{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T22:21:31Z","timestamp":1777501291031,"version":"3.51.4"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,8,28]],"date-time":"2024-08-28T00:00:00Z","timestamp":1724803200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,28]],"date-time":"2024-08-28T00:00:00Z","timestamp":1724803200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"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":[[2024,8,28]]},"DOI":"10.1109\/case59546.2024.10711622","type":"proceedings-article","created":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T17:40:16Z","timestamp":1729705216000},"page":"2780-2785","source":"Crossref","is-referenced-by-count":7,"title":["Large-Scale Data Center Cooling Control via Sample-Efficient Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Ni","family":"Mu","sequence":"first","affiliation":[{"name":"Tsinghua University,Center for Intelligent and Networked System (CFINS),Department of Automation,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Hu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Center for Intelligent and Networked System (CFINS),Department of Automation,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qing-Shan","family":"Jia","sequence":"additional","affiliation":[{"name":"Tsinghua University,Center for Intelligent and Networked System (CFINS),Department of Automation,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Zhu","sequence":"additional","affiliation":[{"name":"China Information Technology Designing & Consulting Institute,Beijing,China,100089"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"He","sequence":"additional","affiliation":[{"name":"China Information Technology Designing & Consulting Institute,Beijing,China,100089"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Data centres and data transmission networks","author":"Kamiya","year":"2020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/EI252483.2021.9713390"},{"key":"ref3","article-title":"Us data center energy usage report","author":"Shehabi","year":"2016","journal-title":"Tech. Rep"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CAC59555.2023.10450959"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref6","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref8","article-title":"E-mapp: Efficient multi-agent reinforcement learning with parallel program guidance","author":"Chang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","article-title":"Training language models to follow instructions with human feedback","author":"Ouyang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","article-title":"Multi-agent reinforcement learning with de-centralized distribution correction","author":"Li","year":"2024","journal-title":"IEEE Transactions on Automation Science and Engineering"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-023-3872-9"},{"key":"ref12","article-title":"Data center cooling using model-predictive control","volume":"31","author":"Lazic","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3360322.3360861"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2927410"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPS54341.2022.00021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2022.119392"},{"key":"ref17","volume-title":"6SigmaDCX package: 6SigmaRoom CFD Software, Future Facilities"},{"key":"ref18","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja"},{"key":"ref19","article-title":"Awac: Accelerating online reinforcement learning with offline datasets","author":"Nair","year":"2020"},{"key":"ref20","first-page":"1702","article-title":"Offline-to-online reinforcement learning via balanced replay and pessimistic q-ensemble","volume-title":"Conference on Robot Learning","author":"Lee"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_1"},{"key":"ref22","article-title":"Query-policy misalignment in preference-based reinforcement learning","author":"Hu","year":"2023"},{"key":"ref23","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"}],"event":{"name":"2024 IEEE 20th International Conference on Automation Science and Engineering (CASE)","location":"Bari, Italy","start":{"date-parts":[[2024,8,28]]},"end":{"date-parts":[[2024,9,1]]}},"container-title":["2024 IEEE 20th International Conference on Automation Science and Engineering (CASE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10711304\/10711288\/10711622.pdf?arnumber=10711622","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T01:47:50Z","timestamp":1732672070000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10711622\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,28]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/case59546.2024.10711622","relation":{},"subject":[],"published":{"date-parts":[[2024,8,28]]}}}