{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T07:37:09Z","timestamp":1772609829203,"version":"3.50.1"},"reference-count":28,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Wallenberg-NTU Presidential Postdoctoral Fellowship"},{"DOI":"10.13039\/501100001475","name":"Nanyang Technological University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001475","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1109\/tac.2023.3274629","type":"journal-article","created":{"date-parts":[[2023,5,11]],"date-time":"2023-05-11T00:32:13Z","timestamp":1683765133000},"page":"1037-1044","source":"Crossref","is-referenced-by-count":8,"title":["Trust-Region Inverse Reinforcement Learning"],"prefix":"10.1109","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4688-1096","authenticated-orcid":false,"given":"Kun","family":"Cao","sequence":"first","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7137-4136","authenticated-orcid":false,"given":"Lihua","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2773458"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920916531"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3026638"},{"key":"ref7","article-title":"Concrete problems in AI safety","author":"Amodei","year":"2016"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref9","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume-title":"Proc. AAAI","volume":"8","author":"Ziebart","year":"2008"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143936"},{"key":"ref11","first-page":"3909","article-title":"Cooperative inverse reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hadfield-Menell","year":"2016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2012.2234824"},{"key":"ref13","first-page":"7461","article-title":"Multi-agent generative adversarial imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Song","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISIC.2011.6045410"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917745980"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2013.6760325"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2017.09.023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1177\/0278364921996384"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/AUCC.2016.7868186"},{"issue":"1","key":"ref20","doi-asserted-by":"crossref","first-page":"11788","DOI":"10.1016\/j.ifacol.2017.08.1989","article-title":"Inverse noncooperative dynamic games","volume":"50","author":"Molloy","year":"2017","journal-title":"IFAC-PapersOnLine"},{"key":"ref21","first-page":"7979","article-title":"Pontryagin differentiable programming: An end-to-end learning and control framework","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Jin","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3148376"},{"key":"ref23","volume-title":"Numerical Optimization","author":"Nocedal","year":"2006"},{"key":"ref24","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman","year":"2015"},{"key":"ref25","first-page":"5285","article-title":"Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu","year":"2017"},{"key":"ref26","volume-title":"Handbook of Dynamic Game Theory","author":"Baar","year":"2018"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10288-005-0065-y"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s12532-018-0139-4"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9\/10416290\/10121904.pdf?arnumber=10121904","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,2]],"date-time":"2025-01-02T19:48:15Z","timestamp":1735847295000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10121904\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":28,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tac.2023.3274629","relation":{},"ISSN":["0018-9286","1558-2523","2334-3303"],"issn-type":[{"value":"0018-9286","type":"print"},{"value":"1558-2523","type":"electronic"},{"value":"2334-3303","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2]]}}}