Fairness in Multi-Agent Sequential Decision-Making
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...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Neural Information Processing Systems Foundation Inc.
2017
|
| Online Access: | http://hdl.handle.net/1721.1/109304 https://orcid.org/0000-0001-5545-1691 https://orcid.org/0000-0003-1338-8107 |
| _version_ | 1826188390779846656 |
|---|---|
| author | Zhang, Chongjie Shah, Julie A |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Zhang, Chongjie Shah, Julie A |
| author_sort | Zhang, Chongjie |
| collection | MIT |
| description | 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. |
| first_indexed | 2024-09-23T07:58:54Z |
| format | Article |
| id | mit-1721.1/109304 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T07:58:54Z |
| publishDate | 2017 |
| publisher | Neural Information Processing Systems Foundation Inc. |
| record_format | dspace |
| spelling | mit-1721.1/1093042022-09-30T01:30:03Z Fairness in Multi-Agent Sequential Decision-Making Zhang, Chongjie Shah, Julie A Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Zhang, Chongjie Shah, Julie A 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. 2017-05-24T13:21:03Z 2017-05-24T13:21:03Z 2014-12 2014-12 Article http://purl.org/eprint/type/ConferencePaper http://hdl.handle.net/1721.1/109304 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. https://orcid.org/0000-0001-5545-1691 https://orcid.org/0000-0003-1338-8107 en_US https://papers.nips.cc/paper/5588-fairness-in-multi-agent-sequential-decision-making Advances in Neural Information Processing Systems 27 (NIPS 2014) 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. application/pdf Neural Information Processing Systems Foundation Inc. NIPS |
| spellingShingle | Zhang, Chongjie Shah, Julie A Fairness in Multi-Agent Sequential Decision-Making |
| title | Fairness in Multi-Agent Sequential Decision-Making |
| title_full | Fairness in Multi-Agent Sequential Decision-Making |
| title_fullStr | Fairness in Multi-Agent Sequential Decision-Making |
| title_full_unstemmed | Fairness in Multi-Agent Sequential Decision-Making |
| title_short | Fairness in Multi-Agent Sequential Decision-Making |
| title_sort | fairness in multi agent sequential decision making |
| url | http://hdl.handle.net/1721.1/109304 https://orcid.org/0000-0001-5545-1691 https://orcid.org/0000-0003-1338-8107 |
| work_keys_str_mv | AT zhangchongjie fairnessinmultiagentsequentialdecisionmaking AT shahjuliea fairnessinmultiagentsequentialdecisionmaking |