{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:05:28Z","timestamp":1755907528386,"version":"3.44.0"},"reference-count":15,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T00:00:00Z","timestamp":1751932800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T00:00:00Z","timestamp":1751932800000},"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":[[2025,7,8]]},"DOI":"10.23919\/acc63710.2025.11107979","type":"proceedings-article","created":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:17:51Z","timestamp":1755800271000},"page":"553-558","source":"Crossref","is-referenced-by-count":0,"title":["Hybrid Reinforcement Learning for Continuous-Time Industrial Systems with Time-Varying Delays"],"prefix":"10.23919","author":[{"given":"Iga","family":"Pawlak","sequence":"first","affiliation":[{"name":"ABB Corporate Research,Västerås,Sweden"}]},{"given":"Soroush","family":"Rastegarpour","sequence":"additional","affiliation":[{"name":"ABB Corporate Research,Västerås,Sweden"}]},{"given":"Hamid Reza","family":"Feyzmahdavian","sequence":"additional","affiliation":[{"name":"ABB Corporate Research,Västerås,Sweden"}]},{"given":"Alf J.","family":"Isaksson","sequence":"additional","affiliation":[{"name":"ABB Corporate Research,Västerås,Sweden"}]}],"member":"263","reference":[{"volume-title":"Reinforcement Learning and Optimal Control.","year":"2019","author":"Bertsekas","key":"ref1"},{"volume-title":"Reinforcement learning: An introduction.","year":"2018","author":"Sutton","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-09393-2"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2024.08.363"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejcon.2025.101326"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2003.809799"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-008-9056-7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5650345"},{"article-title":"Acting in delayed environments with non-stationary markov policies","volume-title":"International Conference on Learning Representations","author":"Derman","key":"ref9"},{"article-title":"At human speed: Deep reinforcement learning with action delay","year":"2018","author":"Firoiu","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.04.015"},{"key":"ref12","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja"},{"issue":"268","key":"ref13","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482386"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2011.03.008"}],"event":{"name":"2025 American Control Conference (ACC)","start":{"date-parts":[[2025,7,8]]},"location":"Denver, CO, USA","end":{"date-parts":[[2025,7,10]]}},"container-title":["2025 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11107441\/11107442\/11107979.pdf?arnumber=11107979","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:50:42Z","timestamp":1755841842000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11107979\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,8]]},"references-count":15,"URL":"https:\/\/doi.org\/10.23919\/acc63710.2025.11107979","relation":{},"subject":[],"published":{"date-parts":[[2025,7,8]]}}}