# DECAF: Learning to be Fair in Multi-agent Resource Allocation

arXiv: https://arxiv.org/abs/2502.04281 · HTML: https://mlsanity.com/paper/2502.04281/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 23 references that are in the map.
- First posted on arXiv 6 Feb 2025.

## Builds on (most cited first, 15 of 15)

- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Deep Reinforcement Learning with Double Q-learning](https://mlsanity.com/paper/1509.06461/) (2015)
- [Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2003.08839/) (2020)
- [Smart "Predict, then Optimize"](https://mlsanity.com/paper/1710.08005/) (2017)
- [Mitigating Bias in Algorithmic Hiring: Evaluating Claims and Practices](https://mlsanity.com/paper/1906.09208/) (2019)
- [Learning Fair Policies in Multiobjective (Deep) Reinforcement Learning with Average and Discounted Rewards](https://mlsanity.com/paper/2008.07773/) (2020)
- [Learning Fairness in Multi-Agent Systems](https://mlsanity.com/paper/1910.14472/) (2019)
- [Learning Fair Policies in Decentralized Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2012.09421/) (2020)
- [Alleviating Matthew Effect of Offline Reinforcement Learning in Interactive Recommendation](https://mlsanity.com/paper/2307.04571/) (2023)
- [Reinforcement Learning for Ridesharing: An Extended Survey](https://mlsanity.com/paper/2105.01099/) (2021)
- [Neural Approximate Dynamic Programming for On-Demand Ride-Pooling](https://mlsanity.com/paper/1911.08842/) (2019)
- [Survey on Fair Reinforcement Learning: Theory and Practice](https://mlsanity.com/paper/2205.10032/) (2022)
- [Using Simple Incentives to Improve Two-Sided Fairness in Ridesharing Systems](https://mlsanity.com/paper/2303.14332/) (2023)

## Built on by (most cited first, 4 of 4)

- [Virtual Agent Economies](https://mlsanity.com/paper/2509.10147/) (2025)
- [Past-Discounting is Key for Learning Markovian Fairness with Long Horizons](https://mlsanity.com/paper/2504.01154/) (2025)
- [The Optimization Trilemma: Efficiency, Comfort and Fairness in Decentralized Multi-agent Coordination](https://mlsanity.com/paper/2607.17311/) (2026)
- [Inference-Time Policy Alignment for Fair Reinforcement Learning](https://mlsanity.com/paper/2608.00175/) (2026)

## Abstract (arXiv)

A wide variety of resource allocation problems operate under resource constraints that are managed by a central arbitrator, with agents who evaluate and communicate preferences over these resources. We formulate this broad class of problems as Distributed Evaluation, Centralized Allocation (DECA) problems and propose methods to learn fair and efficient policies in centralized resource allocation. Our methods are applied to learning long-term fairness in a novel and general framework for fairness in multi-agent systems. We show three different methods based on Double Deep Q-Learning: (1) A joint weighted optimization of fairness and utility, (2) a split optimization, learning two separate Q-estimators for utility and fairness, and (3) an online policy perturbation to guide existing black-box utility functions toward fair solutions. Our methods outperform existing fair MARL approaches on multiple resource allocation domains, even when evaluated using diverse fairness functions, and allow for flexible online trade-offs between utility and fairness.