Strategic Arms with Side Communication Prevail Over Low-Regret MAB Algorithms

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yahmed, Ahmed Ben, Calauzènes, Clément, Perchet, Vianney
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909301377859584
author Yahmed, Ahmed Ben
Calauzènes, Clément
Perchet, Vianney
author_facet Yahmed, Ahmed Ben
Calauzènes, Clément
Perchet, Vianney
contents In the strategic multi-armed bandit setting, when arms possess perfect information about the player's behavior, they can establish an equilibrium where: 1. they retain almost all of their value, 2. they leave the player with a substantial (linear) regret. This study illustrates that, even if complete information is not publicly available to all arms but is shared among them, it is possible to achieve a similar equilibrium. The primary challenge lies in designing a communication protocol that incentivizes the arms to communicate truthfully.
format Preprint
id arxiv_https___arxiv_org_abs_2408_17101
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Strategic Arms with Side Communication Prevail Over Low-Regret MAB Algorithms
Yahmed, Ahmed Ben
Calauzènes, Clément
Perchet, Vianney
Artificial Intelligence
In the strategic multi-armed bandit setting, when arms possess perfect information about the player's behavior, they can establish an equilibrium where: 1. they retain almost all of their value, 2. they leave the player with a substantial (linear) regret. This study illustrates that, even if complete information is not publicly available to all arms but is shared among them, it is possible to achieve a similar equilibrium. The primary challenge lies in designing a communication protocol that incentivizes the arms to communicate truthfully.
title Strategic Arms with Side Communication Prevail Over Low-Regret MAB Algorithms
topic Artificial Intelligence
url https://arxiv.org/abs/2408.17101