{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T18:03:16Z","timestamp":1773165796532,"version":"3.50.1"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61571413"],"award-info":[{"award-number":["61571413"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61632001"],"award-info":[{"award-number":["61632001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2021,2]]},"DOI":"10.1109\/tcyb.2019.2939174","type":"journal-article","created":{"date-parts":[[2019,12,31]],"date-time":"2019-12-31T21:04:22Z","timestamp":1577826262000},"page":"604-613","source":"Crossref","is-referenced-by-count":57,"title":["Asynchronous Episodic Deep Deterministic Policy Gradient: Toward Continuous Control in Computationally Complex Environments"],"prefix":"10.1109","volume":"51","author":[{"given":"Zhizheng","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Jiale","family":"Chen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8525-5066","authenticated-orcid":false,"given":"Zhibo","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Weiping","family":"Li","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"},{"key":"ref32","first-page":"3207","article-title":"Deep reinforcement learning that matters","author":"henderson","year":"2018","journal-title":"Proc AAAI"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.piutam.2011.04.023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2007.901024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.36.823"},{"key":"ref34","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.921000"},{"key":"ref11","article-title":"Model-free episodic control","author":"blundell","year":"2016","journal-title":"arXiv preprint arXiv 1606 04460"},{"key":"ref12","first-page":"2827","article-title":"Neural episodic control","volume":"70","author":"pritzel","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref13","first-page":"13","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"Proc ICLR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref15","first-page":"1","article-title":"Prioritized experience replay","author":"schaul","year":"2016","journal-title":"Proc ICLR"},{"key":"ref16","first-page":"5048","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","first-page":"889","article-title":"Hippocampal contributions to control: The third way","author":"lengyel","year":"2008","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/337"},{"key":"ref19","first-page":"1","article-title":"Parameter space noise for exploration","author":"plappert","year":"2018","journal-title":"Proc ICLR"},{"key":"ref28","article-title":"OpenAI gym","author":"brockman","year":"2016","journal-title":"arXiv preprint arXiv 1606 01540"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/3477.662757"},{"key":"ref27","first-page":"707","article-title":"On generating power law noise","volume":"300","author":"timmer","year":"1995","journal-title":"Astronomy Astrophys"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1007\/978-3-319-94042-7_7","article-title":"Learning to run challenge solutions: Adapting reinforcement learning methods for neuromusculoskeletal environments","author":"kidzi?ski","year":"2018","journal-title":"The NIPS’17 Competition Building Intelligent Systems"},{"key":"ref6","first-page":"1407","article-title":"IMPALA: Scalable distributed deep-RL with importance weighted actor–learner architectures","volume":"80","author":"espeholt","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref5","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref8","first-page":"1","article-title":"Distributed distributional deterministic policy gradients","author":"barth-maron","year":"2018","journal-title":"Proc ICLR"},{"key":"ref7","first-page":"1","article-title":"Distributed prioritized experience replay","author":"horgan","year":"2018","journal-title":"Proc ICLR"},{"key":"ref2","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv preprint arXiv 1509 02971"},{"key":"ref9","article-title":"Accelerated methods for deep reinforcement learning","author":"stooke","year":"2018","journal-title":"arXiv preprint arXiv 1803 02811"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"ref22","first-page":"195","article-title":"Uncertainty-driven imagination for continuous deep reinforcement learning","author":"kalweit","year":"2017","journal-title":"Proc Conf Robot Learn"},{"key":"ref21","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proc ICML"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/461"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3758\/PBR.15.1.96"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2006.03.036"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/9325889\/08946888.pdf?arnumber=8946888","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:35Z","timestamp":1652194415000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8946888\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2]]},"references-count":35,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2019.2939174","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2]]}}}