{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:16:42Z","timestamp":1740100602563,"version":"3.37.3"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,10,31]],"date-time":"2021-10-31T00:00:00Z","timestamp":1635638400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,31]],"date-time":"2021-10-31T00:00:00Z","timestamp":1635638400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100014121","name":"Xilinx","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100014121","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014121","name":"Xilinx","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100014121","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,10,31]]},"DOI":"10.1109\/ieeeconf53345.2021.9723147","type":"proceedings-article","created":{"date-parts":[[2022,3,4]],"date-time":"2022-03-04T20:26:46Z","timestamp":1646425606000},"page":"1186-1190","source":"Crossref","is-referenced-by-count":0,"title":["\u201cMR Q-Learning\u201d Algorithm for Efficient Hardware Implementations"],"prefix":"10.1109","author":[{"given":"Gian","family":"Carlo Cardarilli","sequence":"first","affiliation":[{"name":"University of Rome “Tor Vergata”,Department of Electronic Engineering,Rome,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luca","family":"Di Nunzio","sequence":"additional","affiliation":[{"name":"University of Rome “Tor Vergata”,Department of Electronic Engineering,Rome,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rocco","family":"Fazzolari","sequence":"additional","affiliation":[{"name":"University of Rome “Tor Vergata”,Department of Electronic Engineering,Rome,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniele","family":"Giardino","sequence":"additional","affiliation":[{"name":"University of Rome “Tor Vergata”,Department of Electronic Engineering,Rome,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dario","family":"Natale","sequence":"additional","affiliation":[{"name":"University of Rome “Tor Vergata”,Department of Electronic Engineering,Rome,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marco","family":"Re","sequence":"additional","affiliation":[{"name":"University of Rome “Tor Vergata”,Department of Electronic Engineering,Rome,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sergio","family":"Spano","sequence":"additional","affiliation":[{"name":"University of Rome “Tor Vergata”,Department of Electronic Engineering,Rome,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3063147"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TENCON50793.2020.9293918"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ISVLSI.2017.127"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-94691-7"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2885950"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2961174"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW50202.2020.00024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF51394.2020.9443368"},{"key":"ref19","article-title":"Relaccs: A multi-level approach to accelerator design for reinforcement learning on fpga-based systems","author":"baranwal","year":"2020","journal-title":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2016.2570255"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2012.2227719"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2015.2420792"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2759728"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2938390"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2522401"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197552"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2010.2043968"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3453688.3461533"},{"key":"ref21","first-page":"267","article-title":"An action-selection policy generator for reinforcement learning hardware accelerators","author":"cardarilli","year":"2020","journal-title":"International Conference on Applications in Electronics Pervading Industry Environment and Society"}],"event":{"name":"2021 55th Asilomar Conference on Signals, Systems, and Computers","start":{"date-parts":[[2021,10,31]]},"location":"Pacific Grove, CA, USA","end":{"date-parts":[[2021,11,3]]}},"container-title":["2021 55th Asilomar Conference on Signals, Systems, and Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9723034\/9723086\/09723147.pdf?arnumber=9723147","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,20]],"date-time":"2022-06-20T21:20:08Z","timestamp":1655760008000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9723147\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,31]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/ieeeconf53345.2021.9723147","relation":{},"subject":[],"published":{"date-parts":[[2021,10,31]]}}}