{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T19:58:57Z","timestamp":1781294337120,"version":"3.54.1"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","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"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2023YFB3002201"],"award-info":[{"award-number":["2023YFB3002201"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Serv. Comput."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tsc.2026.3656552","type":"journal-article","created":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T21:10:12Z","timestamp":1769029812000},"page":"2161-2176","source":"Crossref","is-referenced-by-count":1,"title":["Heuristic-Guided Multi-Agent Reinforcement Learning for Computing Service Scheduling in Distributed Data Centers"],"prefix":"10.1109","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4449-4362","authenticated-orcid":false,"given":"Yu","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4752-0316","authenticated-orcid":false,"given":"Cheng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1917-9616","authenticated-orcid":false,"given":"Chungang","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoli","family":"Li","sequence":"additional","affiliation":[{"name":"School of Mathematics, Yangzhou University, Yangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0637-9317","authenticated-orcid":false,"given":"Changjun","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2024.3451170"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.23919\/JCC.2021.02.011"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.23919\/JCC.ja.2021-0776"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2024.3467212"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2025.3570862"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CloudCom55334.2022.00015"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17088"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3334519"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.110.2100124"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2017.2753229"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.2995881"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3025015"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2950621"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3281010"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2018.2879313"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2023.3330413"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/app11135849"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS61813.2024.10682932"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14435-6_7"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3412932"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3123165"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3326297"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3146976"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3407760"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2806777.2806780"},{"key":"ref26","first-page":"499","article-title":"Hawk: Hybrid datacenter scheduling","volume-title":"Proc. USENIX Conf. Usenix Annu. Techn. Conf.","author":"Delgado","year":"2015"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2016.12.032"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2020.2965106"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.26599\/TST.2019.9010044"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3134247"},{"key":"ref31","article-title":"Pareto policy adaptation","volume-title":"Proc. Int. Conf. Learn. Representations, Virtual","author":"Kyriakis","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/s44172-023-00127-7"},{"key":"ref33","first-page":"81748","article-title":"A structure-aware framework for learning device placements on computation graphs","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Duan","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3005745.3005750"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2019.2930575"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3147851"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2022.3213575"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3211622"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2021.3139607"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2024.3360448"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2024.3391318"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2024.3482390"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-9697-9_4"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICPSAsia61913.2024.10761284"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2022.3200109"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3486995"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.14778\/2733004.2733012"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/2741948.2741964"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2022.3157145"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref51","first-page":"55961","article-title":"Sample-efficient multiagent reinforcement learning with reset replay","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Yang","year":"2024"},{"key":"ref52","first-page":"19884","article-title":"Reinforcement learning with augmented data","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Laskin","year":"2020"},{"key":"ref53","first-page":"395","article-title":"Vicinal risk minimization","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Chapelle","year":"2000"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2025.3591010"},{"key":"ref55","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"99","author":"Ng","year":"1999"},{"key":"ref56","article-title":"Soft actor-critic for discrete action settings","author":"Christodoulou","year":"2019"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2021.3092715"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3212996"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3182335"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2024.3395699"}],"container-title":["IEEE Transactions on Services Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4629386\/11559165\/11359987.pdf?arnumber=11359987","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T19:42:56Z","timestamp":1781293376000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11359987\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":60,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tsc.2026.3656552","relation":{},"ISSN":["1939-1374","2372-0204"],"issn-type":[{"value":"1939-1374","type":"electronic"},{"value":"2372-0204","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}