What type of study is this?

This is a Quantitative Study study.

September 16, 2025Open Access

Learning in random utility models via online decision problems

Puntos clave

The proposed learning algorithm achieves Hannan consistency over time, indicating reduced average regret in decision-making.
Average regret relative to the best fixed action vanishes as more decisions are made, showcasing long-term effectiveness.
Embedding the Random Utility Model into a decision-making framework enhances optimization strategies in economics.
This approach applies to areas like recency bias and characterizing equilibria in normal-form games, broadening its relevance.

Resumen

Abstract 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 method, offering an economically grounded approach to online optimization. Applications include modeling recency bias and characterizing coarse correlated equilibria in normal‐form games.

Leer artículo completoexternamente

Preguntar a la IA

Me gusta

Guardar

Ver artículo completo