{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T09:57:16Z","timestamp":1772272636262,"version":"3.50.1"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Science and Technology Major Project of the Ministry of Science and Technology of China","award":["2014ZX07405002"],"award-info":[{"award-number":["2014ZX07405002"]}]},{"name":"Key R&D Program of Jiangsu Province","award":["BE2017035"],"award-info":[{"award-number":["BE2017035"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["2242019k30043"],"award-info":[{"award-number":["2242019k30043"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2927606","type":"journal-article","created":{"date-parts":[[2019,7,9]],"date-time":"2019-07-09T20:13:32Z","timestamp":1562703212000},"page":"92465-92475","source":"Crossref","is-referenced-by-count":19,"title":["Terrain Adaptive Walking of Biped Neuromuscular Virtual Human Using Deep Reinforcement Learning"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9716-1809","authenticated-orcid":false,"given":"Jianpeng","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhu","family":"Qin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7838-9410","authenticated-orcid":false,"given":"Libo","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630868"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1113\/jphysiol.1990.sp018046"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s00221-001-0978-4"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1111\/j.1469-7793.2001.00925.x"},{"key":"ref37","first-page":"7463","article-title":"Generalization of a muscle-reflex control model to 3d walking","author":"song","year":"2013","journal-title":"Proc 35th Annu Int Conf IEEE Eng Med Biol Soc (EMBC)"},{"key":"ref36","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref35","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref34","article-title":"Energy consumption optimization and stumbling corrective response for bipedal walking gait","author":"berger","year":"2011"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2012.6490977"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2508363.2508399"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.072"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1098\/rspb.1938.0050","article-title":"The heat of shortening and the dynamic constants of muscle","volume":"126","author":"hill","year":"1938","journal-title":"Proc R Soc Lond B Biol Sci"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/10.102791"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbiomech.2008.01.002"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.brainresrev.2007.08.004"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(11)60547-3"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780198524052.001.0001"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1098\/rspb.2003.2454"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925881"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1113\/JP270228"},{"key":"ref27","first-page":"2944","article-title":"Learning continuous control policies by stochastic value gradients","author":"heess","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2010.2047592"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073602"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/1618452.1618514"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2335376"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1276377.1276509"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2012.03189.x"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2018.00039"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2893476"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2015.2472533"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/S1672-6529(11)60115-7"},{"key":"ref22","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389841"},{"key":"ref24","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2766910"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref25","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 Process Syst"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08758114.pdf?arnumber=8758114","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,10]],"date-time":"2021-08-10T19:40:36Z","timestamp":1628624436000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8758114\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2927606","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]}}}