{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T12:41:27Z","timestamp":1785156087391,"version":"3.55.0"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2021,7]]},"DOI":"10.1109\/lra.2021.3068662","type":"journal-article","created":{"date-parts":[[2021,3,24]],"date-time":"2021-03-24T19:34:37Z","timestamp":1616614477000},"page":"4616-4623","source":"Crossref","is-referenced-by-count":74,"title":["Where to go Next: Learning a Subgoal Recommendation Policy for Navigation in Dynamic Environments"],"prefix":"10.1109","volume":"6","author":[{"given":"Bruno","family":"Brito","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Everett","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan P.","family":"How","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Javier","family":"Alonso-Mora","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"0","journal-title":"Proc Int Conf Learn Repres (ICLR)"},{"key":"ref38","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-019-09829-4"},{"key":"ref32","article-title":"Exploring model-based planning with policy networks","author":"wang","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref31","article-title":"Model-based lookahead reinforcement learning","author":"hong","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2014.X.052"},{"key":"ref37","article-title":"Recurrent experience replay in distributed reinforcement learning","author":"kapturowski","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2008.4543489"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"856","DOI":"10.1177\/0278364920916531","article-title":"Fully distributed multi-robot collision avoidance via deep reinforcement learning for safe and efficient navigation in complex scenarios","volume":"39","author":"fan","year":"2020","journal-title":"Int J Robot Res"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546877"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.51.4282"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1177\/0278364918781016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3171221.3171255"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914557874"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-015-0310-2"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989199"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202312"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460968"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-090419-075625"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463154"},{"key":"ref28","first-page":"1","article-title":"Guided policy search","author":"levine","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989037"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.2007630"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759232"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3050338"},{"key":"ref29","first-page":"207","article-title":"Variational policy search via trajectory optimization","author":"levine","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794134"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-642-19457-3_1","article-title":"Reciprocal n-body collision avoidance","author":"van den","year":"2011","journal-title":"Robotics Research"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920916531"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2929976"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980408"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2016.2578706"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3024161"},{"key":"ref42","article-title":"FORCES professional","author":"domahidi","year":"2014","journal-title":"Embotech AG"},{"key":"ref24","article-title":"Plan online, learn offline: Efficient learning and exploration via model-based control","author":"lowrey","year":"2019","journal-title":"Int Conf Lear Repres"},{"key":"ref41","article-title":"Stable baselines","author":"hill","year":"2018","journal-title":"Github Repository"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2013.6614995"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2019.8795816"},{"key":"ref25","first-page":"990","article-title":"Deep value model predictive control","author":"farshidian","year":"0","journal-title":"Proc Conf Robot Learn"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9399748\/09385847.pdf?arnumber=9385847","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:54:00Z","timestamp":1652194440000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9385847\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7]]},"references-count":42,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2021.3068662","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7]]}}}