{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T14:27:44Z","timestamp":1785335264102,"version":"3.55.0"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2018,6,1]],"date-time":"2018-06-01T00:00:00Z","timestamp":1527811200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"crossref","award":["2016YFD0702100"],"award-info":[{"award-number":["2016YFD0702100"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["71671086"],"award-info":[{"award-number":["71671086"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61432008"],"award-info":[{"award-number":["61432008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["71732003"],"award-info":[{"award-number":["71732003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP130101658"],"award-info":[{"award-number":["DP130101658"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2018,6]]},"DOI":"10.1109\/tnnls.2018.2790981","type":"journal-article","created":{"date-parts":[[2018,2,1]],"date-time":"2018-02-01T19:15:41Z","timestamp":1517512541000},"page":"2216-2226","source":"Crossref","is-referenced-by-count":111,"title":["Self-Paced Prioritized Curriculum Learning With Coverage Penalty in Deep Reinforcement Learning"],"prefix":"10.1109","volume":"29","author":[{"given":"Zhipeng","family":"Ren","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7425-3559","authenticated-orcid":false,"given":"Daoyi","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0395-1525","authenticated-orcid":false,"given":"Huaxiong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3929-4707","authenticated-orcid":false,"given":"Chunlin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1008"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1096"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1102"},{"key":"ref30","first-page":"3196","article-title":"Self-paced learning for matrix factorization","author":"zhao","year":"2015","journal-title":"Proc AAAI"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref35","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"Proc ICML"},{"key":"ref34","first-page":"2094","article-title":"Deep reinforcement learning with double Q-learning","author":"van hasselt","year":"2016","journal-title":"Proc AAAI"},{"key":"ref28","first-page":"2694","article-title":"Self-paced curriculum learning","author":"jiang","year":"2015","journal-title":"Proc AAAI"},{"key":"ref27","first-page":"2078","article-title":"Self-paced learning with diversity","author":"jiang","year":"2014","journal-title":"Proc Adv NIPS"},{"key":"ref29","author":"meng","year":"2015","journal-title":"What objective does self-paced learning indeed optimize?"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14540"},{"key":"ref1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","author":"schaul","year":"2016","journal-title":"Prioritized experience replay"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref21","author":"hagan","year":"1996","journal-title":"Neural Network Design"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2563981"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2017.8081267"},{"key":"ref26","first-page":"1189","article-title":"Self-paced learning for latent variable models","author":"kumar","year":"2010","journal-title":"Proc Adv NIPS"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2014.11.004"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2011.6037324"},{"key":"ref11","first-page":"75","article-title":"Neural network based model reference adaptive control for ship steering system","volume":"11","author":"cheng","year":"2005","journal-title":"Int J Inf Technol"},{"key":"ref40","author":"kumar","year":"2015","journal-title":"Ask me anything Dynamic memory networks for natural language processing"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2012.6252823"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"621","DOI":"10.1109\/TNNLS.2013.2281663","article-title":"Policy iteration adaptive dynamic programming algorithm for discrete-time nonlinear systems","volume":"25","author":"liu","year":"2014","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref14","author":"mnih","year":"2013","journal-title":"Playing atari with deep reinforcement learning"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993104"},{"key":"ref18","first-page":"1001","article-title":"Generalized prioritized sweeping","author":"andre","year":"1998","journal-title":"Proc Adv NIPS"},{"key":"ref19","first-page":"82","article-title":"Structured prioritized sweeping","author":"dearden","year":"2001","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.231"},{"key":"ref3","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv NIPS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2307532"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2496947"},{"key":"ref7","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc Adv NIPS"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2371046"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2010.5596468"},{"key":"ref46","author":"wu","year":"2016","journal-title":"Google’s neural machine translation system Bridging the gap between human and machine translation"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-13823-7_31"},{"key":"ref48","author":"lillicrap","year":"2015","journal-title":"Continuous control with deep reinforcement learning"},{"key":"ref47","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1613\/jair.3912","article-title":"The arcade learning environment: An evaluation platform for general agents","volume":"47","author":"bellemare","year":"2013","journal-title":"J Artif Intell Res"},{"key":"ref42","first-page":"1","article-title":"The importance of experience replay database composition in deep reinforcement learning","author":"de bruin","year":"2015","journal-title":"Proc NIPS Workshop Deep Rein Learn"},{"key":"ref41","doi-asserted-by":"crossref","DOI":"10.4324\/9781315636863","author":"reilly","year":"2016","journal-title":"Connectionist Approaches to Natural Language Processing"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102352"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(02)00056-4"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/8360119\/08278851.pdf?arnumber=8278851","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:12:34Z","timestamp":1642003954000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8278851\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6]]},"references-count":49,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2018.2790981","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,6]]}}}