{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T12:47:51Z","timestamp":1781354871414,"version":"3.54.1"},"reference-count":25,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100010661","name":"H2020 Project \u201cENERgy-efficient manufacturing system MANagement (ENERMAN)\u201d","doi-asserted-by":"publisher","award":["958478"],"award-info":[{"award-number":["958478"]}],"id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3147674","type":"journal-article","created":{"date-parts":[[2022,1,29]],"date-time":"2022-01-29T00:59:15Z","timestamp":1643417955000},"page":"18526-18543","source":"Crossref","is-referenced-by-count":12,"title":["Deep Reinforcement Learning Acceleration for Real-Time Edge Computing Mixed Integer Programming Problems"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7946-2683","authenticated-orcid":false,"given":"Gerasimos","family":"Gerogiannis","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6124-221X","authenticated-orcid":false,"given":"Michael","family":"Birbas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1347-980X","authenticated-orcid":false,"given":"Aimilios","family":"Leftheriotis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7676-685X","authenticated-orcid":false,"given":"Eleftherios","family":"Mylonas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5219-1676","authenticated-orcid":false,"given":"Nikolaos","family":"Tzanis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9468-7215","authenticated-orcid":false,"given":"Alexios","family":"Birbas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"issue":"2","key":"ref1","volume-title":"Dynamic Programming and Optimal Control","volume":"1","author":"Bertsekas","year":"1995"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2926732"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761969"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/bf00992699"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2019.2928811"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2876279"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304058"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3322645.3322693"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586213"},{"key":"ref10","article-title":"Playing atari with deep reinforcement learning","volume-title":"arXiv:1312.5602","author":"Mnih","year":"2013"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.dcan.2018.10.003"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2018.8377343"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2935450"},{"key":"ref14","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. NIPS","volume":"99","author":"Sutton"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2981557"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2021.3087258"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3014896"},{"key":"ref18","first-page":"1","article-title":"A many-core accelerator design for on-chip deep reinforcement learning","volume-title":"Proc. 39th Int. Conf. Comput.-Aided Design","author":"Wang"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LSSC.2019.2941252"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2019.8662447"},{"key":"ref21","article-title":"An overview of gradient descent optimization algorithms","volume-title":"arXiv:1609.04747","author":"Ruder","year":"2016"},{"key":"ref22","article-title":"Adam: A method for stochastic optimization","volume-title":"arXiv:1412.6980","author":"Kingma","year":"2014"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1142\/9361"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2815360"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09696340.pdf?arnumber=9696340","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T22:58:09Z","timestamp":1705532289000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9696340\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3147674","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}