{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:22:25Z","timestamp":1780053745730,"version":"3.54.0"},"reference-count":40,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772532"],"award-info":[{"award-number":["61772532"]}],"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":["61472424"],"award-info":[{"award-number":["61472424"]}],"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":["51607180"],"award-info":[{"award-number":["51607180"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20150203"],"award-info":[{"award-number":["BK20150203"]}],"id":[{"id":"10.13039\/501100004608","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.2018.2806087","type":"journal-article","created":{"date-parts":[[2018,3,9]],"date-time":"2018-03-09T19:16:31Z","timestamp":1520622991000},"page":"2227-2238","source":"Crossref","is-referenced-by-count":93,"title":["Multisource Transfer Double DQN Based on Actor Learning"],"prefix":"10.1109","volume":"29","author":[{"given":"Jie","family":"Pan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5327-1088","authenticated-orcid":false,"given":"Xuesong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2022-9999","authenticated-orcid":false,"given":"Yuhu","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2009.07.008"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2586303"},{"key":"ref33","first-page":"383","article-title":"Reinforcement learning transfer via sparse coding","author":"ammar","year":"2012","journal-title":"Proc 11th Int Conf Auton Agents Multiagent Syst"},{"key":"ref32","first-page":"880","article-title":"Value functions for RL-based behavior transfer: A comparative study","author":"taylor","year":"2005","journal-title":"Proc Nat Conf Artif Intell"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1329125.1329248"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390225"},{"key":"ref37","first-page":"249","article-title":"Transfer learning in multi-agent reinforcement learning domains","author":"boutsioukis","year":"2011","journal-title":"Proc Lect Notes Comput Sci"},{"key":"ref36","first-page":"3982","article-title":"Transfer learning for multiagent reinforcement learning systems","author":"da silva","year":"2016","journal-title":"Proc Int Joint Conf Artif Intell IJCAI"},{"key":"ref35","first-page":"88","article-title":"Learning relational options for inductive transfer in relational reinforcement learning","author":"croonenborghs","year":"2007","journal-title":"Proc Lect Notes Comput Sci"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152553"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2522401"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2472457"},{"key":"ref11","first-page":"198","article-title":"A control strategy of autonomous vehicles based on deep reinforcement learning","author":"xia","year":"2017","journal-title":"Proc Euro-Int Symp Comput Intell"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1001"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925881"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54042-9_56"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1153"},{"key":"ref16","first-page":"109","author":"cuay\u00e1huitl","year":"2016","journal-title":"SimpleDS A simple deep reinforcement learning dialogue system"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2505084"},{"key":"ref18","author":"ong","year":"2015","journal-title":"Distributed Deep Q-Learning"},{"key":"ref19","article-title":"Accelerating search with transferred heuristics","author":"taylor","year":"2007","journal-title":"Proc ICAPS Workshop AI Planning Learn"},{"key":"ref28","first-page":"1804","article-title":"Opponent modeling in deep reinforcement learning","author":"he","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref27","first-page":"2939","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2609500"},{"key":"ref6","author":"hansen","year":"2016","journal-title":"Using deep Q-learning to control optimization hyperparameters"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23957-1_19"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2561300"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2016.7508798"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MVA.2015.7153249"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2543000"},{"key":"ref9","first-page":"1362","article-title":"Automatic bridge bidding using deep reinforcement learning","author":"yeh","year":"2016","journal-title":"Proc 22nd Conf Artif Intell"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2371046"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/11564096_32"},{"key":"ref22","first-page":"2094","article-title":"Deep reinforcement learning with double Q-learning","author":"hasselt","year":"2016","journal-title":"Proc 30th AAAI Conf Artif Intell"},{"key":"ref21","first-page":"3338","article-title":"Deep learning for real-time Atari game play using offline Monte-Carlo tree search planning","author":"guo","year":"2014","journal-title":"Proc Adv Neural Inf Proces Syst"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2488680"},{"key":"ref23","author":"schulman","year":"2015","journal-title":"High-dimensional continuous control using generalized advantage estimation"},{"key":"ref26","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2014.2348991"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/8360119\/08310951.pdf?arnumber=8310951","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\/8310951\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6]]},"references-count":40,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2018.2806087","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,6]]}}}