{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T18:45:03Z","timestamp":1782758703670,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T00:00:00Z","timestamp":1782345600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,25]]},"DOI":"10.1145\/3805689.3806494","type":"proceedings-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T17:52:08Z","timestamp":1782755528000},"page":"4133-4161","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning Fairness in Multi-agent Systems with Distributed-Evaluation, Centralized-AIIocation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-8782-1388","authenticated-orcid":false,"given":"Ashwin","family":"Kumar","sequence":"first","affiliation":[{"name":"Washington University in St. Louis, St Louis, MO, USA, and Meta, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2617-870X","authenticated-orcid":false,"given":"William","family":"Yeoh","sequence":"additional","affiliation":[{"name":"Washington University in St. Louis, St Louis, MO, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,25]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611675114"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.12233"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2090236.2090255"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2020.3922"},{"key":"e_1_3_2_1_5_1","volume-title":"Survey on Fair Reinforcement Learning: Theory and Practice. arXiv preprint arXiv:2205.10032","author":"Gajane Pratik","year":"2022","unstructured":"Pratik Gajane, Akrati Saxena, Maryam Tavakol, George Fletcher, and Mykola Pechenizkiy. 2022. Survey on Fair Reinforcement Learning: Theory and Practice. arXiv preprint arXiv:2205.10032 (2022)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591636"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the Conference on Neural Information Processing Systems. 3323\u20133331","author":"Hardt Moritz","year":"2016","unstructured":"Moritz Hardt, Eric Price, and Nati Srebro. 2016. Equality of opportunity in supervised learning. In Proceedings of the Conference on Neural Information Processing Systems. 3323\u20133331."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the Conference on Neural Information Processing Systems. 13854\u201313865","author":"Jiang Jiechuan","year":"2019","unstructured":"Jiechuan Jiang and Zongqing Lu. 2019. Learning fairness in multi-agent systems. In Proceedings of the Conference on Neural Information Processing Systems. 13854\u201313865."},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence. 622\u2013629","author":"Kube Amanda R.","unstructured":"Amanda R. Kube, Sanmay Das, and Patrick J. Fowler. 2019. Allocating interventions based on predicted outcomes: A case study on homelessness services. In Proceedings of the AAAI Conference on Artificial Intelligence. 622\u2013629."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocad052"},{"key":"e_1_3_2_1_12_1","unstructured":"Ashwin Kumar. 2025. Towards Fair Sequential Resource Allocation: Algorithmic Designs Interventions and Evaluations. Ph.D. Dissertation. Washington University in St. Louis."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v33i1.27199"},{"key":"e_1_3_2_1_14_1","volume-title":"Past-Discounting is Key for Learning Markovian Fairness with Long Horizons. arXiv preprint arXiv:2504.01154","author":"Kumar Ashwin","year":"2025","unstructured":"Ashwin Kumar and William Yeoh. 2025. Past-Discounting is Key for Learning Markovian Fairness with Long Horizons. arXiv preprint arXiv:2504.01154 (2025)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.65109\/GQAG8531"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3457607"},{"key":"e_1_3_2_1_17_1","volume-title":"Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602","author":"Mnih Volodymyr","year":"2013","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin Riedmiller. 2013. Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103852"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372828"},{"key":"e_1_3_2_1_20_1","first-page":"1","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid Tabish","year":"2020","unstructured":"Tabish Rashid, Mikayel Samvelyan, Christian Schroeder De Witt, Gregory Farquhar, Jakob Foerster, and Shimon Whiteson. 2020. Monotonic value function factorisation for deep multi-agent reinforcement learning. Journal of Machine Learning Research 21, 178 (2020), 1\u201351.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_21_1","volume-title":"The Matthew Effect: How Advantage Begets Further Advantage","author":"Rigney Daniel","unstructured":"Daniel Rigney. 2010. The Matthew Effect: How Advantage Begets Further Advantage. Columbia University Press."},{"key":"e_1_3_2_1_22_1","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5388"},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the International Conference on Machine Learning. 8905\u20138915","author":"Siddique Umer","year":"2020","unstructured":"Umer Siddique, Paul Weng, and Matthieu Zimmer. 2020. Learning fair policies in multi-objective (deep) reinforcement learning with average and discounted rewards. In Proceedings of the International Conference on Machine Learning. 8905\u20138915."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.65109\/JSRC7365"},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the Conference on Neural Information Processing Systems. 8795\u20138806","author":"Wang Kai","year":"2021","unstructured":"Kai Wang, Sanket Shah, Haipeng Chen, Andrew Perrault, Finale Doshi-Velez, and Milind Tambe. 2021. Learning MDPs from features: Predict-then-optimize for sequential decision making by reinforcement learning. In Proceedings of the Conference on Neural Information Processing Systems. 8795\u20138806."},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the International Conference on Machine Learning. 12967\u201312978","author":"Zimmer Matthieu","year":"2021","unstructured":"Matthieu Zimmer, Claire Glanois, Umer Siddique, and Paul Weng. 2021. Learning fair policies in decentralized cooperative multi-agent reinforcement learning. In Proceedings of the International Conference on Machine Learning. 12967\u201312978."}],"event":{"name":"FAccT '26: The 2026 ACM Conference on Fairness, Accountability, and Transparency","location":"Montreal QC Canada","acronym":"FAccT '26","sponsor":["ACM\/SIG"]},"container-title":["Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3805689.3806494","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T18:02:41Z","timestamp":1782756161000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805689.3806494"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,25]]},"references-count":27,"alternative-id":["10.1145\/3805689.3806494","10.1145\/3805689"],"URL":"https:\/\/doi.org\/10.1145\/3805689.3806494","relation":{},"subject":[],"published":{"date-parts":[[2026,6,25]]},"assertion":[{"value":"2026-06-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}