Procedural Fairness in Multi-Agent Bandits
This work addresses fairness for multi-agent systems by shifting focus from outcomes to process, offering a novel framework that is incremental in its application to bandit problems.
The paper tackles the problem of fairness in multi-agent multi-armed bandits by introducing procedural fairness, which emphasizes equal decision-making power for all agents, and finds that it minimally sacrifices outcome-based fairness objectives like equality and utilitarianism.
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. 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 argues that procedural legitimacy deserves greater focus as a fairness objective, and provides a framework for putting procedural fairness into practice.