{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:40:55Z","timestamp":1740102055828,"version":"3.37.3"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","award":["AISG-GC-2019-001-2A,AISG2-TC-2022-004"],"award-info":[{"award-number":["AISG-GC-2019-001-2A,AISG2-TC-2022-004"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,18]]},"DOI":"10.1109\/ijcnn54540.2023.10191692","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T17:30:03Z","timestamp":1690997403000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["Demystifying Complex Treatment Recommendations: A Hierarchical Cooperative Multi-Agent RL Approach"],"prefix":"10.1109","author":[{"given":"Dilruk","family":"Perera","sequence":"first","affiliation":[{"name":"Institute of Data Science, Saw Swee Hock School of Public Health, National University of Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siqi","family":"Liu","sequence":"additional","affiliation":[{"name":"NUS Graduate School - ISEP, Institute of Data Science, National University of Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengling","family":"Feng","sequence":"additional","affiliation":[{"name":"Institute of Data Science, Saw Swee Hock School of Public Health, National University of Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11902"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630669"},{"journal-title":"Hierarchical reinforcement learning for epidemics intervention","year":"2020","author":"dong","key":"ref15"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467181"},{"key":"ref31","article-title":"Safe reinforcement learning","author":"thomas","year":"2015","journal-title":"University of Massachusetts Amherst"},{"key":"ref30","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1912330117"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0253-x"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1002\/14651858.CD003709.pub2"},{"key":"ref2","first-page":"1031","article-title":"Model-based reinforcement learning with nearly tight exploration complexity bounds","author":"szita","year":"0","journal-title":"Proceedings of the 27th International Conference on Machine Learning (ICML-10)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2007.05.001"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMp1606181"},{"key":"ref16","article-title":"A reinforcement learning approach to weaning of mechanical ventilation in intensive care units","author":"prasad","year":"0","journal-title":"33rd Conference on Uncertainty in Artificial Intelligence UAI 2017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3477600"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.surg.2020.11.040"},{"key":"ref24","first-page":"1","article-title":"A markov decision process to suggest optimal treatment of severe infections in intensive care","author":"komorowski","year":"0","journal-title":"Neural Information Processing Systems workshop on Machine Learning for Health"},{"key":"ref23","first-page":"139","article-title":"An empirical study of representation learning for reinforcement learning in healthcare","author":"killian","year":"0","journal-title":"Proceedings of the Machine Learning for Health NeurIPS Workshop"},{"key":"ref26","article-title":"Optimization of neuroprosthetic vision via end-to-end deep reinforcement learning","author":"k\u00fc\u00e7\u00fcko?lu","year":"2022","journal-title":"BioRxiv"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2021.101878"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2016.7591355"},{"key":"ref22","article-title":"Model-based reinforcement learning for sepsis treatment","author":"raghu","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3390\/data2010008"},{"key":"ref28","article-title":"Deep reinforcement learning for sepsis treatment","author":"raghu","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref27","first-page":"508","article-title":"Deep reinforcement learning for closed-loop blood glucose control","author":"fox","year":"0","journal-title":"Machine Learning for Healthcare Conference"},{"key":"ref29","first-page":"4295","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"0","journal-title":"Int Conference on Machine Learning"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2020.101836"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3543846"},{"key":"ref9","article-title":"Near-optimal reinforcement learning in dynamic treatment regimes","volume":"32","author":"zhang","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.i1585"},{"key":"ref3","first-page":"147","article-title":"Continuous state-space models for optimal sepsis treatment: A deep reinforcement learning approach","author":"raghu","year":"0","journal-title":"Machine Learning for Healthcare Conference"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1965.1098193"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"}],"event":{"name":"2023 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2023,6,18]]},"location":"Gold Coast, Australia","end":{"date-parts":[[2023,6,23]]}},"container-title":["2023 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10190990\/10190992\/10191692.pdf?arnumber=10191692","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T17:47:19Z","timestamp":1692640039000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10191692\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/ijcnn54540.2023.10191692","relation":{},"subject":[],"published":{"date-parts":[[2023,6,18]]}}}