{"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":1781354871766,"version":"3.54.1"},"reference-count":24,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"JSPS KAKENHI","award":["JP21H03522"],"award-info":[{"award-number":["JP21H03522"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2021,10]]},"DOI":"10.1109\/lra.2021.3111416","type":"journal-article","created":{"date-parts":[[2021,9,9]],"date-time":"2021-09-09T19:55:05Z","timestamp":1631217305000},"page":"8545-8552","source":"Crossref","is-referenced-by-count":9,"title":["Binarized P-Network: Deep Reinforcement Learning of Robot Control from Raw Images on FPGA"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3358-9520","authenticated-orcid":false,"given":"Yuki","family":"Kadokawa","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yoshihisa","family":"Tsurumine","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3545-4814","authenticated-orcid":false,"given":"Takamitsu","family":"Matsubara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/OJCAS.2020.3043737"},{"key":"ref11","first-page":"2995","article-title":"Theoretical analysis of efficiency and robustness of softmax and gap-increasing operators in reinforcement learning","author":"kozuno","year":"2019","journal-title":"Proc 22nd Int Conf Artif Intell Statist"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3039902.3039915"},{"key":"ref13","article-title":"An FPGA-Based on-device reinforcement learning approach using online sequential learning","author":"watanabe","year":"0"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2018.8445099"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/RTCSA.2019.8864571"},{"key":"ref16","first-page":"3207","article-title":"Dynamic policy programming","volume":"13","author":"azar","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2018.11.004"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2017.95"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794472"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593522"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021744"},{"key":"ref7","first-page":"4107","article-title":"Binarized neural networks","volume":"29","author":"hubara","year":"2016","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref2","first-page":"42","article-title":"Hexapod robot navigation using FPGA based controller","author":"banjanovic-mehmedovic","year":"2019","journal-title":"Proc Int Conf “New Technol Develop Appl"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353931"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989615"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.06.110"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304058"},{"key":"ref21","first-page":"1045","article-title":"Direct feedback alignment provides learning in deep neural networks","author":"n\u00f8kland","year":"2016","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref24","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3425500"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9475905\/09534708.pdf?arnumber=9534708","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:54:10Z","timestamp":1652194450000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9534708\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10]]},"references-count":24,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/lra.2021.3111416","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10]]}}}