{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T12:48:06Z","timestamp":1781354886876,"version":"3.54.1"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2961174","type":"journal-article","created":{"date-parts":[[2019,12,23]],"date-time":"2019-12-23T23:56:55Z","timestamp":1577145415000},"page":"186340-186351","source":"Crossref","is-referenced-by-count":98,"title":["An Efficient Hardware Implementation of Reinforcement Learning: The Q-Learning Algorithm"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8230-7211","authenticated-orcid":false,"given":"Sergio","family":"Spano","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gian Carlo","family":"Cardarilli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Di Nunzio","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rocco","family":"Fazzolari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniele","family":"Giardino","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2415-1386","authenticated-orcid":false,"given":"Marco","family":"Matta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alberto","family":"Nannarelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Re","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","year":"2012","journal-title":"Synthesis and Simulation Design Guide"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/4.126534"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1117\/12.452034"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2019.2909117"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2014.2315634"},{"key":"ref30","first-page":"827","article-title":"Large-scale tabular-form hardware architecture for Q-Learning with delays","author":"liu","year":"2007","journal-title":"Proc 50th Midwest Symp Circuits Syst"},{"key":"ref37","year":"2019","journal-title":"Vivado Design Suite User Guide"},{"key":"ref36","year":"0","journal-title":"FPGAs"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/S3S.2017.8308753"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/second.2006.1629364"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2010.2043968"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2920913"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2901300"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1049\/el.2019.0244"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2946848"},{"key":"ref15","article-title":"On-line Q-learning using connectionist systems","author":"rummery","year":"1994"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2941229"},{"key":"ref18","first-page":"435","article-title":"Hardware implementation of FAST-based reinforcement learning algorithm","author":"hwang","year":"2005","journal-title":"IEEE Int Workshop VLSI Design Video Tech"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MNNFS.1996.493812"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3322645.3322693"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2012.2227719"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(77)90007-8"},{"key":"ref3","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2759728"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2885950"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2016.2570255"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2522401"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2015.2420792"},{"key":"ref2","volume":"4","author":"abu-mostafa","year":"2012","journal-title":"Learning From Data"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2938390"},{"key":"ref1","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/37.236324"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/AERO.2017.7943929"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2018.8445099"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3039902.3039915"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1561\/2200000071"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304058"},{"key":"ref25","first-page":"1889","article-title":"Trust region policy otimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08937555.pdf?arnumber=8937555","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:31:46Z","timestamp":1641987106000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8937555\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2961174","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]}}}