{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T01:13:16Z","timestamp":1755825196967,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,3,4]],"date-time":"2024-03-04T00:00:00Z","timestamp":1709510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006374","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-2312865, IIS-2008139, CCF 2312774"],"award-info":[{"award-number":["IIS-2312865, IIS-2008139, CCF 2312774"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,3,4]]},"DOI":"10.1145\/3616855.3635819","type":"proceedings-article","created":{"date-parts":[[2024,3,4]],"date-time":"2024-03-04T18:18:12Z","timestamp":1709576292000},"page":"47-56","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Ranking with Long-Term Constraints"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8395-594X","authenticated-orcid":false,"given":"Kiant\u00e9","family":"Brantley","sequence":"first","affiliation":[{"name":"Cornell University, Ithaca, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1599-4517","authenticated-orcid":false,"given":"Zhichong","family":"Fang","sequence":"additional","affiliation":[{"name":"Cornell University, Ithaca, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5614-3532","authenticated-orcid":false,"given":"Sarah","family":"Dean","sequence":"additional","affiliation":[{"name":"Cornell University, Ithaca, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3654-3683","authenticated-orcid":false,"given":"Thorsten","family":"Joachims","sequence":"additional","affiliation":[{"name":"Cornell University, Ithaca, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,3,4]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543846"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623366"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the twenty-sixth annual ACM-SIAM symposium on Discrete algorithms. SIAM, 1405--1424","author":"Agrawal Shipra","year":"2014","unstructured":"Shipra Agrawal and Nikhil R Devanur. 2014. Fast algorithms for online stochastic convex programming. In Proceedings of the twenty-sixth annual ACM-SIAM symposium on Discrete algorithms. SIAM, 1405--1424."},{"key":"e_1_3_2_1_4_1","volume-title":"International conference on learning representations.","author":"Andrychowicz Marcin","year":"2020","unstructured":"Marcin Andrychowicz, Anton Raichuk, Piotr Staczyk, Manu Orsini, Sertan Girgin, Rapha\u00ebl Marinier, Leonard Hussenot, Matthieu Geist, Olivier Pietquin, Marcin Michalski, et al. 2020. What matters for on-policy deep actor-critic methods? a large-scale study. In International conference on learning representations."},{"key":"e_1_3_2_1_5_1","volume-title":"Feedback Systems: An Introduction for Scientists and Engineers","author":"Astroem Karl Johan","year":"2020","unstructured":"Karl Johan Astroem and Richard Murray. 2020. Feedback Systems: An Introduction for Scientists and Engineers. Princeton University Press."},{"key":"e_1_3_2_1_6_1","first-page":"147","article-title":"Tres observaciones sobre el algebra lineal","volume":"5","author":"Birkhoff Garrett","year":"1946","unstructured":"Garrett Birkhoff. 1946. Tres observaciones sobre el algebra lineal. Univ. Nac. Tucuman, Ser. A 5 (1946), 147--154.","journal-title":"Univ. Nac. Tucuman, Ser. A"},{"volume-title":"Predictive control for linear and hybrid systems","author":"Borrelli Francesco","key":"e_1_3_2_1_7_1","unstructured":"Francesco Borrelli, Alberto Bemporad, and Manfred Morari. 2017. Predictive control for linear and hybrid systems. Cambridge University Press."},{"key":"e_1_3_2_1_8_1","volume-title":"Estimating and Penalizing Preference Shift in Recommender Systems. In Fifteenth ACM Conference on Recommender Systems. 661--667","author":"Carroll Micah","year":"2021","unstructured":"Micah Carroll, Dylan Hadfield-Menell, Stuart Russell, and Anca Dragan. 2021. Estimating and Penalizing Preference Shift in Recommender Systems. In Fifteenth ACM Conference on Recommender Systems. 661--667."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287601"},{"key":"e_1_3_2_1_10_1","volume-title":"Ranking with fairness constraints. arXiv preprint arXiv:1704.06840","author":"Celis L Elisa","year":"2017","unstructured":"L Elisa Celis, Damian Straszak, and Nisheeth K Vishnoi. 2017. Ranking with fairness constraints. arXiv preprint arXiv:1704.06840 (2017)."},{"key":"e_1_3_2_1_11_1","volume-title":"An Experimental Comparison of Click Position-bias Models. In International Conference on Web Search and Data Mining (WSDM). ACM, 87--94","author":"Craswell Nick","year":"2008","unstructured":"Nick Craswell, Onno Zoeter, Michael Taylor, and Bill Ramsey. 2008. An Experimental Comparison of Click Position-bias Models. In International Conference on Web Search and Data Mining (WSDM). ACM, 87--94."},{"key":"e_1_3_2_1_12_1","volume-title":"Implementation matters in deep policy gradients: A case study on ppo and trpo. arXiv preprint arXiv:2005.12729","author":"Engstrom Logan","year":"2020","unstructured":"Logan Engstrom, Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Firdaus Janoos, Larry Rudolph, and Aleksander Madry. 2020. Implementation matters in deep policy gradients: A case study on ppo and trpo. arXiv preprint arXiv:2005.12729 (2020)."},{"key":"e_1_3_2_1_13_1","volume-title":"User Tampering in Reinforcement Learning Recommender Systems. arXiv preprint arXiv:2109.04083","author":"Evans Charles","year":"2021","unstructured":"Charles Evans and Atoosa Kasirzadeh. 2021. User Tampering in Reinforcement Learning Recommender Systems. arXiv preprint arXiv:2109.04083 (2021)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11229-021-03141-4"},{"key":"e_1_3_2_1_15_1","volume-title":"Reinforcement learning with a corrupted reward channel. arXiv preprint arXiv:1705.08417","author":"Everitt Tom","year":"2017","unstructured":"Tom Everitt, Victoria Krakovna, Laurent Orseau, Marcus Hutter, and Shane Legg. 2017. Reinforcement learning with a corrupted reward channel. arXiv preprint arXiv:1705.08417 (2017)."},{"key":"e_1_3_2_1_16_1","volume-title":"RecSys 2020 Workshop on Online Misinformation- and Harm-Aware Recommender Systems (CEUR Workshop Proceedings","volume":"50","author":"Fern\u00e1ndez Miriam","year":"2020","unstructured":"Miriam Fern\u00e1ndez and Alejandro Bellog\u00edn. 2020. Recommender Systems and Misinformation: The Problem or the Solution?. In RecSys 2020 Workshop on Online Misinformation- and Harm-Aware Recommender Systems (CEUR Workshop Proceedings, Vol. 2758), Antonela Tommasel, Daniela Godoy, and Arkaitz Zubiaga (Eds.). CEUR-WS.org, 40--50. http:\/\/ceur-ws.org\/Vol-2758\/OHARS-paper3.pdf"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557220"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441824"},{"key":"e_1_3_2_1_19_1","volume-title":"Reward reports for reinforcement learning. arXiv preprint arXiv:2204.10817","author":"Gilbert Thomas Krendl","year":"2022","unstructured":"Thomas Krendl Gilbert, Nathan Lambert, Sarah Dean, Tom Zick, and Aaron Snoswell. 2022. Reward reports for reinforcement learning. arXiv preprint arXiv:2204.10817 (2022)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2788583"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2187836.2187839"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/582415.582418"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2007.68"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018699"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2013.6580779"},{"key":"e_1_3_2_1_27_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_28_1","volume-title":"Hidden Incentives for Auto-Induced Distributional Shift. arXiv preprint arXiv:2009.09153","author":"Krueger David","year":"2020","unstructured":"David Krueger, Tegan Maharaj, and Jan Leike. 2020. Hidden Incentives for Auto-Induced Distributional Shift. arXiv preprint arXiv:2009.09153 (2020)."},{"key":"e_1_3_2_1_29_1","volume-title":"A survey on reinforcement learning for recommender systems","author":"Lin Yuanguo","year":"2023","unstructured":"Yuanguo Lin, Yong Liu, Fan Lin, Lixin Zou, Pengcheng Wu, Wenhua Zeng, Huanhuan Chen, and Chunyan Miao. 2023. A survey on reinforcement learning for recommender systems. IEEE Transactions on Neural Networks and Learning Systems (2023)."},{"key":"e_1_3_2_1_30_1","unstructured":"localify [n. d.]. Localify: Local Artist and Music Event Recommendation Application. http:\/\/www.localify.org\/. http:\/\/www.localify.org\/"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412152"},{"key":"e_1_3_2_1_32_1","volume-title":"Fairness and Satisfaction in Recommendation Systems. In ACM Conference on Information and Knowledge Management (CIKM).","author":"Mehrotra Rishabh","year":"2018","unstructured":"Rishabh Mehrotra, James McInerney, Hugues Bouchard, Mounia Lalmas, and Fernando Diaz. 2018. Towards a Fair Marketplace: Counterfactual Evaluation of the trade-off between Relevance, Fairness and Satisfaction in Recommendation Systems. In ACM Conference on Information and Knowledge Management (CIKM)."},{"key":"e_1_3_2_1_33_1","volume-title":"International Conference on Machine Learning. PMLR, 6987--6998","author":"Mladenov Martin","year":"2020","unstructured":"Martin Mladenov, Elliot Creager, Omer Ben-Porat, Kevin Swersky, Richard Zemel, and Craig Boutilier. 2020. Optimizing long-term social welfare in recommender systems: A constrained matching approach. In International Conference on Machine Learning. PMLR, 6987--6998."},{"key":"e_1_3_2_1_34_1","unstructured":"Jamie Morgenstern. 2021. Ensuring equity in online advertising for employment housing and credit. Medium https:\/\/jamiemmt-cs.medium.com\/ensuring-equity-in-online-advertising-for-employment-housing-and-credit-82931668c420."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401100"},{"key":"e_1_3_2_1_36_1","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume":"99","author":"Ng Andrew Y","year":"1999","unstructured":"Andrew Y Ng, Daishi Harada, and Stuart Russell. 1999. Policy invariance under reward transformations: Theory and application to reward shaping. In Icml, Vol. 99. 278--287.","journal-title":"Icml"},{"key":"e_1_3_2_1_37_1","first-page":"2","article-title":"Algorithms for inverse reinforcement learning","volume":"1","author":"Ng Andrew Y","year":"2000","unstructured":"Andrew Y Ng, Stuart Russell, et al. 2000. Algorithms for inverse reinforcement learning. In Icml, Vol. 1. 2.","journal-title":"Icml"},{"key":"e_1_3_2_1_38_1","volume-title":"The effects of reward misspecification: Mapping and mitigating misaligned models. arXiv preprint arXiv:2201.03544","author":"Pan Alexander","year":"2022","unstructured":"Alexander Pan, Kush Bhatia, and Jacob Steinhardt. 2022. The effects of reward misspecification: Mapping and mitigating misaligned models. arXiv preprint arXiv:2201.03544 (2022)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/0--387--29903--3"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220088"},{"key":"e_1_3_2_1_41_1","first-page":"9460","article-title":"Defining and characterizing reward gaming","volume":"35","author":"Skalse Joar","year":"2022","unstructured":"Joar Skalse, Nikolaus Howe, Dmitrii Krasheninnikov, and David Krueger. 2022. Defining and characterizing reward gaming. Advances in Neural Information Processing Systems 35 (2022), 9460--9471.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_42_1","volume-title":"1st Workshop on Recommender Systems for Television and Online Video at ACM RecSys","volume":"14","author":"Turrin Roberto","year":"2014","unstructured":"Roberto Turrin, Andrea Condorelli, Paolo Cremonesi, and Roberto Pagano. 2014. Time-based TV programs prediction. In 1st Workshop on Recommender Systems for Television and Online Video at ACM RecSys, Vol. 14."},{"key":"e_1_3_2_1_43_1","unstructured":"Southern District of New York United States District Court. 2022. Settlement on housing advertisements between Meta and HUD. https:\/\/www.justice.gov\/opa\/press-release\/file\/1514031\/download."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3534633"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271748"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2788615"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330681"},{"key":"e_1_3_2_1_48_1","volume-title":"Min Kyung Lee, and Sicun Gao","author":"Yu Eric Yang","year":"2022","unstructured":"Eric Yang Yu, Zhizhen Qin, Min Kyung Lee, and Sicun Gao. 2022. Policy Optimization with Advantage Regularization for Long-Term Fairness in Decision Systems. arXiv preprint arXiv:2210.12546 (2022)."},{"key":"e_1_3_2_1_49_1","unstructured":"A. Zarezade A. De U. Upadhyay H. Rabiee and M. Gomez-Rodriguez. 2018. Steering Social Activity: A Stochastic Optimal Control Point of View. Journal of Machine Learning Research (2018)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132938"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449889"},{"key":"e_1_3_2_1_52_1","volume-title":"Recommendation Fairness: From Static to Dynamic. arXiv preprint arXiv:2109.03150","author":"Zhang Dell","year":"2021","unstructured":"Dell Zhang and Jun Wang. 2021. Recommendation Fairness: From Static to Dynamic. arXiv preprint arXiv:2109.03150 (2021)."},{"key":"e_1_3_2_1_53_1","volume-title":"Control-based Bidding for Mobile Livestreaming Ads with Exposure Guarantee. In International Conference on Information and Knowledge Management (CIKM). 2539--2548","author":"Zhang Haoqi","year":"2022","unstructured":"Haoqi Zhang, Junqi Jin, Zhenzhe Zheng, Fan Wu, Haiyang Xu, and Jian Xu. 2022. Control-based Bidding for Mobile Livestreaming Ads with Exposure Guarantee. In International Conference on Information and Knowledge Management (CIKM). 2539--2548."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/2835776.2835843"}],"event":{"name":"WSDM '24: The 17th ACM International Conference on Web Search and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Merida Mexico","acronym":"WSDM '24"},"container-title":["Proceedings of the 17th ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3616855.3635819","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3616855.3635819","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:51:49Z","timestamp":1755823909000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3616855.3635819"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,4]]},"references-count":54,"alternative-id":["10.1145\/3616855.3635819","10.1145\/3616855"],"URL":"https:\/\/doi.org\/10.1145\/3616855.3635819","relation":{},"subject":[],"published":{"date-parts":[[2024,3,4]]},"assertion":[{"value":"2024-03-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}