Saved in:
Bibliographic Details
Main Authors: Bichler, Martin, Hoehener, Jan-Sebastian
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.17607
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914575783297024
author Bichler, Martin
Hoehener, Jan-Sebastian
author_facet Bichler, Martin
Hoehener, Jan-Sebastian
contents Autonomous pricing agents are widely deployed in online marketplaces, making algorithmic pricing a prominent application of multi-agent learning. Experimental studies often report collusive outcomes, but these findings typically rely on Q-learning in complete-information environments and lack rigorous convergence guarantees. In this paper, we study the stochastic learning dynamics of Regularized Robbins-Monro (RRM) algorithms in a Bayesian Bertrand competition with private costs. We show that this setting violates standard stability conditions, including monotonicity and the Minty variational inequality, rendering classical convergence results for gradient-based learning inapplicable. Despite this, we prove that Euclidean RRM algorithms converge almost surely to the unique, efficient Bayes-Nash equilibrium within a finite-dimensional approximation of the strategy space. By analyzing symmetric piecewise-linear pricing strategies in a duopoly, we explicitly construct a global Lyapunov function for the projected primal dynamics and establish global asymptotic stability of the equilibrium. Our analysis yields rigorous convergence guarantees for stochastic first-order learning algorithms in Bayesian Bertrand competition and provides a principled counterpoint to widespread claims of algorithmic collusion.
format Preprint
id arxiv_https___arxiv_org_abs_2605_17607
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Convergence of Stochastic First-Order Algorithms in Bertrand Competition Under Incomplete Information
Bichler, Martin
Hoehener, Jan-Sebastian
Computer Science and Game Theory
Autonomous pricing agents are widely deployed in online marketplaces, making algorithmic pricing a prominent application of multi-agent learning. Experimental studies often report collusive outcomes, but these findings typically rely on Q-learning in complete-information environments and lack rigorous convergence guarantees. In this paper, we study the stochastic learning dynamics of Regularized Robbins-Monro (RRM) algorithms in a Bayesian Bertrand competition with private costs. We show that this setting violates standard stability conditions, including monotonicity and the Minty variational inequality, rendering classical convergence results for gradient-based learning inapplicable. Despite this, we prove that Euclidean RRM algorithms converge almost surely to the unique, efficient Bayes-Nash equilibrium within a finite-dimensional approximation of the strategy space. By analyzing symmetric piecewise-linear pricing strategies in a duopoly, we explicitly construct a global Lyapunov function for the projected primal dynamics and establish global asymptotic stability of the equilibrium. Our analysis yields rigorous convergence guarantees for stochastic first-order learning algorithms in Bayesian Bertrand competition and provides a principled counterpoint to widespread claims of algorithmic collusion.
title Convergence of Stochastic First-Order Algorithms in Bertrand Competition Under Incomplete Information
topic Computer Science and Game Theory
url https://arxiv.org/abs/2605.17607