MAFE: Enabling Equitable Algorithm Design in Multi-Agent Multi-Stage Decision-Making Systems
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918326311059456 |
|---|---|
| author | Lazri, Zachary McBride Nakra, Anirudh Brugere, Ivan Dervovic, Danial Polychroniadou, Antigoni Huang, Furong Dachman-Soled, Dana Wu, Min |
| author_facet | Lazri, Zachary McBride Nakra, Anirudh Brugere, Ivan Dervovic, Danial Polychroniadou, Antigoni Huang, Furong Dachman-Soled, Dana Wu, Min |
| contents | Algorithmic fairness is often studied in static or single-agent settings, yet many real-world decision-making systems involve multiple interacting entities whose multi-stage actions jointly influence long-term outcomes. Existing fairness methods applied at isolated decision points frequently fail to mitigate disparities that accumulate over time. Although recent work has modeled fairness as a sequential decision-making problem, it typically assumes centralized agents or simplified dynamics, limiting its applicability to complex social systems. We introduce MAFE, a suite of Multi-Agent Fair Environments designed to simulate realistic, modular, and dynamic systems in which fairness emerges from the interplay of multiple agents. We demonstrate MAFEs across three domains -- loan processing, healthcare, and higher education -- that support heterogeneous agents, configurable interventions, and fairness metrics. The environments are open-source and compatible with standard multi-agent reinforcement learning (MARL) libraries, enabling reproducible evaluation of fairness-aware policies. Through extensive experiments on cooperative use cases, we demonstrate how MAFE facilitates the design of equitable multi-agent algorithms and reveals critical trade-offs between fairness, performance, and coordination. MAFE provides a foundation for systematic progress in dynamic, multi-agent fairness research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_18534 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MAFE: Enabling Equitable Algorithm Design in Multi-Agent Multi-Stage Decision-Making Systems Lazri, Zachary McBride Nakra, Anirudh Brugere, Ivan Dervovic, Danial Polychroniadou, Antigoni Huang, Furong Dachman-Soled, Dana Wu, Min Multiagent Systems Artificial Intelligence Algorithmic fairness is often studied in static or single-agent settings, yet many real-world decision-making systems involve multiple interacting entities whose multi-stage actions jointly influence long-term outcomes. Existing fairness methods applied at isolated decision points frequently fail to mitigate disparities that accumulate over time. Although recent work has modeled fairness as a sequential decision-making problem, it typically assumes centralized agents or simplified dynamics, limiting its applicability to complex social systems. We introduce MAFE, a suite of Multi-Agent Fair Environments designed to simulate realistic, modular, and dynamic systems in which fairness emerges from the interplay of multiple agents. We demonstrate MAFEs across three domains -- loan processing, healthcare, and higher education -- that support heterogeneous agents, configurable interventions, and fairness metrics. The environments are open-source and compatible with standard multi-agent reinforcement learning (MARL) libraries, enabling reproducible evaluation of fairness-aware policies. Through extensive experiments on cooperative use cases, we demonstrate how MAFE facilitates the design of equitable multi-agent algorithms and reveals critical trade-offs between fairness, performance, and coordination. MAFE provides a foundation for systematic progress in dynamic, multi-agent fairness research. |
| title | MAFE: Enabling Equitable Algorithm Design in Multi-Agent Multi-Stage Decision-Making Systems |
| topic | Multiagent Systems Artificial Intelligence |
| url | https://arxiv.org/abs/2502.18534 |