mlsanityData to 14 Oct 2026

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

arXiv 2502.04281 ↗First posted 6 Feb 2025cs.LG cs.CY cs.MAcited by 4

Not on the map. Why?

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.

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

15 of 23 references.

References · 15

  1. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  2. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  3. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  4. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,745
  5. 2020Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 485
  6. 2017Smart "Predict, then Optimize"cited by 339
  7. 2019Mitigating Bias in Algorithmic Hiring: Evaluating Claims and Practicescited by 174
  8. 2020Learning Fair Policies in Multiobjective (Deep) Reinforcement Learning with Average and Discounted Rewardscited by 60
  9. 2019Learning Fairness in Multi-Agent Systemscited by 44
  10. 2020Learning Fair Policies in Decentralized Cooperative Multi-Agent Reinforcement Learningcited by 40
  11. 2023Alleviating Matthew Effect of Offline Reinforcement Learning in Interactive Recommendationcited by 38
  12. 2021Reinforcement Learning for Ridesharing: An Extended Surveycited by 35
3 more
  1. 2019Neural Approximate Dynamic Programming for On-Demand Ride-Poolingcited by 33
  2. 2022Survey on Fair Reinforcement Learning: Theory and Practicecited by 14
  3. 2023Using Simple Incentives to Improve Two-Sided Fairness in Ridesharing Systemscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025Virtual Agent Economiescited by 21
  2. 2025Past-Discounting is Key for Learning Markovian Fairness with Long Horizonscited by 1
  3. 2026The Optimization Trilemma: Efficiency, Comfort and Fairness in Decentralized Multi-agent Coordinationcited by 0
  4. 2026Inference-Time Policy Alignment for Fair Reinforcement Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025A General Incentives-Based Framework for Fairness in Multi-agent Resource Allocation
  2. 2025AdaFair-MARL: Enforcing Adaptive Fairness Constraints in Multi-Agent Reinforcement Learning
  3. 2025MAFE: Enabling Equitable Algorithm Design in Multi-Agent Multi-Stage Decision-Making Systems
  4. 2026Fair Policy Optimization in Major-Minor Weakly Coupled Markov Decision Processes
  5. 2024Fair Resource Allocation in Weakly Coupled Markov Decision Processes
  6. 2023Achieving Fairness in Multi-Agent Markov Decision Processes Using Reinforcement Learning
  7. 2026FairTest: Search-Based Fairness Testing for Multi-Agent Reinforcement Learning Systems
  8. 2026α-fair heterogeneous agent reinforcement learning