Saved in:
Bibliographic Details
Main Author: Conjeaud, Ivan
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2312.02644
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910600402042880
author Conjeaud, Ivan
author_facet Conjeaud, Ivan
contents We study a simple model of algorithmic collusion in which Q-learning algorithms are designed in a strategic fashion. We let players (\textit{designers}) choose their exploration policy simultaneously prior to letting their algorithms repeatedly play a prisoner's dilemma. We prove that, in equilibrium, collusive behavior is reached with positive probability. Our numerical simulations indicate symmetry of the equilibria and give insight for how they are affected by a parameter of interest. We also investigate general profiles of exploration policies. We characterize the behavior of the system for extreme profiles (fully greedy and fully explorative) and use numerical simulations and clustering methods to measure the likelihood of collusive behavior in general cases.
format Preprint
id arxiv_https___arxiv_org_abs_2312_02644
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Algorithmic collusion under competitive design
Conjeaud, Ivan
Theoretical Economics
We study a simple model of algorithmic collusion in which Q-learning algorithms are designed in a strategic fashion. We let players (\textit{designers}) choose their exploration policy simultaneously prior to letting their algorithms repeatedly play a prisoner's dilemma. We prove that, in equilibrium, collusive behavior is reached with positive probability. Our numerical simulations indicate symmetry of the equilibria and give insight for how they are affected by a parameter of interest. We also investigate general profiles of exploration policies. We characterize the behavior of the system for extreme profiles (fully greedy and fully explorative) and use numerical simulations and clustering methods to measure the likelihood of collusive behavior in general cases.
title Algorithmic collusion under competitive design
topic Theoretical Economics
url https://arxiv.org/abs/2312.02644