Procedural Fairness in Multi-Agent Bandits

Joshua Caiata, Carter Blair, Kate Larson

Keywords: Fairness, Multi-armed Bandits, Multi-agent Systems

TL;DR: Instead of optimizing for some outcome, we show that focusing on designing a fair procedure naturally yields strong outcomes, and that decision-making power should be a focus to building multi-agent systems.

Abstract: In the context of multi-agent multi-armed bandits (MA-MAB), fairness is often reduced to outcomes: maximizing welfare, reducing inequality, or balancing utilities. However, evidence in psychology, economics, and Rawlsian theory suggests that fairness is also about process and who gets a say in the decisions being made. We introduce a new fairness objective, procedural fairness, which provides equal decision-making power for all agents, lies in the core, and provides for proportionality in outcomes. Further, empirical results confirm that fairness notions based on optimizing for outcomes sacrifice equal voice and representation, while the sacrifice in outcome-based fairness objectives (like equality and utilitarianism) is minimal under procedurally fair policies. We further prove that different fairness notions prioritize fundamentally different and incompatible values, highlighting that fairness requires explicit normative choices. This paper posits that legitimacy should be increasingly prioritized as a fairness objective and provides a framework for putting procedural fairness into practice.

Area: Game Theory and Economic Paradigms (GTEP)

Generative A I: I acknowledge that I have read and will follow this policy.

Submission Number: 1341