{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T10:49:31Z","timestamp":1761130171475,"version":"3.28.0"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,23]],"date-time":"2024-05-23T00:00:00Z","timestamp":1716422400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,23]],"date-time":"2024-05-23T00:00:00Z","timestamp":1716422400000},"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":[[2024,5,23]]},"DOI":"10.1109\/saci60582.2024.10619866","type":"proceedings-article","created":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T17:24:26Z","timestamp":1723483466000},"page":"000565-000572","source":"Crossref","is-referenced-by-count":3,"title":["Review of Reinforcement Learning-Based Control Algorithms in Artificial Pancreas Systems for Diabetes Mellitus Management"],"prefix":"10.1109","author":[{"given":"Lehel","family":"D\u00e9nes-Fazakas","sequence":"first","affiliation":[{"name":"University Research and Innovation Center, Physiological Controls Research Center Óbuda University,Budapest,Hungary"}]},{"given":"Gy\u0151z\u0151 D\u00e9nes","family":"Fazakas","sequence":"additional","affiliation":[]},{"given":"Gy\u00f6rgy","family":"Eigner","sequence":"additional","affiliation":[{"name":"University Research and Innovation Center, Physiological Controls Research Center Óbuda University,Budapest,Hungary"}]},{"given":"Levente","family":"Kov\u00e1cs","sequence":"additional","affiliation":[{"name":"University Research and Innovation Center, Physiological Controls Research Center Óbuda University,Budapest,Hungary"}]},{"given":"L\u00e1szl\u00f3","family":"Szil\u00e1gyi","sequence":"additional","affiliation":[{"name":"University Research and Innovation Center, Physiological Controls Research Center Óbuda University,Budapest,Hungary"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.12700\/aph.14.1.2017.1.6"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.12700\/APH.20.9.2023.9.1"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.12700\/APH.19.7.2022.7.7"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.12700\/aph.19.5.2022.5.7"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/1932296813514502"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2020.583016"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1080\/10528008.2015.999586"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1088\/0967-3334\/29\/8\/008"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1586\/14787210.5.5.883"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1185\/03007990903482772"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1177\/193229680900300508"},{"volume-title":"Reinforcement Learning: An Introduction","year":"2018","author":"Sutton","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316887"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"journal-title":"Addressing function approximation error in actor-critic methods","year":"2018","author":"Fujimoto","key":"ref17"},{"journal-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref18"},{"journal-title":"Soft actor-critic algorithms and applications","year":"2018","author":"Haarnoja","key":"ref19"},{"key":"ref20","first-page":"305","article-title":"Autonomous driving in reality","volume":"20","author":"Pan","year":"2019","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"ref21","first-page":"1101","article-title":"Artificial intelligence in health care: A report from the national academy of medicine","volume-title":"JAMA","volume":"320","author":"Komorowski","year":"2018"},{"key":"ref22","first-page":"105","article-title":"A closed-loop artificial pancreas","volume":"2019","author":"Breton","year":"2018","journal-title":"Handbook of diabetes technology"},{"key":"ref23","first-page":"717","article-title":"Artificial pancreas systems for type 1 diabetes mellitus: A systematic review and meta-analysis of efficacy and heterogeneity","volume":"8","author":"Herrero","year":"2017","journal-title":"Diabetes Therapy"},{"key":"ref24","first-page":"2254","article-title":"Glucose control with a wearable, closed-loop insulin delivery system in free-living people with type 1 diabetes: A randomized controlled trial","volume":"390","author":"Garg","year":"2017","journal-title":"The Lancet"},{"issue":"Suppl 2","key":"ref25","first-page":"S3","article-title":"Closing the loop: the triumphs and challenges","volume":"18","author":"Hovorka","year":"2016","journal-title":"Diabetes Technology & Therapeutics"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1509351"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1186\/s13098-020-00529-z"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1177\/193229680800200414"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SMC53654.2022.9945084"},{"journal-title":"Reinforcement learning approaches for artificial pancreas control","author":"DEI ROSSI","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1038\/nrendo.2017.3"},{"journal-title":"Finite-sample analysis for sarsa with linear function approximation","year":"2019","author":"Zou","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3100007"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.1995.598994"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"journal-title":"Feedback Control of Dynamic Systems","year":"2018","author":"Franklin","key":"ref36"},{"journal-title":"Model-based reinforcement learning for type 1diabetes blood glucose control","year":"2020","author":"Yamagata","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_179268"},{"journal-title":"Pathfinding in random partially observable environments with vision-informed deep reinforcement learning","year":"2022","author":"Dowling","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1186\/s12902-018-0300-0"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC48229.2022.9871054"},{"volume-title":"simglucose: A type 1 diabetes simulator","year":"2024","author":"Xu","key":"ref42"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2023.104376"},{"key":"ref44","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"International conference on machine learning","author":"Fujimoto"},{"key":"ref45","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume":"33","author":"Kumar","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref46","first-page":"20 132","article-title":"A minimalist approach to offline reinforcement learning","volume":"34","author":"Fujimoto","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3390\/app10186350"},{"journal-title":"Trust region policy optimization","year":"2017","author":"Schulman","key":"ref48"},{"journal-title":"Deep reinforcement learning for closed-loop blood glucose control","year":"2020","author":"Fox","key":"ref49"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2020.101836"}],"event":{"name":"2024 IEEE 18th International Symposium on Applied Computational Intelligence and Informatics (SACI)","start":{"date-parts":[[2024,5,23]]},"location":"Timisoara, Romania","end":{"date-parts":[[2024,5,25]]}},"container-title":["2024 IEEE 18th International Symposium on Applied Computational Intelligence and Informatics (SACI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10619709\/10619059\/10619866.pdf?arnumber=10619866","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T05:16:28Z","timestamp":1723526188000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10619866\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,23]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/saci60582.2024.10619866","relation":{},"subject":[],"published":{"date-parts":[[2024,5,23]]}}}