{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T11:56:11Z","timestamp":1777982171745,"version":"3.51.4"},"reference-count":41,"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.2021.3068952","type":"journal-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T19:58:14Z","timestamp":1616702294000},"page":"4552-4559","source":"Crossref","is-referenced-by-count":157,"title":["Decentralized Multi-Agent Pursuit Using Deep Reinforcement Learning"],"prefix":"10.1109","volume":"6","author":[{"given":"Cristino","family":"de Souza","sequence":"first","affiliation":[]},{"given":"Rhys","family":"Newbury","sequence":"additional","affiliation":[]},{"given":"Akansel","family":"Cosgun","sequence":"additional","affiliation":[]},{"given":"Pedro","family":"Castillo","sequence":"additional","affiliation":[]},{"given":"Boris","family":"Vidolov","sequence":"additional","affiliation":[]},{"given":"Dana","family":"Kuli","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2016.2645516"},{"key":"ref38","article-title":"Graph neural networks: A review of methods and applications","author":"zhou","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref32","first-page":"3391","article-title":"Deep sets","author":"zaheer","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","first-page":"1311","article-title":"Automated curriculum learning for neural networks","author":"graves","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","article-title":"Guided curriculum learning for walking over complex terrain","author":"tidd","year":"2020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICUAS.2018.8453335"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.1494"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IECON.2017.8217089"},{"key":"ref34","first-page":"445","article-title":"Cooperative hunting in lions: the role of the individual","volume":"29","author":"stander","year":"2004","journal-title":"Behav Ecol Sociobiol"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917306"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2016.05.007"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-011-9241-4"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1533\/9781782420590"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-1731-0"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2011.6161237"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.beproc.2011.09.006"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.75.1226"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2005.864190"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2971938"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1002\/acs.1249"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref4","first-page":"6382","article-title":"Multi-Agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2018.00138"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.109.118104"},{"key":"ref6","first-page":"1","article-title":"Deep reinforcement learning for swarm systems","volume":"20","author":"h\u00fcttenrauch","year":"2019","journal-title":"J Mach Learn Res"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/671"},{"key":"ref5","first-page":"66","article-title":"Cooperative multi-agent control using deep reinforcement learning","author":"gupta","year":"0","journal-title":"Proc Auton Agents Multiagent Syst"},{"key":"ref8","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"0"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-32-9682-4_69"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICInfA.2015.7279288"},{"key":"ref9","first-page":"734","article-title":"Sim-to-real reinforcement learning for deformable object manipulation","author":"matas","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/aa69e7"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/5326.704563"},{"key":"ref22","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"0","journal-title":"Proc Int Conf Learn Representations (ICLR)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CCECE.2015.7129412"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-016-0423-3"},{"key":"ref41","article-title":"Emergent tool use from multi-agent autocurricula","author":"baker","year":"0","journal-title":"Proc Int Conf Learn Representations (ICLR)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref26","article-title":"UAV pursuit using reinforcement learning","author":"bonnet","year":"0","journal-title":"Proc Unmanned Syst Technol"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2018.00138"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9399748\/09387125.pdf?arnumber=9387125","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:54:05Z","timestamp":1652194445000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9387125\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7]]},"references-count":41,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2021.3068952","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7]]}}}