{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T07:06:11Z","timestamp":1784099171650,"version":"3.55.0"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,24]],"date-time":"2026-05-24T00:00:00Z","timestamp":1779580800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,24]],"date-time":"2026-05-24T00:00:00Z","timestamp":1779580800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,24]]},"DOI":"10.1109\/icc59461.2026.11586928","type":"proceedings-article","created":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T19:38:09Z","timestamp":1784057889000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Heterogeneous Multi-Agent Reinforcement Learning for Energy-Aware Resource Scheduling in Cloud Environments"],"prefix":"10.1109","author":[{"given":"Ying","family":"He","sequence":"first","affiliation":[{"name":"Shenzhen University,School of Computer Science and Software Engineering,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinxin","family":"Zhu","sequence":"additional","affiliation":[{"name":"Shenzhen University,School of Computer Science and Software Engineering,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peijie","family":"Xian","sequence":"additional","affiliation":[{"name":"Shenzhen University,School of Computer Science and Software Engineering,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei Richard","family":"Yu","sequence":"additional","affiliation":[{"name":"Carleton University,School of Information Technology,Ottawa,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangzheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of California,San Diego,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianbo","family":"Du","sequence":"additional","affiliation":[{"name":"Xi’an University of Posts & Telecommunications,Shananxi Key Laboratory of Information Communication Network and Security,Xi’an,China,710121"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.12720\/jait.14.5.1063-1072"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-1549-1_32"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/NOMS47738.2020.9110428"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3542929.3563469"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACSOS-C52956.2021.00025"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.6061"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1787"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-09996-w"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-024-09644-x"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.14386"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref14","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume":"29","author":"Foerster","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref16","article-title":"Soft actor-critic algorithms and applications","author":"Haamoja","year":"2018"},{"key":"ref17","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"International Conference on Machine Learning","author":"Silver"},{"key":"ref18","article-title":"Is independent learning all you need in the starcraft multi-agent challenge?","author":"De Witt","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2901791"}],"event":{"name":"ICC 2026 - IEEE International Conference on Communications","location":"Glasgow, United Kingdom","start":{"date-parts":[[2026,5,24]]},"end":{"date-parts":[[2026,5,28]]}},"container-title":["ICC 2026 - IEEE International Conference on Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11586754\/11586037\/11586928.pdf?arnumber=11586928","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T06:11:09Z","timestamp":1784095869000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11586928\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,24]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icc59461.2026.11586928","relation":{},"subject":[],"published":{"date-parts":[[2026,5,24]]}}}