# AdaFair-MARL: Enforcing Adaptive Fairness Constraints in Multi-Agent Reinforcement Learning

arXiv: https://arxiv.org/abs/2511.14135 · HTML: https://mlsanity.com/paper/2511.14135/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 32 references that are in the map.
- First posted on arXiv 18 Nov 2025.

## Builds on (most cited first, 18 of 18)

- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Constrained Policy Optimization](https://mlsanity.com/paper/1705.10528/) (2017)
- [The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games](https://mlsanity.com/paper/2103.01955/) (2021)
- [Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2003.08839/) (2020)
- [On the Utility of Learning about Humans for Human-AI Coordination](https://mlsanity.com/paper/1910.05789/) (2019)
- [Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks](https://mlsanity.com/paper/2006.07869/) (2020)
- [SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2212.07489/) (2022)
- [Inequity aversion improves cooperation in intertemporal social dilemmas](https://mlsanity.com/paper/1803.08884/) (2018)
- [Robotouille: An Asynchronous Planning Benchmark for LLM Agents](https://mlsanity.com/paper/2502.05227/) (2025)
- [The Confluence of Networks, Games and Learning](https://mlsanity.com/paper/2105.08158/) (2021)
- [Rapidly Built Medical Crash Cart! Lessons Learned and Impacts on High-Stakes Team Collaboration in the Emergency Room](https://mlsanity.com/paper/2502.18688/) (2025)
- [Skill-Aligned Fairness in Multi-Agent Learning for Collaboration in Healthcare](https://mlsanity.com/paper/2508.18708/) (2025)
- [A Parametric, Second-Order Cone Representable Model of Fairness for Decision-Making Problems](https://mlsanity.com/paper/2412.05143/) (2024)
- [Fairness Aware Reinforcement Learning via Proximal Policy Optimization](https://mlsanity.com/paper/2502.03953/) (2025)
- [Human-Robot Teaming Field Deployments: A Comparison Between Verbal and Non-verbal Communication](https://mlsanity.com/paper/2506.08890/) (2025)
- [Help or Hindrance: Understanding the Impact of Robot Communication in Action Teams](https://mlsanity.com/paper/2506.08892/) (2025)
- [Equinox: Holistic Fair Scheduling in Serving Large Language Models](https://mlsanity.com/paper/2508.16646/) (2025)
- [Task Allocation for Multi-agent Systems via Unequal-dimensional Optimal Transport](https://mlsanity.com/paper/2503.09369/) (2025)

## Abstract (arXiv)

Fair workload enforcement in heterogeneous multi-agent systems that pursue shared objectives remains challenging. Fixed fairness penalties often introduce inefficiencies, training instability, and conflicting agent incentives. Reward-shaping approaches in fair Multi-Agent Reinforcement Learning (MARL) typically incorporate fairness through heuristic penalties or scalar reward modifications and often rely on post-hoc evaluation. However, these methods do not guarantee that a desired fairness level will be satisfied. To address this limitation, we propose the Adaptive Fairness Multi-Agent Reinforcement Learning (AdaFair-MARL) framework, which formulates workload fairness as an explicit constraint so that agents maintain balanced contributions while optimizing team performance. We present AdaFair-MARL, a constrained cooperative MARL framework whose core algorithmic component is a primal-dual update that enforces workload fairness via adaptive Lagrange multiplier updates. Grounding the framework in a cooperative Markov game, we derive the fairness constraint from Jain's Fairness Index (JFI) geometry and show that the resulting feasible set admits a second-order cone representation, enabling principled Lagrangian dual-ascent updates without manual penalty tuning. Experiments in a simulated hospital coordination environment (MARLHospital) demonstrate the effectiveness of AdaFair-MARL compared to reward-shaping and fixed-penalty fairness methods, improving workload balance while maintaining team performance. We found that AdaFair-MARL achieves nearly perfect constraint satisfaction (0.99-1.00) while significantly improving workload fairness compared to fixed-penalty baselines.