{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T05:38:40Z","timestamp":1772084320581,"version":"3.50.1"},"reference-count":16,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,13]],"date-time":"2021-09-13T00:00:00Z","timestamp":1631491200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,13]],"date-time":"2021-09-13T00:00:00Z","timestamp":1631491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,13]],"date-time":"2021-09-13T00:00:00Z","timestamp":1631491200000},"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":[],"published-print":{"date-parts":[[2021,9,13]]},"DOI":"10.1109\/pimrc50174.2021.9569387","type":"proceedings-article","created":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T15:05:59Z","timestamp":1639494359000},"page":"1148-1153","source":"Crossref","is-referenced-by-count":10,"title":["A Safe Reinforcement Learning Architecture for Antenna Tilt Optimisation"],"prefix":"10.1109","author":[{"given":"Erik","family":"Aumayr","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Saman","family":"Feghhi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Filippo","family":"Vannella","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ezeddin Al","family":"Hakim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Grigorios","family":"Iakovidis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Learning human objectives by evaluating hypothetical behavior","author":"reddy","year":"2019"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11797","article-title":"Safe reinforcement learning via shielding","author":"alshiekh","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref12","article-title":"Antenna tilt optimization using Reinforcement Learning with doubly-safe exploration","author":"vairamuthu","year":"2020","journal-title":"Master’s thesis"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC49053.2021.9417363"},{"key":"ref14","article-title":"Towards physically safe reinforcement learning under supervision","author":"zhang","year":"2019"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref16","article-title":"Off-policy Learning for Remote Electrical Tilt Optimization","author":"vannella","year":"2020","journal-title":"IEEE Vehicular Technology Conference (VTC Fall)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1186\/1687-1499-2014-57"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1002\/bltj.20463","article-title":"A fuzzy reinforcement learning approach for self-optimization of coverage in lte networks","volume":"15","author":"razavi","year":"2010","journal-title":"Bell Labs Technical Journal"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2019.2933420"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2013.6554660"},{"key":"ref8","first-page":"2298","article-title":"Safe policy improvement by minimizing robust baseline regret","author":"ghavamzadeh","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref7","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"garc?a","year":"2015","journal-title":"Journal of Machine Learning Research"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref1","article-title":"Self-tuning of remote electrical tilts based on call traces for coverage and capacity optimization in LTE","author":"buenestado","year":"2017","journal-title":"IEEE Transactions on Vehicular Technology"},{"key":"ref9","article-title":"Help an agent out: Student\/teacher learning in sequential decision tasks","author":"torrey","year":"2012","journal-title":"Proceedings of the Adaptive and Learning Agents workshop (at AAMAS-12)"}],"event":{"name":"2021 IEEE 32nd Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)","location":"Helsinki, Finland","start":{"date-parts":[[2021,9,13]]},"end":{"date-parts":[[2021,9,16]]}},"container-title":["2021 IEEE 32nd Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9569244\/9569245\/09569387.pdf?arnumber=9569387","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,18]],"date-time":"2023-01-18T08:04:33Z","timestamp":1674029073000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9569387\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,13]]},"references-count":16,"URL":"https:\/\/doi.org\/10.1109\/pimrc50174.2021.9569387","relation":{},"subject":[],"published":{"date-parts":[[2021,9,13]]}}}