No-Regret Learning in Stackelberg Games with an Application to Electric Ride-Hailing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Maddux, Anna, Maljkovic, Marko, Geroliminis, Nikolas, Kamgarpour, Maryam
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918241439318016
author Maddux, Anna
Maljkovic, Marko
Geroliminis, Nikolas
Kamgarpour, Maryam
author_facet Maddux, Anna
Maljkovic, Marko
Geroliminis, Nikolas
Kamgarpour, Maryam
contents We consider the problem of efficiently learning to play single-leader multi-follower Stackelberg games when the leader lacks knowledge of the lower-level game. Such games arise in hierarchical decision-making problems involving self-interested agents. For example, in electric ride-hailing markets, a central authority aims to learn optimal charging prices to shape fleet distributions and charging patterns of ride-hailing companies. Existing works typically apply gradient-based methods to find the leader's optimal strategy. Such methods are impractical as they require that the followers share private utility information with the leader. Instead, we treat the lower-level game as a black box, assuming only that the followers' interactions approximate a Nash equilibrium while the leader observes the realized cost of the resulting approximation. Under kernel-based regularity assumptions on the leader's cost function, we develop a no-regret algorithm that converges to an $ε$-Stackelberg equilibrium in $O(\sqrt{T})$ rounds. Finally, we validate our approach through a numerical case study on optimal pricing in electric ride-hailing markets.
format Preprint
id arxiv_https___arxiv_org_abs_2504_03745
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle No-Regret Learning in Stackelberg Games with an Application to Electric Ride-Hailing
Maddux, Anna
Maljkovic, Marko
Geroliminis, Nikolas
Kamgarpour, Maryam
Systems and Control
Computer Science and Game Theory
We consider the problem of efficiently learning to play single-leader multi-follower Stackelberg games when the leader lacks knowledge of the lower-level game. Such games arise in hierarchical decision-making problems involving self-interested agents. For example, in electric ride-hailing markets, a central authority aims to learn optimal charging prices to shape fleet distributions and charging patterns of ride-hailing companies. Existing works typically apply gradient-based methods to find the leader's optimal strategy. Such methods are impractical as they require that the followers share private utility information with the leader. Instead, we treat the lower-level game as a black box, assuming only that the followers' interactions approximate a Nash equilibrium while the leader observes the realized cost of the resulting approximation. Under kernel-based regularity assumptions on the leader's cost function, we develop a no-regret algorithm that converges to an $ε$-Stackelberg equilibrium in $O(\sqrt{T})$ rounds. Finally, we validate our approach through a numerical case study on optimal pricing in electric ride-hailing markets.
title No-Regret Learning in Stackelberg Games with an Application to Electric Ride-Hailing
topic Systems and Control
Computer Science and Game Theory
url https://arxiv.org/abs/2504.03745