{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T02:54:49Z","timestamp":1781232889508,"version":"3.54.1"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"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":[[2019,7]]},"DOI":"10.1109\/embc.2019.8857295","type":"proceedings-article","created":{"date-parts":[[2019,10,8]],"date-time":"2019-10-08T00:51:21Z","timestamp":1570495881000},"page":"3960-3963","source":"Crossref","is-referenced-by-count":35,"title":["Deep Reinforcement Learning for Optimal Critical Care Pain Management with Morphine using Dueling Double-Deep Q Networks"],"prefix":"10.1109","author":[{"given":"Daniel","family":"Lopez-Martinez","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Patrick","family":"Eschenfeldt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sassan","family":"Ostvar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Myles","family":"Ingram","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chin","family":"Hur","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rosalind","family":"Picard","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Continuous State-Space Models for Optimal Sepsis Treatment - a Deep Reinforcement Learning Approach","author":"raghu","year":"2017","journal-title":"Machine Learning for Healthcare Conference"},{"key":"ref11","first-page":"161","article-title":"Reinforcement Learning with Action-Derived Rewards for Chemotherapy and Clinical Trial Dosing Regimen Selection","volume":"85","author":"yauney","year":"2018","journal-title":"MLHC"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpain.2004.11.005"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.35"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1093\/bjaceaccp\/mkv018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1093\/bja\/aen094"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1111\/pme.12915"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"watkins","year":"1992","journal-title":"Machine Learning"},{"key":"ref18","first-page":"2094","article-title":"Deep Reinforcement Learning with Double Q-learning","author":"van hasselt","year":"2016","journal-title":"Proc of the Thirtieth AAAI Conference on Artificial Intelligence"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1109\/MCOM.2016.1600399CM","article-title":"Dueling Network Architectures for Deep Reinforcement Learning","volume":"54","author":"wang","year":"2015","journal-title":"IEEE Communications Magazine"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.286"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8545823"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref5","article-title":"Physiological and Behavioral Profiling for Nociceptive Pain Estimation Using Personalized Multitask Learning","author":"lopez-martinez","year":"2017","journal-title":"Neural Information Processing Systems (NIPS) Workshop on Machine Learning for Health"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2016.7591355"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2018.8513575"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1097\/CCM.0b013e3182783b72"},{"key":"ref9","article-title":"Deep Reinforcement Learning for Sepsis Treatment","author":"raghu","year":"2017","journal-title":"Neural Information Processing Systems (NIPS) Workshop on Machine Learning for Health"},{"key":"ref20","article-title":"A Method for Stochastic Optimization","author":"kingma","year":"2015","journal-title":"Proceedings of the 3rd International Conference on Learning Representations"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.280.6206.12"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpsychires.2014.08.009"}],"event":{"name":"2019 41st Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)","location":"Berlin, Germany","start":{"date-parts":[[2019,7,23]]},"end":{"date-parts":[[2019,7,27]]}},"container-title":["2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8844528\/8856280\/08857295.pdf?arnumber=8857295","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:10:38Z","timestamp":1657854638000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8857295\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/embc.2019.8857295","relation":{},"subject":[],"published":{"date-parts":[[2019,7]]}}}