Simulation code for ACM CS&Law 2025 paper

This repository contains the simulation code for Section 6 of our paper "Regulation of Algorithmic Collusion, Refined: Testing Pessimistic Calibrated Regret" appearing at ACM CS&Law 2025. The simulation is designed to test the effect of unknown costs of the auditing method.

Running the simulation

pip install -r requirements.txt
./run.sh

To modify the configuration, edit config.py as needed.

Citation

@inproceedings{10.1145/3709025.3712217,
    author = {Hartline, Jason D. and Wang, Chang and Zhang, Chenhao},
    title = {Regulation of Algorithmic Collusion, Refined: Testing Pessimistic Calibrated Regret},
    year = {2025},
    isbn = {9798400714214},
    publisher = {Association for Computing Machinery},
    address = {New York, NY, USA},
    url = {https://doi.org/10.1145/3709025.3712217},
    doi = {10.1145/3709025.3712217},
    booktitle = {Proceedings of the 2025 Symposium on Computer Science and Law},
    pages = {108–120},
    numpages = {13},
    keywords = {Algorithmic collusion, Algorithmic pricing, Antitrust, Regulation of algorithms},
    location = {Munich, Germany},
    series = {CSLAW '25}
}