{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:21:37Z","timestamp":1740133297361,"version":"3.37.3"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000196","name":"Canada Foundation for Innovation","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100000196","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100007711","name":"British Columbia Knowledge Development Fund (BCKDF) of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007711","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Networking"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tnet.2024.3444593","type":"journal-article","created":{"date-parts":[[2024,8,26]],"date-time":"2024-08-26T17:40:44Z","timestamp":1724694044000},"page":"4855-4870","source":"Crossref","is-referenced-by-count":0,"title":["Game-Theoretic Bandits for Network Optimization With High-Probability Swap-Regret Upper Bounds"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6465-591X","authenticated-orcid":false,"given":"Zhiming","family":"Huang","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Victoria, Victoria, BC, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4893-6847","authenticated-orcid":false,"given":"Jianping","family":"Pan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Victoria, Victoria, BC, Canada"}]}],"member":"263","reference":[{"key":"ref1","first-page":"911","article-title":"A near-optimal high-probability swap-regret upper bound for multi-agent bandits in unknown general-sum games","volume-title":"Proc. Conf. Uncertainty Artif. Intell. (UAI)","volume":"216","author":"Huang"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS57875.2023.00060"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jebo.2016.04.006"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/0304-4068(74)90037-8"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546921"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1017\/9781108571401"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1111\/1468-0262.00153"},{"issue":"47","key":"ref8","first-page":"1307","article-title":"From external to internal regret","volume":"8","author":"Blum","year":"2007","journal-title":"J. Mach. Learn. Res."},{"article-title":"Incomplete information and internal regret in prediction of individual sequences","year":"2005","author":"Stoltz","key":"ref9"},{"key":"ref10","first-page":"18550","article-title":"A tight lower bound and efficient reduction for swap regret","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"33","author":"Ito"},{"article-title":"V-learning\u2014A simple, efficient, decentralized algorithm for multiagent RL","volume-title":"Proc. ICLR Workshop Gamification Multiagent Solutions","author":"Jin","key":"ref11"},{"key":"ref12","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. (JMLR)"},{"key":"ref13","first-page":"613","article-title":"Efficient learning by implicit exploration in bandit problems with side observations","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Koc\u00e1k"},{"key":"ref14","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. (NeurIPS)","volume":"28","author":"Neu"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2015.7218651"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/24"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2018.2852361"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3466772.3467045"},{"key":"ref19","first-page":"961","article-title":"Non-stochastic multi-player multi-armed bandits: Optimal rate with collision information, sublinear without","volume-title":"Proc. 33rd Conf. Learn. Theory","volume":"125","author":"Bubeck"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2010.2062509"},{"key":"ref21","first-page":"854","article-title":"Distributed exploration in multi-armed bandits","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"26","author":"Hillel"},{"key":"ref22","first-page":"19","article-title":"Gossip-based distributed stochastic bandit algorithms","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Szorenyi"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CISS.2014.6814096"},{"key":"ref24","first-page":"2730","article-title":"Cooperative Multi-agent Bandits with Heavy Tails","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Dubey"},{"article-title":"Some notes on computation of games solutions","year":"1949","author":"Brown","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.2307\/1969530"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2014.0687"},{"key":"ref28","first-page":"6372","article-title":"Learning with bandit feedback in potential games","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Cohen"},{"key":"ref29","first-page":"925","article-title":"Follow-the-regularized-leader routes to chaos in routing games","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"139","author":"Bielawski"},{"key":"ref30","first-page":"7688","article-title":"Learning in nonzero-sum stochastic games with potentials","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"139","author":"Mguni"},{"key":"ref31","first-page":"7736","article-title":"Signatured deep fictitious play for mean field games with common noise","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"139","author":"Min"},{"key":"ref32","first-page":"10772","article-title":"Global convergence of policy gradient for linear-quadratic mean-field control\/game in continuous time","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"139","author":"Wang"},{"key":"ref33","first-page":"11436","article-title":"Learning while playing in mean-field games: Convergence and optimality","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"139","author":"Xie"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1137\/140980685"},{"key":"ref36","first-page":"5872","article-title":"Multiplicative weights update with constant step-size in congestion games: Convergence, limit cycles and chaos","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"30","author":"Palaiopanos"},{"key":"ref37","first-page":"18990","article-title":"Hedging in games: Faster convergence of external and swap regrets","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"33","author":"Chen"},{"key":"ref38","first-page":"27604","article-title":"Near-optimal no-regret learning in general games","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"34","author":"Daskalakis"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3519935.3520031"},{"key":"ref40","first-page":"39076","article-title":"Near-optimal no-regret learning dynamics for general convex games","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"35","author":"Farina"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1137\/S0097539701398375"},{"key":"ref42","first-page":"2197","article-title":"Fighting bandits with a new kind of smoothness","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"28","author":"Abernethy"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1287\/opre.35.2.282"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3055399.3055463"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2005.1424480"},{"key":"ref46","first-page":"343","article-title":"PCC Vivace: Online-learning congestion control","volume-title":"Proc. 15th USENIX Symp. Networked Syst. Design Implement.","author":"Don"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3232755.3232770"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/1868447.1868466"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/1400097.1400105"},{"key":"ref50","first-page":"78","volume-title":"BBR Congestion Control","author":"Cardwell","year":"2024"},{"key":"ref51","first-page":"731","article-title":"Pantheon: The training ground for internet congestion-control research","volume-title":"Proc. USENIX Annu. Tech. Conf. (ATC)","author":"Yan"},{"volume-title":"Common TCP Evaluation Suite","year":"2014","author":"Hayes","key":"ref52"},{"key":"ref53","first-page":"459","article-title":"Stochastic forecasts achieve high throughput and low delay over cellular networks","volume-title":"Proc. 10th USENIX Conf. Networked Syst. Design Implement. (NSDI)","author":"Winstein"}],"container-title":["IEEE\/ACM Transactions on Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/90\/10807683\/10645817.pdf?arnumber=10645817","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T06:47:32Z","timestamp":1734677252000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10645817\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":53,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tnet.2024.3444593","relation":{},"ISSN":["1063-6692","1558-2566"],"issn-type":[{"type":"print","value":"1063-6692"},{"type":"electronic","value":"1558-2566"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}