Competing Bandits: Learning under Competition

TL;DR

This paper explores how competition influences the adoption of better learning algorithms in systems where users both generate revenue and provide data, analyzing the balance between exploration and user choice.

Contribution

It introduces a model of competing multi-armed bandit algorithms with user choice, examining how competition incentivizes the adoption of improved algorithms under various user response models.

Findings

Competition can incentivize the adoption of better bandit algorithms.

User rationality and competitiveness significantly affect algorithm adoption.

The study relates findings to economic theories of competition and innovation.

Abstract

Most modern systems strive to learn from interactions with users, and many engage in exploration: making potentially suboptimal choices for the sake of acquiring new information. We initiate a study of the interplay between exploration and competition--how such systems balance the exploration for learning and the competition for users. Here the 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 systems. In our model, we consider competition between two multi-armed bandit algorithms faced with the same bandit instance. Users arrive one by one and choose among the two algorithms, so that each algorithm makes progress if and only if it is chosen. We ask whether and to what extent competition incentivizes the adoption of better bandit algorithms. We investigate this issue for several models of user response, as we vary the degree of rationality and competitiveness in the model. Our findings are closely related to the "competition vs. innovation" relationship, a well-studied theme in economics.