{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T12:58:05Z","timestamp":1778158685365,"version":"3.51.4"},"reference-count":96,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100006041","name":"Innovate UK\/CELTIC-NEXT European collaborative project on AI-enabled Massive MIMO","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006041","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Next-Generation Converged Digital Infrastructure (NG-CDI) Project"},{"DOI":"10.13039\/501100000266","name":"BT and Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/R004935\/1"],"award-info":[{"award-number":["EP\/R004935\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3217511","type":"journal-article","created":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:22:33Z","timestamp":1667517753000},"page":"113808-113826","source":"Crossref","is-referenced-by-count":44,"title":["RLOps: Development Life-Cycle of Reinforcement Learning Aided Open RAN"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1516-1993","authenticated-orcid":false,"given":"Peizheng","family":"Li","sequence":"first","affiliation":[{"name":"Department of Electrical and Electronic Engineering, University of Bristol, Bristol, U.K"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5837-9496","authenticated-orcid":false,"given":"Jonathan","family":"Thomas","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, University of Bristol, Bristol, U.K"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9332-2700","authenticated-orcid":false,"given":"Xiaoyang","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, University of Bristol, Bristol, U.K"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1333-7385","authenticated-orcid":false,"given":"Ahmed","family":"Khalil","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, University of Bristol, Bristol, U.K"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6980-5267","authenticated-orcid":false,"given":"Abdelrahim","family":"Ahmad","sequence":"additional","affiliation":[{"name":"Vilicom U.K. Ltd., Reading, U.K"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5786-6679","authenticated-orcid":false,"given":"Rui","family":"Inacio","sequence":"additional","affiliation":[{"name":"Vilicom U.K. Ltd., Reading, U.K"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5884-1705","authenticated-orcid":false,"given":"Shipra","family":"Kapoor","sequence":"additional","affiliation":[{"name":"Applied Research, Suffolk, U.K"}]},{"given":"Arjun","family":"Parekh","sequence":"additional","affiliation":[{"name":"Applied Research, Suffolk, U.K"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0133-6676","authenticated-orcid":false,"given":"Angela","family":"Doufexi","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, University of Bristol, Bristol, U.K"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0826-1996","authenticated-orcid":false,"given":"Arman","family":"Shojaeifard","sequence":"additional","affiliation":[{"name":"InterDigital Communications Inc., Wilmington, DE, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4879-1206","authenticated-orcid":false,"given":"Robert J.","family":"Piechocki","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, University of Bristol, Bristol, U.K"}]}],"member":"263","reference":[{"key":"ref73","article-title":"How to make deep RL work in practice","author":"rao","year":"2020","journal-title":"arXiv 2010 13083"},{"key":"ref72","first-page":"1","article-title":"Stochastic neural networks for hierarchical reinforcement learning","author":"florensa","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.39.10.1953"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3020400"},{"key":"ref76","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref77","first-page":"25","article-title":"Learning curriculum policies for reinforcement learning","author":"narvekar","year":"2019","journal-title":"Proc 18th Int Conf Auto Agents Multiagent Syst"},{"key":"ref74","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC.2018.8445920"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2019.2909893"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/APCCAS47518.2019.8953134"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45855.2022.9838763"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/SECON52354.2021.9491579"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3390\/s22145375"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2021.108682"},{"key":"ref37","article-title":"The next decade of telecommunications artificial intelligence","author":"ouyang","year":"2021","journal-title":"arXiv 2101 09163"},{"key":"ref36","article-title":"Federated deep reinforcement learning for resource allocation in O-RAN slicing","author":"zhang","year":"2022","journal-title":"arXiv 2208 01736"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC51071.2022.9771908"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3166160"},{"key":"ref60","volume":"7","author":"altman","year":"1999","journal-title":"Constrained Markov Decision Processes"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1186\/s42400-019-0027-x"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67383-7_2"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.5220\/0006197105590566"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3390\/s22135029"},{"key":"ref64","article-title":"Robust deep reinforcement learning with adversarial attacks","author":"pattanaik","year":"2017","journal-title":"arXiv 1712 03632"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IWCMC51323.2021.9498852"},{"key":"ref65","article-title":"OpenAI gym","author":"brockman","year":"2016","journal-title":"arXiv 1606 01540 [cs]"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05961-4"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA52953.2021.00154"},{"key":"ref67","first-page":"1","article-title":"Machine learning: The high interest credit card of technical debt","author":"sculley","year":"2014","journal-title":"Proc SEML Softw Eng Mach Learn (NIPS Workshop)"},{"key":"ref68","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"levine","year":"2020","journal-title":"arXiv 2005 01643"},{"key":"ref2","author":"li","year":"2020","journal-title":"O-RAN use cases and deployment scenarios Towards open and smart RAN"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2017.8258038"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2020.107516"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03819-2"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3188217"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2011.5741148"},{"key":"ref24","article-title":"Communication and computation O-RAN resource slicing for URLLC services using deep reinforcement learning","author":"filali","year":"2022","journal-title":"arXiv 2202 06439"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.101.2001120"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3188013"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICC42927.2021.9500721"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2998358"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2000343"},{"key":"ref95","author":"chang","year":"2019","journal-title":"NIST Big Data Interoperability Framework Volume 1 Definitions"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2946162"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"ref92","first-page":"361","article-title":"Measuring sample efficiency and generalization in reinforcement learning benchmarks: Neurips 2020 procgen benchmark","volume":"133","author":"mohanty","year":"2021","journal-title":"Proc NIPS"},{"key":"ref91","first-page":"1407","article-title":"IMPALA: Scalable distributed deep-RL with importance weighted actor-learner architectures","author":"espeholt","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref90","first-page":"1","article-title":"Distributed prioritized experience replay","author":"horgan","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/BIGCOMP.2017.7881733"},{"key":"ref59","article-title":"Deep reinforcement learning for radio resource allocation and management in next generation heterogeneous wireless networks: A survey","author":"alwarafy","year":"2021","journal-title":"arXiv 2106 00574"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/2996890.3007869"},{"key":"ref57","article-title":"Learning under concept drift: A review","author":"lu","year":"2020","journal-title":"arXiv 2004 05785"},{"key":"ref56","article-title":"Horizon: Facebook’s open source applied reinforcement learning platform","author":"gauci","year":"2018","journal-title":"arXiv 1811 00260"},{"key":"ref55","article-title":"Deep reinforcement learning: An overview","author":"li","year":"2017","journal-title":"arXiv 1701 07274"},{"key":"ref54","first-page":"4134","article-title":"Bayesian optimization with robust Bayesian neural networks","volume":"29","author":"springenberg","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3013848"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140919"},{"key":"ref11","author":"bishop","year":"2006","journal-title":"Pattern Recognition and Machine Learning"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2019.2934851"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref13","year":"2021","journal-title":"Ran Vs Cloud RAN Vs Vran Vs O-RAN A Simple Guide!"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/app12010408"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2807385"},{"key":"ref82","year":"2022","journal-title":"Mlops Continuous delivery and automation pipelines in machine learning"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2979670"},{"key":"ref81","first-page":"943","article-title":"A Bayesian framework for reinforcement learning","author":"strens","year":"2000","journal-title":"Proc ICML"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2019.105657"},{"key":"ref84","article-title":"Concrete problems in AI safety","author":"amodei","year":"2016","journal-title":"arXiv 1606 06565"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref83","article-title":"Dealing with non-stationarity in multi-agent deep reinforcement learning","author":"papoudakis","year":"2019","journal-title":"arXiv 1906 04737"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3340404"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1561\/2200000049"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1016\/j.promfg.2018.10.167"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ISSNIP.2007.4496871"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2019.2898944"},{"key":"ref6","article-title":"A data quality-driven view of MLOps","author":"renggli","year":"2021","journal-title":"arXiv 2102 07750"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2876279"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-57321-8_5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6633\/aab406"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16937"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MS.2016.68"},{"key":"ref49","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1007\/978-3-030-57321-8_5","article-title":"Explainable reinforcement learning: A survey","author":"puiutta","year":"2020","journal-title":"Proc Int Cross-Domain Conf Mach Learn Knowl Extraction"},{"key":"ref87","article-title":"Robust constrained-MDPs: Soft-constrained robust policy optimization under model uncertainty","author":"russel","year":"2020","journal-title":"arXiv 2010 04870"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2930000"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref46","first-page":"4962","article-title":"Evaluating the performance of reinforcement learning algorithms","author":"jordan","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3459991"},{"key":"ref48","article-title":"Model-based reinforcement learning: A survey","author":"moerland","year":"2020","journal-title":"arXiv 2006 16712"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/WCSP.2018.8555891"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2020.3001121"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1002\/ett.3627"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2022.07.019"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09931127.pdf?arnumber=9931127","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,28]],"date-time":"2022-11-28T20:05:44Z","timestamp":1669665944000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9931127\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":96,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3217511","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}