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

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.