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

  • Ashwin Kumar
  • , William Yeoh

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

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. 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.

Original languageEnglish
Title of host publicationProceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025
EditorsYevgeniy Vorobeychik, Sanmay Das, Ann Nowe
PublisherInternational Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
Pages2591-2593
Number of pages3
ISBN (Electronic)9798400714269
StatePublished - 2025
Event24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025 - Detroit, United States
Duration: May 19 2025May 23 2025

Publication series

NameProceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
ISSN (Print)1548-8403
ISSN (Electronic)1558-2914

Conference

Conference24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025
Country/TerritoryUnited States
CityDetroit
Period05/19/2505/23/25

Keywords

  • Fairness
  • Multi-Agent RL
  • Resource Allocation

Fingerprint

Dive into the research topics of 'DECAF: Learning to be Fair in Multi-agent Resource Allocation'. Together they form a unique fingerprint.

Cite this