Fairness in Multi-Agent Sequential Decision-Making
Name
Shah_Fairness in multi.pdf
Size
216.09 KB
Format
Adobe PDF
Checksum (MD5)
a19dc9017e44e8a1205a0fb16aea6def
Author(s)
Zhang, Chongjie
Shah, Julie A
Date Issued
December 2014
Journal
Advances in Neural Information Processing Systems 27 (NIPS 2014)
Publisher
Neural Information Processing Systems Foundation Inc.
Citation
Zhang, Chongjie and Shah, Julie A. "Fairness in Multi-Agent Sequential Decision-Making." Advances in Neural Information Processing Systems 27 (NIPS 2014), December 8-13 2014 Palais des Congrès de Montréal, Montréal, Canada, Neural Information Processing Systems Foundation Inc., December 2014 © 2014 Neural Information Processing Systems Foundation Inc.
Version
Final published version
Abstract
We define a fairness solution criterion for multi-agent decision-making problems, where agents have local interests. This new criterion aims to maximize the worst performance of agents with consideration on the overall performance. We develop a simple linear programming approach and a more scalable game-theoretic approach for computing an optimal fairness policy. This game-theoretic approach formulates this fairness optimization as a two-player, zero-sum game and employs an iterative algorithm for finding a Nash equilibrium, corresponding to an optimal fairness policy. We scale up this approach by exploiting problem structure and value function approximation. Our experiments on resource allocation problems show that this fairness criterion provides a more favorable solution than the utilitarian criterion, and that our game-theoretic approach is significantly faster than linear programming.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://papers.nips.cc/paper/5588-fairness-in-multi-agent-sequential-decision-making
