Machine-Learned Prediction Equilibrium for Dynamic Traffic Assignment
Abstract
We study a dynamic traffic assignment model, where agents base their instantaneous routing decisions on real-time delay predictions. We formulate a mathematically concise model and derive properties of the predictors that ensure a dynamic prediction equilibrium exists. We demonstrate the versatility of our framework by showing that it subsumes the well-known full information and instantaneous information models, in addition to admitting further realistic predictors as special cases. We complement our theoretical analysis by an experimental study, in which we systematically compare the induced average travel times of different predictors, including a machine-learning model trained on data gained from previously computed equilibrium flows, both on a synthetic and a real road network.
Cite
Text
Graf et al. "Machine-Learned Prediction Equilibrium for Dynamic Traffic Assignment." AAAI Conference on Artificial Intelligence, 2022. doi:10.1609/AAAI.V36I5.20438Markdown
[Graf et al. "Machine-Learned Prediction Equilibrium for Dynamic Traffic Assignment." AAAI Conference on Artificial Intelligence, 2022.](https://mlanthology.org/aaai/2022/graf2022aaai-machine/) doi:10.1609/AAAI.V36I5.20438BibTeX
@inproceedings{graf2022aaai-machine,
title = {{Machine-Learned Prediction Equilibrium for Dynamic Traffic Assignment}},
author = {Graf, Lukas and Harks, Tobias and Kollias, Kostas and Markl, Michael},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2022},
pages = {5059-5067},
doi = {10.1609/AAAI.V36I5.20438},
url = {https://mlanthology.org/aaai/2022/graf2022aaai-machine/}
}