Official code for article "Expression is enough: Improving traffic signal control with advanced traffic state representation"

1 Introduction

Official code for article "Expression is enough: Improving traffic signal control with advanced traffic state representation".

The code structure is based on Efficient_XLight.

2 Requirements

python3.6,tensorflow=2.4, cityflow, pandas, numpy

cityflow needs a linux environment, and we run the code on Manjaro Linux.

3 Usage

Parameters are well-prepared, and you can run the code directly.

Our proposed method:

• For Advanced-MPLight, run:

python run_advanced_mplight.py

• For Advanced-CoLight, run:

python run_advanced_colight.py

• For Advanced-MP, run:

python run_advanced_maxpressure.py

For the baseline methods:

• Efficient-PressLight

python run_efficient_presslight.py

• Efficient-CoLight

python run_efficient_colight.py

• Efficient-MPLight`

python run_efficient_mplight.py

• Fixed-Time

python run_fixedtime.py

• Max-Pressure

python run_maxpressure.py

• PressLight

python run_presslight.py

• MPLight

python run_mplight.py

• Colight

python run_colight.py

4、Code details

4.1、structure

• models: contains all the models used in our article.
• utils: contains all the methods to simulate and train the models.

4.2、Reference

The code is modified from Efficient_XLight. The Max-Pressure is created by ourselves, based on MaxPressure .

• PressLight: Bsed on LIT model, which comes from Colight.
• Colight : Based on Colight.
• Fixed-Time: From MPLight.
• MPLight: From MPLight.

If you use our method, please cite our article.

@misc{zhang2021expression,
      title={Expression is enough: Improving traffic signal control with advanced traffic state representation}, 
      author={Liang Zhang and Qiang Wu and Jun Shen and Linyuan Lü and Jianqing Wu and Bo Du},
      year={2021},
      eprint={2112.10107},
      archivePrefix={arXiv},
      primaryClass={cs.AI}
}