Competing Bandits: The Perils of Exploration Under Competition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Aridor, Guy, Mansour, Yishay, Slivkins, Aleksandrs, Wu, Zhiwei Steven
Format: Preprint
Published: 2020
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916433918689280
author Aridor, Guy
Mansour, Yishay
Slivkins, Aleksandrs
Wu, Zhiwei Steven
author_facet Aridor, Guy
Mansour, Yishay
Slivkins, Aleksandrs
Wu, Zhiwei Steven
contents Most online platforms strive to learn from interactions with users, and many engage in exploration: making potentially suboptimal choices for the sake of acquiring new information. We study the interplay between exploration and competition: how such platforms balance the exploration for learning and the competition for users. Here users play three distinct roles: they are customers that generate revenue, they are sources of data for learning, and they are self-interested agents which choose among the competing platforms. We consider a stylized duopoly model in which two firms face the same multi-armed bandit problem. Users arrive one by one and choose between the two firms, so that each firm makes progress on its bandit problem only if it is chosen. Through a mix of theoretical results and numerical simulations, we study whether and to what extent competition incentivizes the adoption of better bandit algorithms, and whether it leads to welfare increases for users. We find that stark competition induces firms to commit to a "greedy" bandit algorithm that leads to low welfare. However, weakening competition by providing firms with some "free" users incentivizes better exploration strategies and increases welfare. We investigate two channels for weakening the competition: relaxing the rationality of users and giving one firm a first-mover advantage. Our findings are closely related to the "competition vs. innovation" relationship, and elucidate the first-mover advantage in the digital economy.
format Preprint
id arxiv_https___arxiv_org_abs_2007_10144
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Competing Bandits: The Perils of Exploration Under Competition
Aridor, Guy
Mansour, Yishay
Slivkins, Aleksandrs
Wu, Zhiwei Steven
Computer Science and Game Theory
Machine Learning
Theoretical Economics
Most online platforms strive to learn from interactions with users, and many engage in exploration: making potentially suboptimal choices for the sake of acquiring new information. We study the interplay between exploration and competition: how such platforms balance the exploration for learning and the competition for users. Here users play three distinct roles: they are customers that generate revenue, they are sources of data for learning, and they are self-interested agents which choose among the competing platforms. We consider a stylized duopoly model in which two firms face the same multi-armed bandit problem. Users arrive one by one and choose between the two firms, so that each firm makes progress on its bandit problem only if it is chosen. Through a mix of theoretical results and numerical simulations, we study whether and to what extent competition incentivizes the adoption of better bandit algorithms, and whether it leads to welfare increases for users. We find that stark competition induces firms to commit to a "greedy" bandit algorithm that leads to low welfare. However, weakening competition by providing firms with some "free" users incentivizes better exploration strategies and increases welfare. We investigate two channels for weakening the competition: relaxing the rationality of users and giving one firm a first-mover advantage. Our findings are closely related to the "competition vs. innovation" relationship, and elucidate the first-mover advantage in the digital economy.
title Competing Bandits: The Perils of Exploration Under Competition
topic Computer Science and Game Theory
Machine Learning
Theoretical Economics
url https://arxiv.org/abs/2007.10144