{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T03:59:35Z","timestamp":1768363175491,"version":"3.49.0"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Science Foundation","award":["CCF-2332800"],"award-info":[{"award-number":["CCF-2332800"]}]},{"DOI":"10.13039\/100023530","name":"Army Contracting Command - Aberdeen Proving Ground","doi-asserted-by":"publisher","award":["W911NF-22-1-015"],"award-info":[{"award-number":["W911NF-22-1-015"]}],"id":[{"id":"10.13039\/100023530","id-type":"DOI","asserted-by":"publisher"}]},{"name":"U.S. Army Combat Capabilities Development Command","award":["W911NF2520046"],"award-info":[{"award-number":["W911NF2520046"]}]},{"DOI":"10.13039\/100000006","name":"U.S. Office of Naval Research","doi-asserted-by":"crossref","award":["N000142412615"],"award-info":[{"award-number":["N000142412615"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/ton.2025.3648382","type":"journal-article","created":{"date-parts":[[2025,12,25]],"date-time":"2025-12-25T18:25:27Z","timestamp":1766687127000},"page":"2416-2429","source":"Crossref","is-referenced-by-count":0,"title":["Distributed Learning for Multi-Stage Bandits: No-Regret Algorithm and Lower Bound"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1166-8773","authenticated-orcid":false,"given":"I-Hong","family":"Hou","sequence":"first","affiliation":[{"name":"Department of ECE, Texas A&M University, College Station, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3641512.3686369"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1137\/S0097539701398375"},{"key":"ref3","first-page":"1","article-title":"Minimax policies for adversarial and stochastic bandits","volume-title":"Proc. Conf. Learn. Theory","author":"Audibert"},{"key":"ref4","first-page":"2785","article-title":"Regret bounds and minimax policies under partial monitoring","volume":"11","author":"Audibert","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref5","first-page":"3168","article-title":"Explore no more: Improved high-probability regret bounds for non-stochastic bandits","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Neu"},{"key":"ref6","first-page":"375","article-title":"Algorithms for adversarial bandit problems with multiple plays","volume-title":"Proc. Int. Conf. Algorithmic Learn. Theory","author":"Taishi"},{"key":"ref7","first-page":"1263","article-title":"More adaptive algorithms for adversarial bandits","volume-title":"Proc. Conf. Learn. Theory","author":"Wei"},{"key":"ref8","first-page":"234","article-title":"Cooperative online learning: Keeping your neighbors updated","volume-title":"Proc. Algorithmic Learn. Theory","author":"Cesa-Bianchi"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3512798.3512817"},{"issue":"1","key":"ref10","first-page":"9529","article-title":"Multi-agent multi-armed bandits with limited communication","volume":"23","author":"Agarwal","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2020.109445"},{"key":"ref12","first-page":"7813","article-title":"One more step towards reality: Cooperative bandits with imperfect communication","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Madhushani"},{"key":"ref13","first-page":"4529","article-title":"Decentralized cooperative stochastic bandits","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Mart\u00ednez-Rubio"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2010.2062509"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11739"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/11871842_29"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/469"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2012.2186810"},{"key":"ref19","first-page":"22931","article-title":"Policy optimization in adversarial MDPs: Improved exploration via dilated bonuses","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Luo"},{"key":"ref20","first-page":"11437","article-title":"Follow-the-perturbed-leader for adversarial Markov decision processes with bandit feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dai"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230574"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IWQOS52092.2021.9521328"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-98358-1_20"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2021.3106937"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-021-09987-4"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2010.5757647"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.23919\/JCN.2021.000030"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/MASCOTS.2012.14"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2968562"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2014.2363136"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2019.2917393"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2021.3065703"},{"key":"ref33","first-page":"1","article-title":"Reinforcement learning for multi-hop scheduling and routing of real-time flows","volume-title":"Proc. 18th Int. Symp. Modeling Optim. Mobile, Ad Hoc, Wireless Netw. (WiOPT)","author":"HasanzadeZonuzy"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2010.111910.091238"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2010.100610"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1561\/2200000018"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1006\/inco.1996.2612"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1561\/2200000024"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3368567.3368568"}],"container-title":["IEEE Transactions on Networking"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/10723154\/11317935\/11316163-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10723154\/11317935\/11316163.pdf?arnumber=11316163","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T20:58:05Z","timestamp":1768337885000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11316163\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/ton.2025.3648382","relation":{},"ISSN":["2998-4157"],"issn-type":[{"value":"2998-4157","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}