{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T23:27:10Z","timestamp":1770334030151,"version":"3.49.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"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":[[2019,7]]},"DOI":"10.1109\/spawc.2019.8815546","type":"proceedings-article","created":{"date-parts":[[2019,8,29]],"date-time":"2019-08-29T20:41:47Z","timestamp":1567111307000},"page":"1-5","source":"Crossref","is-referenced-by-count":13,"title":["Learning First-to-Spike Policies for Neuromorphic Control Using Policy Gradients"],"prefix":"10.1109","author":[{"given":"Bleema","family":"Rosenfeld","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, New Jersey Institute of Technology, Newark, NJ, 07102, USA"}]},{"given":"Osvaldo","family":"Simeone","sequence":"additional","affiliation":[{"name":"Department of Informatics, King's College London, Centre for Telecommunications Research, London, WC2R 2LS, UK"}]},{"given":"Bipin","family":"Rajendran","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, New Jersey Institute of Technology, Newark, NJ, 07102, USA"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2016.2595580"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0115620"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460482"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2015.7280696"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2007.19.6.1468"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966242"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1000586"},{"key":"ref17","article-title":"Training probabilistic spiking neural networks with first-to-spike decoding","author":"bagheri","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref18","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref19","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"ArXiv Preprint"},{"key":"ref4","article-title":"Machine learning for wireless networks with artificial intelligence: A tutorial on neural networks","author":"chen","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2018.112130359"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1523\/ENEURO.0301-17.2018"},{"key":"ref5","first-page":"136","article-title":"Variational learning for recurrent spiking networks","author":"danilo","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511815706"},{"key":"ref7","article-title":"Hybrid macro\/micro level backpropagation for training deep spiking neural networks","author":"jin","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"668","DOI":"10.1126\/science.1254642","article-title":"A million spiking-neuron integrated circuit with a scalable communication network and interface","volume":"345","author":"merolla","year":"2014","journal-title":"Science"},{"key":"ref1","article-title":"Human-level performance in first-person multi-player games with population-based deep reinforcement learning","author":"jaderberg","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.3305-05.2005"},{"key":"ref20","article-title":"Reinforcement learning for robots using neural networks","author":"lin","year":"1993","journal-title":"Carnegie Mellon University"}],"event":{"name":"2019 IEEE 20th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC)","location":"Cannes, France","start":{"date-parts":[[2019,7,2]]},"end":{"date-parts":[[2019,7,5]]}},"container-title":["2019 IEEE 20th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8790959\/8815388\/08815546.pdf?arnumber=8815546","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:39:37Z","timestamp":1755909577000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8815546\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/spawc.2019.8815546","relation":{},"subject":[],"published":{"date-parts":[[2019,7]]}}}