Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Melo, Emerson
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2506.16030
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913901323485184
author Melo, Emerson
author_facet Melo, Emerson
contents This paper examines the Random Utility Model (RUM) in repeated stochastic choice settings where decision-makers lack full information about payoffs. We propose a gradient-based learning algorithm that embeds RUM into an online decision-making framework. Our analysis establishes Hannan consistency for a broad class of RUMs, meaning the average regret relative to the best fixed action in hindsight vanishes over time. We also show that our algorithm is equivalent to the Follow-The-Regularized-Leader (FTRL) method, offering an economically grounded approach to online optimization. Applications include modeling recency bias and characterizing coarse correlated equilibria in normal-form games
format Preprint
id arxiv_https___arxiv_org_abs_2506_16030
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning in Random Utility Models Via Online Decision Problems
Melo, Emerson
Theoretical Economics
This paper examines the Random Utility Model (RUM) in repeated stochastic choice settings where decision-makers lack full information about payoffs. We propose a gradient-based learning algorithm that embeds RUM into an online decision-making framework. Our analysis establishes Hannan consistency for a broad class of RUMs, meaning the average regret relative to the best fixed action in hindsight vanishes over time. We also show that our algorithm is equivalent to the Follow-The-Regularized-Leader (FTRL) method, offering an economically grounded approach to online optimization. Applications include modeling recency bias and characterizing coarse correlated equilibria in normal-form games
title Learning in Random Utility Models Via Online Decision Problems
topic Theoretical Economics
url https://arxiv.org/abs/2506.16030