{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T21:10:57Z","timestamp":1729631457622,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,6,8]],"date-time":"2022-06-08T00:00:00Z","timestamp":1654646400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,8]],"date-time":"2022-06-08T00:00:00Z","timestamp":1654646400000},"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":[[2022,6,8]]},"DOI":"10.23919\/acc53348.2022.9867386","type":"proceedings-article","created":{"date-parts":[[2022,9,5]],"date-time":"2022-09-05T20:24:10Z","timestamp":1662409450000},"page":"3406-3411","source":"Crossref","is-referenced-by-count":2,"title":["Multi-Agent Stochastic Control using Path Integral Policy Improvement"],"prefix":"10.23919","author":[{"given":"Peter","family":"Varnai","sequence":"first","affiliation":[{"name":"KTH Royal Institute of Technology,Division of Decision and Control Systems, School of Electrical Engineering and Computer Science,Stockholm,Sweden,114 28"}]},{"given":"Dimos V.","family":"Dimarogonas","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology,Division of Decision and Control Systems, School of Electrical Engineering and Computer Science,Stockholm,Sweden,114 28"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759306"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989384"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2955699"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9304312"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1609\/icaps.v26i1.13789","article-title":"Real-time stochastic optimal control for multi-agent quadrotor systems","author":"g\u00f3mez","year":"2016","journal-title":"Twenty-Sixth International Conference on Automated Planning and Scheduling"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1613\/jair.2473","article-title":"Graphical model inference in optimal control of stochastic multi-agent systems","volume":"32","author":"van den broek","year":"2008","journal-title":"Journal of Artificial Intelligence Research"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9482942"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.23919\/ACC53348.2022.9867386"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1080\/14697688.2019.1575974"},{"key":"ref19","first-page":"564","article-title":"Information-geometric optimization algorithms: A unifying picture via invariance principles","volume":"18","author":"ollivier","year":"2017","journal-title":"J Machine Learning Research (JMLR)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2021.3137133"},{"key":"ref3","first-page":"3137","article-title":"A generalized path integral control approach to reinforcement learning","volume":"11","author":"theodorou","year":"2010","journal-title":"Journal of Machine Learning Research (JMLR)"},{"key":"ref6","first-page":"1547","article-title":"Path integral policy improvement with covariance matrix adaptation","author":"stulp","year":"2012","journal-title":"Proc of the International Conference on Machine Learning (ICML)"},{"key":"ref5","article-title":"Path integral policy improvement: an information-geometric approach","author":"varnai","year":"0","journal-title":"Journal of Machine Learning Research (JMLR)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2983923"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2547979"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1515\/9781400835355"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487277"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2019.04.008"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2017.8264561"}],"event":{"name":"2022 American Control Conference (ACC)","start":{"date-parts":[[2022,6,8]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2022,6,10]]}},"container-title":["2022 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9866948\/9867142\/09867386.pdf?arnumber=9867386","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T07:21:54Z","timestamp":1727940114000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9867386\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,8]]},"references-count":21,"URL":"https:\/\/doi.org\/10.23919\/acc53348.2022.9867386","relation":{},"subject":[],"published":{"date-parts":[[2022,6,8]]}}}