{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T02:25:05Z","timestamp":1793327105329,"version":"4.5.0"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["ACI-1445606"],"award-info":[{"award-number":["ACI-1445606"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CMU Manufacturing Futures Initiative"},{"DOI":"10.13039\/100000915","name":"Richard King Mellon Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000915","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1409987"],"award-info":[{"award-number":["1409987"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1724392"],"award-info":[{"award-number":["1724392"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1817189"],"award-info":[{"award-number":["1817189"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1837779"],"award-info":[{"award-number":["1837779"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["ACI-1445606"],"award-info":[{"award-number":["ACI-1445606"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2019,7]]},"DOI":"10.1109\/lra.2019.2903261","type":"journal-article","created":{"date-parts":[[2019,3,6]],"date-time":"2019-03-06T15:30:37Z","timestamp":1551886237000},"page":"2378-2385","source":"Crossref","is-referenced-by-count":394,"title":["PRIMAL: Pathfinding via Reinforcement and Imitation Multi-Agent Learning"],"prefix":"10.1109","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7579-9916","authenticated-orcid":false,"given":"Guillaume","family":"Sartoretti","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0536-4853","authenticated-orcid":false,"given":"Justin","family":"Kerr","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunfei","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Glenn","family":"Wagner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"T. K. Satish","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sven","family":"Koenig","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5434-7945","authenticated-orcid":false,"given":"Howie","family":"Choset","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"vecer\u00edk","year":"2017"},{"key":"ref38","article-title":"Reinforcement learning from imperfect demonstrations","author":"gao","year":"2018"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref32","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref31","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"0","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref30","article-title":"Prioritized experience replay","author":"schaul","year":"2015"},{"key":"ref37","article-title":"Learning complex dexterous manipulation with deep reinforcement learning and demonstrations","author":"rajeswaran","year":"2017"},{"key":"ref36","article-title":"Overcoming exploration in reinforcement learning with demonstrations","author":"nair","year":"2017"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CSSE.2008.920"},{"key":"ref34","article-title":"Reinforcement learning through asynchronous advantage actor-critic on a GPU","author":"babaeizadeh","year":"2016"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989037"},{"key":"ref40","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"0","journal-title":"Proc 14th Int Conf Artif Intell Statist"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05816-6_3"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460802"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref14","article-title":"Searching with consistent prioritization for multi-agent path finding","author":"ma","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546877"},{"key":"ref16","first-page":"1118","article-title":"Multiple path coordination for mobile robots: A geometric algorithm","author":"leroy","year":"0","journal-title":"Proc 16th Int Joint Conf Artif Intell"},{"key":"ref17","first-page":"3166","article-title":"Multi-agent path finding with payload transfers and the package-exchange robot-routing problem","author":"ma","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref18","first-page":"3822","article-title":"Asynchronous decentralized prioritized planning for coordination in multi-robot system","author":"c\u00e1p","year":"0","journal-title":"Proc IEEE\/RSJ Int Conf Intell Robots Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/BF01840371"},{"key":"ref28","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","author":"foerster","year":"0","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref4","first-page":"19","article-title":"Suboptimal variants of the conflict-based search algorithm for the multi-agent pathfinding problem","author":"barer","year":"0","journal-title":"the 7th Annual Symposium on Combinatorial Search"},{"key":"ref27","article-title":"Counterfactual multi-agent policy gradients","author":"foerster","year":"2017"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2014.11.001"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-011-9265-9"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32723-0_24"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19457-3_1"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.2514\/6.2007-6553"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-73424-6_2"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364906065378"},{"key":"ref9","first-page":"55","article-title":"MAPP: A scalable multi-agent path planning algorithm with tractability and completeness guarantees","volume":"42","author":"wang","year":"2011","journal-title":"J Artif Intell Res"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/science.1254295"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2002.1014852"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6631119"},{"key":"ref21","first-page":"563","article-title":"Conflict-based search for optimal multi-agent path finding","author":"sharon","year":"0","journal-title":"Proc 26th AAAI Conf Artif Intell"},{"key":"ref42","article-title":"Incorporating Nesterov momentum into Adam","author":"dozat","year":"2016"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14435-6_7"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/1329125.1329407"},{"key":"ref23","first-page":"173","article-title":"Finding optimal solutions to cooperative pathfinding problems","author":"standley","year":"0","journal-title":"Proc 24th AAAI Conf Artif Intell"},{"key":"ref26","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"0","journal-title":"Proc 31st Conf Neural Inf Process Syst"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2792745.2792775"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielaam\/7083369\/8668830\/8661608-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/8668830\/08661608.pdf?arnumber=8661608","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T17:13:50Z","timestamp":1657732430000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8661608\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":43,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2019.2903261","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,7]]}}}