{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T15:08:17Z","timestamp":1767971297387,"version":"3.49.0"},"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\/acc55779.2023.10156379","type":"proceedings-article","created":{"date-parts":[[2023,7,3]],"date-time":"2023-07-03T13:48:03Z","timestamp":1688392083000},"page":"2842-2847","source":"Crossref","is-referenced-by-count":6,"title":["Equivariant Reinforcement Learning for Quadrotor UAV"],"prefix":"10.23919","author":[{"given":"Beomyeol","family":"Yu","sequence":"first","affiliation":[{"name":"George Washington University,Mechanical and Aerospace Engineering,Washington, DC,20051"}]},{"given":"Taeyoung","family":"Lee","sequence":"additional","affiliation":[{"name":"George Washington University,Mechanical and Aerospace Engineering,Washington, DC,20051"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967695"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-018-0891-8"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2693418"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2884725"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CCE53527.2021.9633086"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LARS\/SBR\/WRE.2018.00094"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1020"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref17","article-title":"General E(2)-equivariant steerable CNNs","volume":"32","author":"weiler","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref16","first-page":"2990","article-title":"Group equivariant convolutional networks","author":"cohen","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref19","article-title":"Multi-agent MDP homomorphic networks","author":"van der pol","year":"2021"},{"key":"ref18","first-page":"4199","article-title":"MDP homomorphic networks: Group symmetries in reinforcement learning","volume":"33","author":"van der pol","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015961"},{"key":"ref23","author":"kelley","year":"2017","journal-title":"General Topology"},{"key":"ref26","author":"yu","year":"2022","journal-title":"Equivariant reinforcement learning for quadrotor UAV"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007686309208"},{"key":"ref20","article-title":"SO(2)-equivariant reinforcement learning","author":"wang","year":"0"},{"key":"ref22","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref21","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref28","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref27","author":"brockman","year":"2016","journal-title":"OpenAI Gym"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2019.104222"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2010.5717652"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2720851"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3057046"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636053"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2006.377588"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389776"}],"event":{"name":"2023 American Control Conference (ACC)","location":"San Diego, CA, USA","start":{"date-parts":[[2023,5,31]]},"end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10155646\/10155787\/10156379.pdf?arnumber=10156379","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T13:30:16Z","timestamp":1690205416000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10156379\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,31]]},"references-count":28,"URL":"https:\/\/doi.org\/10.23919\/acc55779.2023.10156379","relation":{},"subject":[],"published":{"date-parts":[[2023,5,31]]}}}