{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T16:46:34Z","timestamp":1785602794518,"version":"3.56.0"},"reference-count":41,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61300101"],"award-info":[{"award-number":["61300101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project of the Ministry of Science and Technology of China","doi-asserted-by":"crossref","award":["2014ZX07405002"],"award-info":[{"award-number":["2014ZX07405002"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"crossref"}]},{"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"}]},{"name":"Key Research and Development Program of Jiangsu Province","award":["BE2017035"],"award-info":[{"award-number":["BE2017035"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2933492","type":"journal-article","created":{"date-parts":[[2019,8,6]],"date-time":"2019-08-06T16:02:25Z","timestamp":1565107345000},"page":"109544-109554","source":"Crossref","is-referenced-by-count":48,"title":["Crowd Navigation in an Unknown and Dynamic Environment Based on Deep Reinforcement Learning"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7838-9410","authenticated-orcid":false,"given":"Libo","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinfeng","family":"Zhai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhu","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1889","article-title":"Trust region policy optimization","volume":"37","author":"schulman","year":"2015","journal-title":"Proceedings of the 32nd Intl Conf on Machine Learning"},{"key":"ref38","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref33","article-title":"Learning to reinforcement learn","author":"wang","year":"2016","journal-title":"arXiv 1611 05763"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref31","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v31i3.2303"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2008.4543489"},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.1145\/3072959.3073602","article-title":"DeepLoco: Dynamic locomotion skills using hierarchical deep reinforcement learning","volume":"36","author":"peng","year":"2017","journal-title":"ACM Trans Graph"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3274247.3274510"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1002\/cav.1572"},{"key":"ref40","first-page":"267","article-title":"Approximately optimal approximate reinforcement learning","volume":"2","author":"kakade","year":"2002","journal-title":"Proc ICML"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1002\/cav.403"},{"key":"ref12","first-page":"194","article-title":"A navigation graph for real-time crowd animation on multilayered and uneven Terrain","author":"pettre","year":"2005","journal-title":"Proc 1st Int Workshop Crowd Simulation"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1073368.1073410"},{"key":"ref14","first-page":"362","article-title":"Better group behaviors in complex environments using global","volume":"8","author":"bayazit","year":"2003","journal-title":"Artif Life"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-25090-3_29"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-25090-3_28"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22180-9_49"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/VR.2007.352468"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2485895.2485909"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/2945.928167"},{"key":"ref27","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":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/37402.37406"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1661412.1618468"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(01)00129-1"},{"key":"ref5","first-page":"362","article-title":"Better group behaviors in complex environments using global roadmaps","author":"bayazit","year":"2002","journal-title":"Proc 8th Int Conf Artif Life"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12472"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1315184.1315201"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1028523.1028553"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-004-0265-z"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"487","DOI":"10.1038\/35035023","article-title":"Simulating dynamical features of escape panic","volume":"407","author":"helbing","year":"2000","journal-title":"Nature"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2002.1014237"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-21996-7_12"},{"key":"ref21","first-page":"54","article-title":"Multi-agent reinforcement learning for simulating pedestrian navigation","author":"martinez-gil","year":"2011","journal-title":"Proc Int Workshop Adapt Learn Agents"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICInfA.2015.7279322"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1177\/027836499801700706"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5772\/10528"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509772"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08789446.pdf?arnumber=8789446","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:31:54Z","timestamp":1641987114000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8789446\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2933492","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]}}}