{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T17:22:24Z","timestamp":1791480144492,"version":"4.3.4"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1109\/tnnls.2021.3106818","type":"journal-article","created":{"date-parts":[[2021,9,3]],"date-time":"2021-09-03T19:58:26Z","timestamp":1630699106000},"page":"2513-2527","source":"Crossref","is-referenced-by-count":18,"title":["Learning a Low-Dimensional Representation of a Safe Region for Safe Reinforcement Learning on Dynamical Systems"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9542-4858","authenticated-orcid":false,"given":"Zhehua","family":"Zhou","sequence":"first","affiliation":[{"name":"Chair of Automatic Control Engineering, Technical University of Munich, Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8723-1837","authenticated-orcid":false,"given":"Ozgur S.","family":"Oguz","sequence":"additional","affiliation":[{"name":"Max Planck Institute for Intelligent Systems, University of Stuttgart, Stuttgart, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marion","family":"Leibold","sequence":"additional","affiliation":[{"name":"Chair of Automatic Control Engineering, Technical University of Munich, Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1776-2752","authenticated-orcid":false,"given":"Martin","family":"Buss","sequence":"additional","affiliation":[{"name":"Chair of Automatic Control Engineering, Technical University of Munich, Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/0278364916645661"},{"key":"ref35","first-page":"235","article-title":"Categories of belief fusion","volume":"13","author":"j\u00f8sang","year":"2018","journal-title":"J Adv Inf Fusion"},{"key":"ref12","first-page":"8103","article-title":"A Lyapunov-based approach to safe reinforcement learning","author":"chow","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-42337-1"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3024161"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2016.XII.017"},{"key":"ref36","article-title":"Modelling and control of quadcopter","author":"luukkonen","year":"2011"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1137\/18M118935X"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2007.7068567"},{"key":"ref11","first-page":"803","article-title":"Lyapunov design for safe reinforcement learning","volume":"3","author":"perkins","year":"2002","journal-title":"J Mach Learn Res"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1515\/9780691214696"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00600"},{"key":"ref32","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref2","first-page":"1","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073602"},{"key":"ref17","first-page":"1451","article-title":"Safe exploration in Markov decision processes","author":"moldovan","year":"2012","journal-title":"Proc 29th Int Conf Mach Learn (ICML)"},{"key":"ref16","first-page":"1093","article-title":"Safe reinforcement learning using robust action governor","author":"li","year":"2021","journal-title":"Proc 3rd Conf Learn Dyn Control (L4DC)"},{"key":"ref19","author":"rasmussen","year":"2006","journal-title":"Gaussian Processes for Machine Learning"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2876389"},{"key":"ref24","first-page":"561","article-title":"Benchmarking reinforcement learning algorithms on real-world robots","author":"mahmood","year":"2018","journal-title":"Proc 2nd Conf Robot Learn (CoRL)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794107"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.2992981"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2017.8263977"},{"key":"ref22","first-page":"908","article-title":"Safe model-based reinforcement learning with stability guarantees","author":"berkenkamp","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7798979"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989186"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-78841-6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2015.12.011"},{"key":"ref8","article-title":"Adversarial attacks on neural network policies","author":"huang","year":"2017","journal-title":"arXiv 1702 02284"},{"key":"ref7","article-title":"Transfer from simulation to real world through learning deep inverse dynamics model","author":"christiano","year":"2016","journal-title":"arXiv 1610 03518"},{"key":"ref9","first-page":"22","article-title":"Constrained policy optimization","author":"achiam","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn (ICML)"},{"key":"ref4","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"garc?a","year":"2015","journal-title":"J Mach Learn Res"},{"key":"ref3","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"Proc Int Conf Int Conf Mach Learn"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref5","first-page":"1","article-title":"An application of reinforcement learning to aerobatic helicopter flight","author":"abbeel","year":"2006","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10114428\/09528905.pdf?arnumber=9528905","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,22]],"date-time":"2023-05-22T17:55:03Z","timestamp":1684778103000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9528905\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5]]},"references-count":36,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3106818","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5]]}}}