{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:45:39Z","timestamp":1740102339364,"version":"3.37.3"},"reference-count":12,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,7,3]],"date-time":"2023-07-03T00:00:00Z","timestamp":1688342400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,3]],"date-time":"2023-07-03T00:00:00Z","timestamp":1688342400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003141","name":"Consejo Nacional de Ciencia y Tecnologia CONACYT","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003141","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,7,3]]},"DOI":"10.1109\/codit58514.2023.10284480","type":"proceedings-article","created":{"date-parts":[[2023,10,24]],"date-time":"2023-10-24T17:46:12Z","timestamp":1698169572000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Application of Reinforcement Learning with Recurrent Neural Networks for Optimal Scheduling of Flow-Shop Systems Under Uncertainty"],"prefix":"10.1109","author":[{"given":"Daniel","family":"Rangel-Martinez","sequence":"first","affiliation":[{"name":"University of Waterloo,Chemical Engineering Department,Canada"}]},{"given":"Luis","family":"Ricardez-Sandoval","sequence":"additional","affiliation":[{"name":"University of Waterloo,Chemical Engineering Department,Canada"}]}],"member":"263","reference":[{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2018.03.212"},{"journal-title":"An Industrial Application of Deep Reinforcement Learning for Chemical Production Scheduling 2020","year":"0","author":"hubbs","key":"ref7"},{"key":"ref12","first-page":"278","article-title":"Policy Invariance Under Reward Transformations: Theory and Application to Reward Shaping","author":"ng","year":"1999","journal-title":"Proceedings of the Sixteenth International Conference on Machine Learning"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11740-020-00967-8"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.simpat.2004.12.003"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/17.293383"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2020.106982"},{"journal-title":"Deep recurrent q-learning for partially observable mdps","year":"2017","author":"hausknecht","key":"ref11"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.11.051"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASMC.2018.8373191"},{"key":"ref2","article-title":"Reinforcement Learning, second edition: An Introduction","author":"sutton","year":"2018","journal-title":"MIT Press"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-020-00326-5"}],"event":{"name":"2023 9th International Conference on Control, Decision and Information Technologies (CoDIT)","start":{"date-parts":[[2023,7,3]]},"location":"Rome, Italy","end":{"date-parts":[[2023,7,6]]}},"container-title":["2023 9th International Conference on Control, Decision and Information Technologies (CoDIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10284032\/10284045\/10284480.pdf?arnumber=10284480","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:02:38Z","timestamp":1699902158000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10284480\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,3]]},"references-count":12,"URL":"https:\/\/doi.org\/10.1109\/codit58514.2023.10284480","relation":{},"subject":[],"published":{"date-parts":[[2023,7,3]]}}}