{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T20:37:45Z","timestamp":1781901465956,"version":"3.54.5"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3598712","type":"journal-article","created":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T17:35:26Z","timestamp":1755106526000},"page":"142493-142516","source":"Crossref","is-referenced-by-count":20,"title":["Hierarchical Reinforcement Learning for Energy-Efficient API Traffic Optimization in Large-Scale Advertising Systems"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8645-4736","authenticated-orcid":false,"given":"Enkai","family":"Ji","sequence":"first","affiliation":[{"name":"Department of Computer Science, Rutgers University, New Brunswick, NJ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1781-5233","authenticated-orcid":false,"given":"Yihan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Engineering and Applied Science, The University of Pennsylvania, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5213-4371","authenticated-orcid":false,"given":"Suchuan","family":"Xing","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianian","family":"Jin","sequence":"additional","affiliation":[{"name":"Fu Foundation School of Engineering and Applied Science, Columbia University, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2501040.2501980"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1561\/1500000049"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3109859.3109921"},{"key":"ref4","article-title":"Real-time bidding benchmarking with iPinYou dataset","author":"Zhang","year":"2014","journal-title":"arXiv:1407.7073"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219823"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2648584.2648589"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2532128"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3071594"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67425-4_12"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-4657-6_28"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2020.2995900"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2382553.2382556"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref15","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3005745.3005750"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICAC.2006.1662383"},{"key":"ref20","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05961-4"},{"key":"ref22","first-page":"3814","article-title":"Data center cooling using model-predictive control","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Lazic"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8485853"},{"key":"ref24","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref25","volume-title":"Microservices Patterns: With Examples in Java","author":"Richardson","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MS.2018.2141039"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1155\/2014\/920829"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/MCC.2017.22"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s10723-017-9419-x"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2904543"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3390\/electronics14071431"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3373316"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342080"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3152434.3152441"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CLOUD.2019.00061"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CSNT60213.2024.10545922"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3453160"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref39","article-title":"Data-efficient hierarchical reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Nachum"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref41","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lowe"},{"issue":"178","key":"ref42","first-page":"1","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-30671-1_89"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/2020408.2020604"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330870"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330782"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3132747.3132772"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387524"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230545"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1364\/JOCN.7.00A379"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.14778\/3342263.3342644"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"issue":"167","key":"ref53","first-page":"1","article-title":"Risk-constrained reinforcement learning with percentile risk criteria","volume":"18","author":"Chow","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref54","article-title":"Parameter space noise for exploration","author":"Plappert","year":"2017","journal-title":"arXiv:1706.01905"},{"key":"ref55","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020","journal-title":"arXiv:2005.01643"},{"key":"ref56","article-title":"Prioritized experience replay","author":"Schaul","year":"2015","journal-title":"arXiv:1511.05952"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-018-2345-2"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8486300"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/2835776.2835843"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/2872427.2883071"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11123801.pdf?arnumber=11123801","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,20]],"date-time":"2025-08-20T18:43:36Z","timestamp":1755715416000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11123801\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3598712","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}