{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T16:45:15Z","timestamp":1765039515597,"version":"3.44.0"},"reference-count":11,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"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":[[2019,6]]},"DOI":"10.1109\/ichi.2019.8904645","type":"proceedings-article","created":{"date-parts":[[2019,11,25]],"date-time":"2019-11-25T14:38:04Z","timestamp":1574692684000},"page":"1-3","source":"Crossref","is-referenced-by-count":27,"title":["Deep Inverse Reinforcement Learning for Sepsis Treatment"],"prefix":"10.1109","author":[{"given":"Chao","family":"Yu","sequence":"first","affiliation":[{"name":"Dalian University of Technology,School of Computer Science and Technology,Dalian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guoqi","family":"Ren","sequence":"additional","affiliation":[{"name":"Dalian University of Technology,School of Computer Science and Technology,Dalian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiming","family":"Liu","sequence":"additional","affiliation":[{"name":"Hong Kong Baptist University,Department of Computer Science,Kowloon Tong,Hongkong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1039\/b907946g"},{"journal-title":"Reinforcement Learning An Introduction MIT Press","year":"2018","author":"sutton","key":"ref3"},{"key":"ref10","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"NIPS"},{"key":"ref6","article-title":"Continuous state-space models for optimal sepsis treatment-a deep reinforcement learning approach","author":"raghu","year":"2017","journal-title":"arXiv preprint arXiv 1705 08422"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/BF01709751"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.35"},{"key":"ref8","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","volume":"1","author":"ng","year":"2000","journal-title":"ICML"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-019-0763-6"},{"key":"ref2","article-title":"Deep reinforcement learning for sepsis treatment","author":"raghu","year":"2017","journal-title":"arXiv preprint arXiv 1711 07128"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-019-0755-6"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2016.0287"}],"event":{"name":"2019 IEEE International Conference on Healthcare Informatics (ICHI)","start":{"date-parts":[[2019,6,10]]},"location":"Xi'an, China","end":{"date-parts":[[2019,6,13]]}},"container-title":["2019 IEEE International Conference on Healthcare Informatics (ICHI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8895688\/8904471\/08904645.pdf?arnumber=8904645","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T19:19:33Z","timestamp":1756754373000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8904645\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6]]},"references-count":11,"URL":"https:\/\/doi.org\/10.1109\/ichi.2019.8904645","relation":{},"subject":[],"published":{"date-parts":[[2019,6]]}}}