{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T08:27:22Z","timestamp":1758961642505,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,31]],"date-time":"2023-05-31T00:00:00Z","timestamp":1685491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,31]],"date-time":"2023-05-31T00:00:00Z","timestamp":1685491200000},"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":[],"published-print":{"date-parts":[[2023,5,31]]},"DOI":"10.23919\/acc55779.2023.10156236","type":"proceedings-article","created":{"date-parts":[[2023,7,3]],"date-time":"2023-07-03T17:48:03Z","timestamp":1688406483000},"page":"78-83","source":"Crossref","is-referenced-by-count":3,"title":["Federated reinforcement learning for generalizable motion planning"],"prefix":"10.23919","author":[{"given":"Zhenyuan","family":"Yuan","sequence":"first","affiliation":[{"name":"Pennsylvania State University,School of Electrical Engineering and Computer Science,USA,PA 16802"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siyuan","family":"Xu","sequence":"additional","affiliation":[{"name":"Pennsylvania State University,School of Electrical Engineering and Computer Science,USA,PA 16802"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minghui","family":"Zhu","sequence":"additional","affiliation":[{"name":"Pennsylvania State University,School of Electrical Engineering and Computer Science,USA,PA 16802"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914549607"},{"key":"ref12","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"garc?a","year":"2015","journal-title":"Journal of Machine Learning Research"},{"key":"ref15","first-page":"5872","article-title":"Fully decen-tralized multi-agent reinforcement learning with networked agents","author":"zhang","year":"2018","journal-title":"Proc Int Conf Machine Learning (ICML)"},{"key":"ref14","first-page":"293","article-title":"PAC-Bayes control: Synthesizing controllers that provably generalize to novel environments","author":"majumdar","year":"2018","journal-title":"Conference on Robot Learning (CoRL)"},{"journal-title":"Deep Learning","year":"2016","author":"goodfellow","key":"ref11"},{"journal-title":"The Nature of Statistical Learning Theory","year":"2013","author":"vapnik","key":"ref10"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917712421"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546877"},{"key":"ref17","first-page":"6795","article-title":"A tutorial on distributed (non-bayesian) learning: Problem, algorithms and results","author":"nedi?","year":"2016","journal-title":"Proc IEEE Conf Decision and Control (CDC)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147886"},{"journal-title":"Federated Learning","year":"2020","author":"yang","key":"ref19"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2017.8264129"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1137\/120880811"},{"key":"ref23","article-title":"Convergence rates for the stochastic gradient descent method for non-convex objective functions","volume":"21","author":"fehrman","year":"2020","journal-title":"Journal of Machine Learning Research"},{"year":"0","key":"ref26","article-title":"Pybullet"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4939-4032-5"},{"key":"ref20","first-page":"949","article-title":"Natural evolution strategies","volume":"15","author":"wierstra","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"article-title":"Federated reinforcement learning for generalizable motion planning","year":"2022","author":"yuan","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3182\/20020721-6-ES-1901.00244"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.2514\/6.2013-4865"},{"journal-title":"Zermelo’s Navigation Problems","year":"2001","author":"zlobec","key":"ref27"},{"key":"ref8","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.769"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/machines7020024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-015-9467-7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989693"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1115\/1.4037782"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2975759"}],"event":{"name":"2023 American Control Conference (ACC)","start":{"date-parts":[[2023,5,31]]},"location":"San Diego, CA, USA","end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10155646\/10155787\/10156236.pdf?arnumber=10156236","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,3]],"date-time":"2023-07-03T20:48:39Z","timestamp":1688417319000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10156236\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,31]]},"references-count":28,"URL":"https:\/\/doi.org\/10.23919\/acc55779.2023.10156236","relation":{},"subject":[],"published":{"date-parts":[[2023,5,31]]}}}