{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T12:15:45Z","timestamp":1771330545749,"version":"3.50.1"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/iscas.2019.8702229","type":"proceedings-article","created":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T21:02:28Z","timestamp":1556744548000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Preliminary Results Towards Reinforcement Learning with Mixed-Signal Memristive Neuromorphic Circuits"],"prefix":"10.1109","author":[{"given":"Nan","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adrien F.","family":"Vincent","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dmitri","family":"Strukov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-018-04482-4"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/nature14441"},{"key":"ref12","first-page":"5279","article-title":"Scalable trust-region method for deep reinforcement learning using kronecker-factored approximation","author":"wu","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref13","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015"},{"key":"ref14","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref15","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref16","article-title":"Design of a hybrid robot control system using memristor-model and ant-inspired based information transfer protocols","author":"gale","year":"2014"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.7551\/978-0-262-33027-5-ch025"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2463209.2488887"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574705002596"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/WISP.2015.7139171"},{"key":"ref4","article-title":"3d simulation for robot arm control with deep q-learning","author":"james","year":"2016"},{"key":"ref27","first-page":"450","article-title":"A hardware random number generator","author":"tkacik","year":"2002","journal-title":"International Workshop on Cryptographic Hardware and Embedded Systems"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref29","article-title":"Parameter space noise for exploration","author":"plappert","year":"2017"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref8","first-page":"13","volume":"8","author":"yang","year":"2013","journal-title":"Memristive devices for computing"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2296777"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref20","year":"2011","journal-title":"Quarc instructor workbook inverted pendulum experiment for matlab\/simulink users"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313077"},{"key":"ref21","year":"2009","journal-title":"SRV02 User Manual"},{"key":"ref24","author":"sutton","year":"1984","journal-title":"Temporal credit assignment in reinforcement learning"},{"key":"ref23","first-page":"278","article-title":"An analysis of actor\/critic algorithms using eligibility traces: Reinforcement learning with imperfect value function","author":"kimura","year":"1998","journal-title":"Proceedings of the Fifteenth International Conference on Machine Learning"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-934613-41-5.50014-3"}],"event":{"name":"2019 IEEE International Symposium on Circuits and Systems (ISCAS)","location":"Sapporo, Japan","start":{"date-parts":[[2019,5,26]]},"end":{"date-parts":[[2019,5,29]]}},"container-title":["2019 IEEE International Symposium on Circuits and Systems (ISCAS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8682239\/8702066\/08702229.pdf?arnumber=8702229","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:08:18Z","timestamp":1657854498000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8702229\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/iscas.2019.8702229","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}