{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T03:12:57Z","timestamp":1780369977722,"version":"3.54.1"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF Grants: NSF AI Institute for Future Edge Networks and Distributed Intelligence","award":["2112471"],"award-info":[{"award-number":["2112471"]}]},{"name":"NSF Grants: NSF AI Institute for Future Edge Networks and Distributed Intelligence","award":["CNS-NeTS-2106679"],"award-info":[{"award-number":["CNS-NeTS-2106679"]}]},{"name":"NSF Grants: NSF AI Institute for Future Edge Networks and Distributed Intelligence","award":["CNS-NeTS-2007231"],"award-info":[{"award-number":["CNS-NeTS-2007231"]}]},{"DOI":"10.13039\/100000006","name":"the Office of Naval Research","doi-asserted-by":"crossref","award":["N00014-19-1-2621"],"award-info":[{"award-number":["N00014-19-1-2621"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000183","name":"the Army Research Office","doi-asserted-by":"crossref","award":["W911NF-24-1-0103"],"award-info":[{"award-number":["W911NF-24-1-0103"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/ton.2025.3553858","type":"journal-article","created":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T13:53:32Z","timestamp":1744206812000},"page":"1976-1988","source":"Crossref","is-referenced-by-count":1,"title":["State-Independent Control for Constrained Markov Decision Processes With Birth-Death Dynamics"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5663-4411","authenticated-orcid":false,"given":"Yilin","family":"Zheng","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, The Ohio State University, Columbus, OH, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5560-5806","authenticated-orcid":false,"given":"Atilla","family":"Eryilmaz","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, The Ohio State University, Columbus, OH, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3164539"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v26i1.8279"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/862"},{"key":"ref4","article-title":"On the long-term impact of algorithmic decision policies: Effort unfairness and feature segregation through social learning","author":"Heidari","year":"2019","journal-title":"arXiv:1903.01209"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref6","first-page":"1617","article-title":"Fairness in reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jabbari"},{"key":"ref7","first-page":"1144","article-title":"Algorithms for fairness in sequential decision making","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Wen"},{"key":"ref8","volume-title":"Further Topics on Discrete-time Markov Control Processes","volume":"42","author":"Hern\u00e1ndez-Lerma","year":"2012"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmaa.2016.05.055"},{"key":"ref10","first-page":"8378","article-title":"Natural policy gradient primal-dual method for constrained Markov decision processes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ding"},{"key":"ref11","article-title":"Sample-efficient constrained reinforcement learning with general parameterization","author":"Uddin Mondal","year":"2024","journal-title":"arXiv:2405.10624"},{"key":"ref12","first-page":"1563","article-title":"Near-optimal regret bounds for reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"11","author":"Jaksch"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2591971.2591983"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2016.2562564"},{"key":"ref15","first-page":"263","article-title":"Minimax regret bounds for reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Azar"},{"key":"ref16","first-page":"1","article-title":"Reinforcement learning in a birth and death process: Breaking the dependence on the state space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Anselmi"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5986"},{"key":"ref18","first-page":"8938","article-title":"Regret, stability & fairness in matching markets with bandit learners","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Cen"},{"key":"ref19","first-page":"325","article-title":"Fairness in learning: Classic and contextual bandits","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Joseph"},{"key":"ref20","first-page":"8376","article-title":"On preserving non-discrimination when combining expert advice","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Blum"},{"key":"ref21","first-page":"13750","article-title":"Group-fair online allocation in continuous time","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"\u00c7ayci"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1980.tb01111.x"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1214\/aoap\/1177005207"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1214\/aoap\/1177005588"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.2307\/3214163"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.2307\/3214547"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2010.2068950"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2018.8437712"},{"key":"ref29","first-page":"11878","article-title":"Restless-UCB, an efficient and low-complexity algorithm for online restless bandits","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s00186-020-00731-9"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26207"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26672"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287578"},{"key":"ref34","article-title":"Reinforcement learning for joint optimization of multiple rewards","author":"Agarwal","year":"2019","journal-title":"arXiv:1909.02940"},{"key":"ref35","first-page":"4860","article-title":"Learning adversarial Markov decision processes with bandit feedback and unknown transition","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"1","author":"Jin"},{"key":"ref36","first-page":"15277","article-title":"Upper confidence primal-dual reinforcement learning for CMDP with adversarial loss","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Qiu"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3179415"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/0025-5564(75)90122-4"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1002\/wics.1423"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1287\/opre.29.5.971"},{"key":"ref41","first-page":"1","article-title":"A general birth-death-sampling model for epidemiology and macroevolution","volume":"2020","author":"MacPherson","year":"2020","journal-title":"BioRxiv"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.peva.2021.102245"},{"key":"ref43","article-title":"Dynamic programming for structured continuous Markov decision problems","author":"Feng","year":"2012","journal-title":"arXiv:1207.4115"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/SCT.1994.315792"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6377(02)00231-6"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1561\/2200000050"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1090\/mbk\/107"},{"key":"ref48","first-page":"29048","article-title":"Finite-time analysis of whittle index based Q-learning for restless multi-armed bandits with neural network function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xiong"}],"container-title":["IEEE Transactions on Networking"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/10723154\/11131549\/10959102-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10723154\/11131549\/10959102.pdf?arnumber=10959102","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:52:05Z","timestamp":1755910325000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10959102\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":48,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/ton.2025.3553858","relation":{},"ISSN":["2998-4157"],"issn-type":[{"value":"2998-4157","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}