Data ◽  
Model Development ◽  
Traffic Signal ◽  
Control Algorithms ◽  
Signal Control ◽  
Traffic Signal Control ◽  
Q Learning

Adaptive traffic signal control algorithms based on probe vehicle data

2020 ◽  
Vol 25 (1) ◽  
pp. 41-57 ◽  
Author(s):  
Fushi Lian ◽  
Bokui Chen ◽  
Kai Zhang ◽  
Lixin Miao ◽  
Jinchao Wu ◽  
...  
Keyword(s):  
Traffic Signal ◽  
Control Algorithms ◽  
Signal Control ◽  
Traffic Signal Control ◽  
Adaptive Traffic Signal Control ◽  
Probe Vehicle ◽  
Vehicle Data

Traffic Signal Control Algorithms of a Traffic Network

1995 ◽  
Vol 28 (10) ◽  
pp. 459-464
Author(s):  
E.J. Davison ◽  
H. Shimizu ◽  
H. Naraki
Keyword(s):  
Traffic Signal ◽  
Control Algorithms ◽  
Signal Control ◽  
Traffic Signal Control ◽  
Traffic Network

scholarly journals Development of a Neural Network Based Q Learning Algorithm for Traffic Signal Control

2011 ◽  
Vol 2-3 ◽  
pp. 91-95
Author(s):  
Li Bi Fu ◽  
Kil To Chong
Keyword(s):  
Neural Network ◽  
Memory Load ◽  
Learning Algorithm ◽  
Control Area ◽  
Traffic Signal ◽  
Signal Control ◽  
Traffic Signal Control ◽  
Q Learning ◽  
Traffic Efficiency ◽  
Continuous State

As one kind of reinforcement learning method, Q learning algorithm has already been proved to achieve many significant results in traffic signal control area. However, when the state of Markov Decision Process is very big or continuous, the computation load and the memory load will become very big and can not be solved then. Therefore, this paper proposed a neural network based Q learning algorithm to solve this problem known as “Curse of Dimensionality”. This new method realized generalization of conventional Q learnig algorithm in huge and continuous state space as neural network is a very effective value function approximator. Experiment has been implemented upon an isolated intersection and simulation results show that the proposed method can improve the traffic efficiency significantly than the conventional Q learning algorithm.

Sign in / Sign up

Export Citation Format

Share Document