{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T16:20:19Z","timestamp":1761582019607,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"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":[[2020,8]]},"DOI":"10.1109\/case48305.2020.9216863","type":"proceedings-article","created":{"date-parts":[[2020,10,8]],"date-time":"2020-10-08T20:01:51Z","timestamp":1602187311000},"page":"1434-1440","source":"Crossref","is-referenced-by-count":7,"title":["Deep Q-learning for the Control of PLC-based Automated Production Systems"],"prefix":"10.1109","author":[{"given":"Jonas","family":"Zinn","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Birgit","family":"Vogel-Heuser","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paulina","family":"Ockier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10295","article-title":"Deep reinforcement learning with double q-learning","author":"van hasselt","year":"2016","journal-title":"THIRTIETH AAAI Conference on Artificial Intelligence"},{"key":"ref11","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2015","journal-title":"arXiv preprint arXiv 1511 05271"},{"key":"ref12","article-title":"Prioritized experience replay","author":"schaul","year":"2015","journal-title":"arXiv preprint arXiv 1511 05952"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref16","first-page":"1","article-title":"Selfsupervised deep reinforcement learning with generalized computation graphs for robot navigation","author":"kahn","year":"2018","journal-title":"2018 IEEE International Conference on Robotics and Automation (ICRA)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202312"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IS.2018.8710460"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/AI4I.2018.8665712"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989324"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref6","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv preprint arXiv 1312 5602"},{"key":"ref5","first-page":"5048","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11796","article-title":"Rainbow: Combining improvements in deep reinforcement learning","author":"hessel","year":"2018","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"ref7","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487156"},{"article-title":"Learning an embedding space for transferable robot skills","year":"2018","author":"hausman","key":"ref1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"journal-title":"Researching Evolution in Industrial Plant Automation Scenarios and Documentation of the Pick and Place Unit","year":"2014","author":"vogel-heuser","key":"ref20"},{"journal-title":"Modeling capabilities of industrial plants for order-controlled production","year":"2019","author":"wolf","key":"ref21"}],"event":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","start":{"date-parts":[[2020,8,20]]},"location":"Hong Kong, Hong Kong","end":{"date-parts":[[2020,8,21]]}},"container-title":["2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9210430\/9216730\/09216863.pdf?arnumber=9216863","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,22]],"date-time":"2022-11-22T17:59:14Z","timestamp":1669139954000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9216863\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/case48305.2020.9216863","relation":{},"subject":[],"published":{"date-parts":[[2020,8]]}}}