Online Learning for Traffic Routing under Unknown Preferences

This repository contains the official implementation for the paper Online Learning for Traffic Routing under Unknown Preferences by Devansh Jalota, Karthik Gopalakrishhah, Navid Azizan, Ramesh Johari, and Marco Pavone, published in AISTATS'23.

Data sources

The traffic network, user flows, and road capacities are obtained from the TNTP dataset

Requirements

This code uses the following packages

• Gurobi for the optimization solvers
• Geopandas for manipulating geospatial data
• Contextily for loading basemap for plots

Running the code

• main.py to run simulations
• plots.py to generate the plots

Citation

If you found this codebase useful in your research, please consider citing

@InProceedings{pmlr-v206-jalota23a,
  title = 	 {Online Learning for Traffic Routing under Unknown Preferences},
  author =       {Jalota, Devansh and Gopalakrishnan, Karthik and Azizan, Navid and Johari, Ramesh and Pavone, Marco},
  booktitle = 	 {Proceedings of The 26th International Conference on Artificial Intelligence and Statistics},
  pages = 	 {3210--3229},
  year = 	 {2023},
  volume = 	 {206},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {25--27 Apr},
  publisher =    {PMLR},
  pdf = 	 {https://proceedings.mlr.press/v206/jalota23a/jalota23a.pdf},
}