Learning in Random Utility Models Via Online Decision Problems

  title={Learning in Random Utility Models Via Online Decision Problems},
  author={Emerson Melo},
  • E. Melo
  • Published 21 December 2021
  • Economics, Computer Science
  • ArXiv
. This paper studies the Random Utility Model (RUM) in a repeated stochastic choice situation, in which the decision maker is imperfectly informed about the payoffs associated to each of the available alternatives. By embedding the RUM into an online decision problem, we develop a gradient-based learning algorithm and establish that a large class of RUMs are Hannan consistent (Hannan [1957]); that is, the average difference between the expected payoffs generated by a RUM and that of the best fixed… 

Tables from this paper

On the uniqueness of quantal response equilibria and its application to network games

  • E. Melo
  • Economics
    Economic Theory
  • 2021
This paper studies the uniqueness of a quantal response equilibrium (QRE) in a broad class of n-person normal form games. We make three main contributions. First, we show that the uniqueness of a QRE




Stochastic models of choice behavior

The notion of “utility” is fundamental in most current theories of human decision. The problem of determining the utility function of a given decision maker, however, presents grave difficulties. It

Random Orderings and Stochastic Theories of Responses (1960)

In interpreting human behavior there is a need to substitute ‘stochastic consistency of choices’ for ‘absolute consistency of choices’. The latter is usually assumed in economic theory, but is not

Regret in Decision Making under Uncertainty

By explicitly incorporating regret, expected utility theory not only becomes a better descriptive predictor but also may become a more convincing guide for prescribing behavior to decision makers.

Twenty Lectures on Algorithmic Game Theory

This book grew out of the author's Stanford University course on algorithmic game theory, and aims to give students and other newcomers a quick and accessible introduction to many of the most important concepts in the field.

Stochastic Choice and Preferences for Randomization

We conduct an experiment in which subjects face the same questions repeated multiple times, with repetitions of two types: (1) following the literature, the repetitions are distant from each other;

A simple adaptive procedure leading to correlated equilibrium

We propose a new and simple adaptive procedure for playing a game: ‘‘regret-matching.’’ In this procedure, players may depart from their current play with probabilities that are proportional to

Bayes Correlated Equilibrium and the Comparison of Information Structures in Games

A game of incomplete information can be decomposed into a basic game and an information structure. The basic game defines the set of actions, the set of payoff states the payoff functions and the

Recency, records and recaps: learning and non-equilibrium behavior in a simple decision problem

Nash equilibrium takes optimization as a primitive, but suboptimal behavior can persist in simple stochastic decision problems. This has motivated the development of other equilibrium concepts such

Online Linear Optimization via Smoothing

A new optimization-theoretic approach to analyzing Follow-the-Leader style algorithms, particularly in the setting where perturbations are used as a tool for regularization, and establishes an equivalence between “Follow the Regularized Leader” and ‘Follow the Perturbed Leader’ up to the smoothness properties.