MAFE: Multi-Agent Fair Environments for Decision-Making Systems
This addresses the lack of realistic environments for fairness research in multi-agent systems, which is an incremental contribution to the field.
The paper tackles the problem of fairness in multi-agent decision-making systems by introducing Multi-Agent Fair Environments (MAFEs) as testbeds, with experimental results showing their utility for developing fair algorithms.
Fairness constraints applied to machine learning (ML) models in static contexts have been shown to potentially produce adverse outcomes among demographic groups over time. To address this issue, emerging research focuses on creating fair solutions that persist over time. While many approaches treat this as a single-agent decision-making problem, real-world systems often consist of multiple interacting entities that influence outcomes. Explicitly modeling these entities as agents enables more flexible analysis of their interventions and the effects they have on a system's underlying dynamics. A significant challenge in conducting research on multi-agent systems is the lack of realistic environments that leverage the limited real-world data available for analysis. To address this gap, we introduce the concept of a Multi-Agent Fair Environment (MAFE) and present and analyze three MAFEs that model distinct social systems. Experimental results demonstrate the utility of our MAFEs as testbeds for developing multi-agent fair algorithms.