arui-234 / larger_real_net

Large Scale Traffic Signal Control Using a Novel Multiagent Reinforcement Learning

This folder (CoDQL_exp1) provides the experimental code in the simplified TSC simulator.

This folder (CoDQL_exp2) provides the experimental code in the more realistic TSC simulator.

==This folder (CoDQL_exp2/large_grid_larger) provides a realistic 7*7 traffic signal control simulator based on SUMO.

==Please call build_file.py under [environment_dir]/data/ to generate SUMO network files

Requirements

• SUMO

Cite

Please cite the associated paper for this work if you use this code:

@ARTICLE{9186324,
  author={X. {Wang} and L. {Ke} and Z. {Qiao} and X. {Chai}},
  journal={IEEE Transactions on Cybernetics}, 
  title={Large-Scale Traffic Signal Control Using a Novel Multiagent Reinforcement Learning}, 
  year={2020},
  volume={},
  number={},
  pages={1-14},
  doi={10.1109/TCYB.2020.3015811}}
}
or
X. Wang, L. Ke, Z. Qiao and X. Chai, "Large-Scale Traffic Signal Control Using a Novel Multiagent Reinforcement Learning," in IEEE Transactions on Cybernetics, doi: 10.1109/TCYB.2020.3015811.

Updating~