{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:41:56Z","timestamp":1767339716377,"version":"3.28.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T00:00:00Z","timestamp":1656288000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T00:00:00Z","timestamp":1656288000000},"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":[[2022,6,27]]},"DOI":"10.1109\/icca54724.2022.9831850","type":"proceedings-article","created":{"date-parts":[[2022,7,25]],"date-time":"2022-07-25T16:18:44Z","timestamp":1658765924000},"page":"332-337","source":"Crossref","is-referenced-by-count":8,"title":["Safe RAN control: A Symbolic Reinforcement Learning Approach"],"prefix":"10.1109","author":[{"given":"Alexandros","family":"Nikou","sequence":"first","affiliation":[{"name":"Ericsson Research,Research Area Artificial Intelligence (AI)"}]},{"given":"Anusha","family":"Mujumdar","sequence":"additional","affiliation":[{"name":"Ericsson Research,Research Area Artificial Intelligence (AI)"}]},{"given":"Vaishnavi","family":"Sundararajan","sequence":"additional","affiliation":[{"name":"University of California"}]},{"given":"Marin","family":"Orlic","sequence":"additional","affiliation":[{"name":"Ericsson Research,Research Area Artificial Intelligence (AI)"}]},{"given":"Aneta Vulgarakis","family":"Feljan","sequence":"additional","affiliation":[{"name":"Ericsson Research,Research Area Artificial Intelligence (AI)"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196796"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-017-0468-y"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref13","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":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2020-Fall49728.2020.9348456"},{"article-title":"Remote electrical tilt optimization via safe reinforcement learning","year":"2020","author":"vannella","key":"ref15"},{"article-title":"Safe reinforcement learning for antenna tilt optimisation using shielding and multiple baselines","year":"2020","author":"feghhi","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12107"},{"article-title":"Principles of model checking","year":"2008","author":"baier","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2004.1428622"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2016.2605380"},{"article-title":"Wieless communications: Principle and practice","year":"2001","author":"rappaport","key":"ref27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1186\/1687-1499-2014-57"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/PIMRC.2010.5672065"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2019.2933420"},{"key":"ref8","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"},{"article-title":"Reinforcement learning: An introduction","year":"2018","author":"sutton","key":"ref7"},{"key":"ref2","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":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i06.6563"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2013.6554660"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2018.08.023"},{"key":"ref22","first-page":"2107","article-title":"Using reward machines for high-level task specification and decomposition in reinforcement learning","author":"icarte","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref21","article-title":"Robust and Decentralized Control of Multi-agent Systems under High-level Tasks","author":"nikou","year":"2019","journal-title":"Doctoral thesis"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCA54724.2022.9831850"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"ref26","first-page":"540","article-title":"Introduction to algorithms","author":"cormen","year":"2001"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44585-4_6"}],"event":{"name":"2022 IEEE 17th International Conference on Control & Automation (ICCA)","start":{"date-parts":[[2022,6,27]]},"location":"Naples, Italy","end":{"date-parts":[[2022,6,30]]}},"container-title":["2022 IEEE 17th International Conference on Control & Automation (ICCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9831427\/9831807\/09831850.pdf?arnumber=9831850","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T16:04:52Z","timestamp":1660579492000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9831850\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,27]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icca54724.2022.9831850","relation":{},"subject":[],"published":{"date-parts":[[2022,6,27]]}}}