{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T05:44:15Z","timestamp":1773207855646,"version":"3.50.1"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,7]],"date-time":"2023-06-07T00:00:00Z","timestamp":1686096000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,7]],"date-time":"2023-06-07T00:00:00Z","timestamp":1686096000000},"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":[[2023,6,7]]},"DOI":"10.1109\/aiiot58121.2023.10174426","type":"proceedings-article","created":{"date-parts":[[2023,7,13]],"date-time":"2023-07-13T17:18:41Z","timestamp":1689268721000},"page":"0797-0803","source":"Crossref","is-referenced-by-count":5,"title":["Action Masked Deep Reinforcement learning for Controlling Industrial Assembly Lines"],"prefix":"10.1109","author":[{"given":"Ali Mohamed","family":"Ali","sequence":"first","affiliation":[{"name":"Carleton University,Dept. of Mechanical and Aerospace Engineering,Ottawa,Canada"}]},{"given":"Luca","family":"Tirel","sequence":"additional","affiliation":[{"name":"University of Rome \"La Sapienza\",Dept. of Computer, Control, and Management Engineering,Rome,Italy"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2987820"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17088"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2021.107462"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11040539"},{"key":"ref20","article-title":"A closer look at invalid action masking in policy gradient algorithms","volume":"abs 2006 14171","author":"huang","year":"2020","journal-title":"CoRR"},{"key":"ref11","article-title":"A two-stage framework and reinforcement learning-based optimization algorithms for complex scheduling problems","author":"he","year":"2021"},{"key":"ref10","first-page":"1114","article-title":"A reinforcement learning approach to job-shop scheduling","author":"zhang","year":"1995","journal-title":"Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.11.2.308"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1115\/1.4014559"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CoDIT49905.2020.9263946"},{"key":"ref16","article-title":"Openai gym","volume":"abs 1606 1540","author":"brockman","year":"2016","journal-title":"CoRR"},{"key":"ref19","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref18","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013"},{"key":"ref8","article-title":"Reinforcement learning in large or unknown mdps","author":"tewari","year":"2007","journal-title":"Ph D Dissertation"},{"key":"ref7","article-title":"Artificial intelligence: a modern approach","author":"russell","year":"2002"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/21.257756"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2006.10.010"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.32.8.909"},{"key":"ref6","article-title":"Learning from delayed rewards","author":"watkins","year":"1989"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CoDIT49905.2020.9263946"}],"event":{"name":"2023 IEEE World AI IoT Congress (AIIoT)","location":"Seattle, WA, USA","start":{"date-parts":[[2023,6,7]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["2023 IEEE World AI IoT Congress (AIIoT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10174256\/10174258\/10174426.pdf?arnumber=10174426","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T17:56:45Z","timestamp":1690912605000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10174426\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,7]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/aiiot58121.2023.10174426","relation":{},"subject":[],"published":{"date-parts":[[2023,6,7]]}}}