{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T13:24:05Z","timestamp":1767705845597,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031226946"},{"type":"electronic","value":"9783031226953"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-22695-3_39","type":"book-chapter","created":{"date-parts":[[2022,12,2]],"date-time":"2022-12-02T15:11:58Z","timestamp":1669993918000},"page":"557-570","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Non-linear Continuous Action Spaces for\u00a0Reinforcement Learning in\u00a0Type 1 Diabetes"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7702-0718","authenticated-orcid":false,"given":"Chirath","family":"Hettiarachchi","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4967-3348","authenticated-orcid":false,"given":"Nicolo","family":"Malagutti","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6964-3819","authenticated-orcid":false,"given":"Christopher J.","family":"Nolan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4195-1641","authenticated-orcid":false,"given":"Hanna","family":"Suominen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7665-7039","authenticated-orcid":false,"given":"Elena","family":"Daskalaki","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,12,3]]},"reference":[{"issue":"5","key":"39_CR1","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1586\/17434440.2013.827515","volume":"10","author":"MK Bothe","year":"2013","unstructured":"Bothe, M.K., Dickens, L., et al.: The use of reinforcement learning algorithms to meet the challenges of an artificial pancreas. Expert Rev. Med. Devices 10(5), 661\u2013673 (2013)","journal-title":"Expert Rev. Med. Devices"},{"issue":"1","key":"39_CR2","doi-asserted-by":"publisher","first-page":"e20973","DOI":"10.2196\/20973","volume":"6","author":"N Brew-Sam","year":"2021","unstructured":"Brew-Sam, N., Chhabra, M., et al.: Experiences of young people and their caregivers of using technology to manage type 1 diabetes mellitus: systematic literature review and narrative synthesis. JMIR Diabetes 6(1), e20973 (2021)","journal-title":"JMIR Diabetes"},{"key":"39_CR3","unstructured":"Brockman, G., et al.: OpenAI gym. arXiv Eprint arXiv:1606.01540 (2016)"},{"issue":"11","key":"39_CR4","doi-asserted-by":"publisher","first-page":"2672","DOI":"10.2337\/db11-0654","volume":"60","author":"C Cobelli","year":"2011","unstructured":"Cobelli, C., Renard, E., Kovatchev, B.: Artificial pancreas: past, present, future. Diabetes 60(11), 2672\u20132682 (2011)","journal-title":"Diabetes"},{"issue":"10138","key":"39_CR5","doi-asserted-by":"publisher","first-page":"2449","DOI":"10.1016\/S0140-6736(18)31320-5","volume":"391","author":"LA DiMeglio","year":"2018","unstructured":"DiMeglio, L.A., Evans-Molina, C., Oram, R.A.: Type 1 diabetes. Lancet 391(10138), 2449\u20132462 (2018)","journal-title":"Lancet"},{"key":"39_CR6","unstructured":"Dulac-Arnold, G., Mankowitz, D., Hester, T.: Challenges of real-world reinforcement learning. arXiv preprint arXiv:1904.12901 (2019)"},{"key":"39_CR7","unstructured":"Fox, I., Wiens, J.: Reinforcement learning for blood glucose control: challenges and opportunities. In: Reinforcement Learning for Real Life (RL4RealLife) Workshop in the 36th International Conference on Machine Learning (2019)"},{"key":"39_CR8","unstructured":"Fox, I., et al.: Deep reinforcement learning for closed-loop blood glucose control. In: Machine Learning for Healthcare Conference, pp. 508\u2013536. PMLR (2020)"},{"issue":"1","key":"39_CR9","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1177\/193229680900300106","volume":"3","author":"BP Kovatchev","year":"2009","unstructured":"Kovatchev, B.P., Breton, M., et al.: In silico preclinical trials: a proof of concept in closed-loop control of type 1 diabetes. J. Diabetes Sci. Technol. 3(1), 44\u201355 (2009)","journal-title":"J. Diabetes Sci. Technol."},{"issue":"6","key":"39_CR10","doi-asserted-by":"publisher","first-page":"849","DOI":"10.1089\/dia.2005.7.849","volume":"7","author":"BP Kovatchev","year":"2005","unstructured":"Kovatchev, B.P., Clarke, W.L., et al.: Quantifying temporal glucose variability in diabetes via continuous glucose monitoring: mathematical methods and clinical application. Diabetes Technol. Ther. 7(6), 849\u2013862 (2005)","journal-title":"Diabetes Technol. Ther."},{"key":"39_CR11","unstructured":"Lazaric, A., Restelli, M., Bonarini, A.: Reinforcement learning in continuous action spaces through sequential monte carlo methods. In: Advances in Neural Information Processing Systems, vol. 20 (2007)"},{"issue":"2","key":"39_CR12","doi-asserted-by":"publisher","first-page":"536","DOI":"10.1109\/JBHI.2020.3002022","volume":"25","author":"S Lee","year":"2020","unstructured":"Lee, S., Kim, J., et al.: Toward a fully automated artificial pancreas system using a bioinspired reinforcement learning design: in silico validation. IEEE J. Biomed. Health Inform. 25(2), 536\u2013546 (2020)","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"39_CR13","unstructured":"Lillicrap, T.P., Hunt, J.J., Pritzel, A., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"39_CR14","doi-asserted-by":"publisher","first-page":"105756","DOI":"10.1109\/ACCESS.2021.3100007","volume":"9","author":"MH Lim","year":"2021","unstructured":"Lim, M.H., Lee, W.H., et al.: A blood glucose control framework based on reinforcement learning with safety and interpretability: in silico validation. IEEE Access 9, 105756\u2013105775 (2021)","journal-title":"IEEE Access"},{"key":"39_CR15","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1214\/aoms\/1177730491","volume":"18","author":"HB Mann","year":"1947","unstructured":"Mann, H.B., Whitney, D.R.: On a test of whether one of two random variables is stochastically larger than the other. Ann. Math. Stat. 18, 50\u201360 (1947)","journal-title":"Ann. Math. Stat."},{"key":"39_CR16","unstructured":"Naik, A., Shariff, R., et al.: Discounted reinforcement learning is not an optimization problem. arXiv preprint arXiv:1910.02140 (2019)"},{"issue":"14","key":"39_CR17","doi-asserted-by":"publisher","first-page":"977","DOI":"10.1056\/NEJM199309303291401","volume":"329","author":"D Nathan","year":"1993","unstructured":"Nathan, D., Genuth, S., et al.: The effect of intensive treatment of diabetes on the development and progression of long-term complications in insulin-dependent diabetes mellitus. N. Engl. J. Med. 329(14), 977\u2013986 (1993)","journal-title":"N. Engl. J. Med."},{"key":"39_CR18","unstructured":"Online: Insulin pump comparison. http:\/\/www.betterlivingnow.com\/forms\/Insulin-Pump-Comparison.pdf. Accessed 24 Mar 2022"},{"issue":"2","key":"39_CR19","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1152\/physiologyonline.2000.15.2.72","volume":"15","author":"P Rorsman","year":"2000","unstructured":"Rorsman, P., Eliasson, L., Renstrom, E., Gromada, J., Barg, S., Gopel, S.: The cell physiology of biphasic insulin secretion. Physiology 15(2), 72\u201377 (2000)","journal-title":"Physiology"},{"issue":"7839","key":"39_CR20","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1038\/s41586-020-03051-4","volume":"588","author":"J Schrittwieser","year":"2020","unstructured":"Schrittwieser, J., Antonoglou, I., et al.: Mastering Atari, go, chess and shogi by planning with a learned model. Nature 588(7839), 604\u2013609 (2020)","journal-title":"Nature"},{"key":"39_CR21","unstructured":"Schulman, J., Moritz, P., Levine, S., et al.: High-dimensional continuous control using generalized advantage estimation. arXiv preprint arXiv:1506.02438 (2015)"},{"key":"39_CR22","unstructured":"Schulman, J., Wolski, F., et al.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"issue":"1","key":"39_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.4103\/2230-973X.176456","volume":"6","author":"RB Shah","year":"2016","unstructured":"Shah, R.B., Patel, M., et al.: Insulin delivery methods: past, present and future. Int. J. Pharm. Investig. 6(1), 1\u20139 (2016)","journal-title":"Int. J. Pharm. Investig."},{"issue":"3\/4","key":"39_CR24","doi-asserted-by":"publisher","first-page":"591","DOI":"10.2307\/2333709","volume":"52","author":"SS Shapiro","year":"1965","unstructured":"Shapiro, S.S., Wilk, M.B.: An analysis of variance test for normality (complete samples). Biometrika 52(3\/4), 591\u2013611 (1965)","journal-title":"Biometrika"},{"key":"39_CR25","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)"},{"key":"39_CR26","unstructured":"Tassa, Y., Doron, Y., Muldal, A., Erez, T., et al.: DeepMind control suite. arXiv preprint arXiv:1801.00690 (2018)"},{"key":"39_CR27","doi-asserted-by":"crossref","unstructured":"Todorov, E., Erez, T., Tassa, Y.: MuJoCo: a physics engine for model-based control. In: 2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 5026\u20135033. IEEE (2012)","DOI":"10.1109\/IROS.2012.6386109"},{"key":"39_CR28","unstructured":"Vajapey, A.: Predicting optimal sedation control with reinforcement learning. Ph.D. thesis, Massachusetts Institute of Technology (2019)"},{"key":"39_CR29","unstructured":"Xie, J.: Simglucose v0. 2.1 (2018). https:\/\/github.com\/jxx123\/simglucose. Accessed 13 Jan 2022"},{"key":"39_CR30","unstructured":"Zahavy, T., et al.: Learn what not to learn: action elimination with deep reinforcement learning. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"39_CR31","doi-asserted-by":"crossref","unstructured":"Zhu, T., Li, K., Georgiou, P.: A dual-hormone closed-loop delivery system for type 1 diabetes using deep reinforcement learning. arXiv preprint arXiv:1910.04059 (2019)","DOI":"10.1007\/978-3-030-53352-6_5"},{"issue":"4","key":"39_CR32","doi-asserted-by":"publisher","first-page":"1223","DOI":"10.1109\/JBHI.2020.3014556","volume":"25","author":"T Zhu","year":"2020","unstructured":"Zhu, T., Li, K., Herrero, P., Georgiou, P.: Basal glucose control in type 1 diabetes using deep reinforcement learning: an in silico validation. IEEE J. Biomed. Health Inform. 25(4), 1223\u20131232 (2020)","journal-title":"IEEE J. Biomed. Health Inform."}],"container-title":["Lecture Notes in Computer Science","AI 2022: Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-22695-3_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T15:29:14Z","timestamp":1710257354000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-22695-3_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031226946","9783031226953"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-22695-3_39","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"3 December 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"A repository of code used in this study, and further supplementary material, is available at .","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code Availability"}},{"value":"AI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australasian Joint Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Perth, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"35","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ausai2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ajcai2022.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"90","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"56","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"62% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}