{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T05:49:49Z","timestamp":1776145789943,"version":"3.50.1"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tpds.2026.3674891","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T19:40:55Z","timestamp":1773862855000},"page":"1186-1204","source":"Crossref","is-referenced-by-count":0,"title":["Scalable and Efficient Reinforcement Learning for Virtual Machine Rescheduling in Cloud Data Centers"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6114-2801","authenticated-orcid":false,"given":"Xianzhong","family":"Ding","sequence":"first","affiliation":[{"name":"Lawrence Berkeley National Laboratory, Berkeley, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7203-2883","authenticated-orcid":false,"given":"Yunkai","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, Berkeley, CA, USA"}]},{"given":"Binbin","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7329-5917","authenticated-orcid":false,"given":"Donghao","family":"Ying","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, Berkeley, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2250-5528","authenticated-orcid":false,"given":"Tieying","family":"Zhang","sequence":"additional","affiliation":[{"name":"ByteDance, San Jose, CA, USA"}]},{"given":"Jianjun","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance, San Jose, CA, USA"}]},{"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"ByteDance, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4531-9704","authenticated-orcid":false,"given":"Alberto","family":"Cerpa","sequence":"additional","affiliation":[{"name":"University of California, Merced, Merced, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2057-2885","authenticated-orcid":false,"given":"Wan","family":"Du","sequence":"additional","affiliation":[{"name":"University of California, Merced, Merced, CA, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3717476"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3492321.3519589"},{"key":"ref3","first-page":"273","article-title":"Live migration of virtual machines","volume-title":"Proc. 2nd Conf. Symp. Netw. Syst. Des. Implementation","author":"Clark","year":"2005"},{"key":"ref4","first-page":"845","article-title":"Protean: VM allocation service at scale","volume-title":"Proc. 14th USENIX Conf. Operating Syst. Des. Implementation","author":"Hadary","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2018.07.001"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-019-02954-w"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-55792-2_10"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.1070.0254"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/DSAA54385.2022.10032386"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2014.2343945"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1131322.1131328"},{"key":"ref12","first-page":"11091","article-title":"Analysis of CI\/CD application in kubernetes architecture","volume":"71","year":"2023","journal-title":"Math. Statistician Eng. Appl."},{"key":"ref13","article-title":"Cluster design in data center","year":"2025"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3477132.3483588"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472902"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1137\/1033004"},{"key":"ref17","article-title":"Heuristics for vector bin packing","author":"Panigrahy","year":"2011"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2021.105400"},{"key":"ref19","first-page":"2024-","article-title":"Numa architecture platforms"},{"key":"ref20","article-title":"Cplex optimizer","year":"2025"},{"key":"ref21","article-title":"Gurobi solver","year":"2025"},{"key":"ref22","article-title":"Kubernetes scheduler","year":"2025"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45586-8_5"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342221"},{"key":"ref25","article-title":"Chip placement with deep reinforcement learning","author":"Mirhoseini","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref27","first-page":"1","article-title":"Sample efficient deep reinforcement learning via uncertainty estimation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mai","year":"2022"},{"key":"ref28","article-title":"OpenAI Gym","author":"Brockman","year":"2016"},{"key":"ref29","article-title":"Reinforcement learning with sparse rewards using guidance from offline demonstration","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Rengarajan","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref32","article-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"issue":"140","key":"ref34","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref36","article-title":"Attend2pack: Bin packing through deep reinforcement learning with attention","author":"Zhang","year":"2021"},{"key":"ref37","article-title":"Solving packing problems by conditional query learning","author":"Li","year":"2020"},{"key":"ref38","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref39","volume-title":"Pattern Recognition and Machine Learning (Information Science and Statistics","author":"Bishop","year":"2007"},{"key":"ref40","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016"},{"key":"ref41","first-page":"4045","article-title":"Time limits in reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pardo","year":"2018"},{"key":"ref42","first-page":"1","article-title":"Layer-wise coordination between encoder and decoder for neural machine translation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"He","year":"2018"},{"key":"ref43","first-page":"1","article-title":"Deep symbolic regression: Recovering mathematical expressions from data via risk-seeking policy gradients","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Petersen","year":"2021"},{"key":"ref44","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref45","first-page":"1","article-title":"Neural architecture search with reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zoph","year":"2017"},{"key":"ref46","first-page":"1","article-title":"EPOpt: Learning robust neural network policies using model ensembles","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Rajeswaran","year":"2017"},{"key":"ref47","article-title":"High-dimensional continuous control using generalized advantage estimation","volume-title":"Proc. Int. Conf. Learn. Representations (ICLR)","author":"Schulman","year":"2016"},{"issue":"274","key":"ref48","first-page":"1","article-title":"CleanRL: High-quality single-file implementations of deep reinforcement learning algorithms","volume":"23","author":"Huang","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref49","article-title":"PyTorch: An open source machine learning framework","year":"2019"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3481933"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342080"},{"issue":"7","key":"ref52","first-page":"579","article-title":"Multilayer perceptron and neural networks","volume":"8","author":"Popescu","year":"2009","journal-title":"WSEAS Trans. Circuits Syst."},{"key":"ref53","first-page":"4344","article-title":"Learning by playing solving sparse reward tasks from scratch","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Riedmiller","year":"2018"},{"key":"ref54","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2015.02.002"},{"key":"ref56","first-page":"1","article-title":"Reinforcement learning driven heuristic optimization","volume-title":"Proc. Workshop Deep Reinforcement Learn. Knowl. Discov.","author":"Cai","year":"2019"},{"key":"ref57","first-page":"5235","article-title":"Solving a new 3D bin packing problem with deep reinforcement learning method","volume-title":"Proc. IEEE Int. Conf. Robot. Autom. (ICRA)","author":"Hu","year":"2017"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2016.2615933"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/2741948.2741964"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/S0377-2217(98)00139-8"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16155"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref63","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.32473\/flairs.v35i.130584"},{"key":"ref65","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Achiam","year":"2017"},{"key":"ref66","first-page":"70","article-title":"Autophase: Juggling HLS phase orderings in random forests with deep reinforcement learning","volume-title":"Proc. Mach. Learn. Syst.","volume":"2","author":"Haj-Ali","year":"2020"},{"key":"ref67","first-page":"9367","article-title":"Reinforcement learning for integer programming: Learning to cut","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tang","year":"2020"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1345"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5723"},{"key":"ref70","article-title":"Smart feasibility pump: Reinforcement learning for (mixed) integer programming","author":"Qi","year":"2021"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108254"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/71\/11434582\/11440117.pdf?arnumber=11440117","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T05:04:06Z","timestamp":1776143046000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11440117\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":71,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2026.3674891","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}