{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T17:26:07Z","timestamp":1785432367359,"version":"3.56.0"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61921004"],"award-info":[{"award-number":["61921004"]}],"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":["U1713209"],"award-info":[{"award-number":["U1713209"]}],"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":["61942301"],"award-info":[{"award-number":["61942301"]}],"id":[{"id":"10.13039\/501100001809","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":[[2021,8]]},"DOI":"10.1109\/tnnls.2020.3015767","type":"journal-article","created":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T20:38:16Z","timestamp":1598301496000},"page":"3578-3587","source":"Crossref","is-referenced-by-count":34,"title":["A Parallel Framework of Adaptive Dynamic Programming Algorithm With Off-Policy Learning"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9269-334X","authenticated-orcid":false,"given":"Changyin","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuewen","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-015-5462-z"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2016.12.009"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2012.02.005"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/72.914523"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2771459"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2281663"},{"key":"ref37","article-title":"Nonzero-sum game reinforcement learning for performance optimization in large-scale industrial processes","author":"li","year":"2019","journal-title":"IEEE Trans Cybern"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2016.2537984"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2586303"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2541020"},{"key":"ref10","first-page":"-387i","article-title":"Deterministic policy gradient algorithms","volume":"32","author":"silver","year":"2014","journal-title":"Proc ICLR"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2542923"},{"key":"ref11","first-page":"1","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc ICLR"},{"key":"ref12","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc ICML"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref14","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"Proc ICML"},{"key":"ref15","article-title":"Benchmarking reinforcement learning algorithms on real-world robots","author":"mahmood","year":"2018","journal-title":"arXiv 1809 07731"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2006.878720"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2755501"},{"key":"ref4","article-title":"Deep reinforcement learning: An overview","author":"li","year":"2017","journal-title":"arXiv 1701 07274"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2790260"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref6","first-page":"2939","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"Proc ICML"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2002.801727"},{"key":"ref5","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"},{"key":"ref8","article-title":"Prioritized experience replay","author":"schaul","year":"2015","journal-title":"arXiv 1511 05952"},{"key":"ref7","first-page":"3215","article-title":"Rainbow: Combining improvements in deep reinforcement learning","author":"hessel","year":"2018","journal-title":"Proc AAAI"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14540"},{"key":"ref9","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref20","author":"bertsekas","year":"1996","journal-title":"Neuro-Dynamic Programming"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2009.933854"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2712188"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2623859"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.926614"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2861945"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/72.623201"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511627040"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2013.12.038"},{"key":"ref43","author":"bellamn","year":"1957","journal-title":"Dynamic Programming"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2014.12.066"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9505270\/09174778.pdf?arnumber=9174778","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:04Z","timestamp":1652194384000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9174778\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8]]},"references-count":44,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2020.3015767","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8]]}}}