{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T14:28:46Z","timestamp":1779200926153,"version":"3.51.4"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,2,4]],"date-time":"2021-02-04T00:00:00Z","timestamp":1612396800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,2,4]],"date-time":"2021-02-04T00:00:00Z","timestamp":1612396800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,2,4]],"date-time":"2021-02-04T00:00:00Z","timestamp":1612396800000},"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":[[2021,2,4]]},"DOI":"10.1109\/icara51699.2021.9376509","type":"proceedings-article","created":{"date-parts":[[2021,3,17]],"date-time":"2021-03-17T20:24:06Z","timestamp":1616012646000},"page":"226-230","source":"Crossref","is-referenced-by-count":16,"title":["Self-Organised Swarm Flocking with Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Mehmet B.","family":"Bezcioglu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Barry","family":"Lennox","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Farshad","family":"Arvin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.58.4828"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/15\/9\/095011"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-23807-0_22"},{"key":"ref13","author":"mnih","year":"2013","journal-title":"Playing atari with deep reinforcement learning"},{"key":"ref14","author":"tavakoli","year":"2017","journal-title":"Action branching architectures for deep reinforcement learning"},{"key":"ref15","author":"van de wiele","year":"2020","journal-title":"Q-learning in enormous action spaces via amortized approximate maximization"},{"key":"ref16","author":"silver","year":"2014","journal-title":"Deterministic policy gradient algorithms"},{"key":"ref17","author":"lillicrap","year":"2015","journal-title":"Continuous control with deep reinforcement learning"},{"key":"ref18","author":"h\u00fcttenrauch","year":"2017","journal-title":"Guided Deep Reinforcement Learning for Swarm Systems[J]"},{"key":"ref19","first-page":"1","article-title":"Deep reinforcement learning for swarm systems","volume":"20","author":"h\u00fcttenrauch","year":"2019","journal-title":"Journal of Machine Learning Research"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3034800"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11721-008-0016-2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms14189"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2016.12.006"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/280811.281008"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2966412"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/1059712316632851"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2020.100762"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.75.1226"},{"key":"ref20","article-title":"Inverse reinforcement learning of bird flocking behavior","author":"pinsler","year":"0","journal-title":"ICRA Swarms Workshop"},{"key":"ref22","first-page":"40","article-title":"Learning real team solutions","author":"versino","year":"1996","journal-title":"Distributed Artificial Intelligence Meets Machine Learning Learning in Multi-Agent Environments"},{"key":"ref21","author":"matheron","year":"2019","journal-title":"The problem with ddpg understanding failures in deterministic environments with sparse rewards"}],"event":{"name":"2021 7th International Conference on Automation, Robotics and Applications (ICARA)","location":"Prague, Czech Republic","start":{"date-parts":[[2021,2,4]]},"end":{"date-parts":[[2021,2,6]]}},"container-title":["2021 7th International Conference on Automation, Robotics and Applications (ICARA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9376360\/9376362\/09376509.pdf?arnumber=9376509","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:43:52Z","timestamp":1652197432000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9376509\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,4]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icara51699.2021.9376509","relation":{},"subject":[],"published":{"date-parts":[[2021,2,4]]}}}