{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T16:06:04Z","timestamp":1780502764998,"version":"3.54.1"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP-180103424"],"award-info":[{"award-number":["DP-180103424"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2023,2]]},"DOI":"10.1109\/tnnls.2021.3099621","type":"journal-article","created":{"date-parts":[[2021,8,9]],"date-time":"2021-08-09T20:16:32Z","timestamp":1628540192000},"page":"677-689","source":"Crossref","is-referenced-by-count":9,"title":["On the Guaranteed Almost Equivalence Between Imitation Learning From Observation and Demonstration"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8360-5149","authenticated-orcid":false,"given":"Zhihao","family":"Cheng","sequence":"first","affiliation":[{"name":"School of Computer Science, Faculty of Engineering, University of Sydney, Darlington, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8128-2788","authenticated-orcid":false,"given":"Liu","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Faculty of Engineering, University of Sydney, Darlington, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4224-1318","authenticated-orcid":false,"given":"Aishan","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Lab of Software Development Environment, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, Multi-Media Laboratory (MMLAB), The Chinese University of Hong Kong, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Fang","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Computer Science, Eindhoven University of Technology, Eindhoven, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"JD Explore Academy, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"End to end learning for self-driving cars","volume-title":"arXiv:1604.07316","author":"Bojarski","year":"2016"},{"key":"ref2","first-page":"3812","article-title":"InfoGAIL: Interpretable imitation learning from visual demonstrations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2996386"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2008.iv.034"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3004893"},{"key":"ref6","article-title":"Learning human behaviors from motion capture by adversarial imitation","volume-title":"arXiv:1707.02201","author":"Merel","year":"2017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793515"},{"key":"ref8","article-title":"A learning-from-observation framework: One-shot robot teaching for grasp-manipulation-release household operations","volume-title":"arXiv:2008.01513","author":"Wake","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459670"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00722"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356501"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275014"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1080\/00207590500492435"},{"key":"ref14","article-title":"State-only imitation with transition dynamics mismatch","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Gangwani"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/687"},{"key":"ref16","article-title":"Generative adversarial imitation from observation","volume-title":"arXiv:1807.06158","author":"Torabi","year":"2018"},{"key":"ref17","first-page":"239","article-title":"Imitation learning from observations by minimizing inverse dynamics disagreement","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/487"},{"key":"ref19","first-page":"4565","article-title":"Generative adversarial imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3021530"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198538677.003.0006"},{"key":"ref22","first-page":"661","article-title":"Efficient reductions for imitation learning","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist.","author":"Ross"},{"key":"ref23","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proc. 14th Int. Conf. Artif. Intell. Statist.","author":"Ross"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2543000"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.064"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/9.45152"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/18.61115"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1142\/9321"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/70.258046"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1201\/9781420053739"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6224695"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1002\/9780470753767"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.054"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2020.3019883"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3022950"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2275948"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2021.3060731"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2003.07.001"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2010.5530951"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2017.2647987"},{"key":"ref44","volume-title":"Principles of Mathematical Analysis","volume":"3","author":"Rudin","year":"1964"},{"key":"ref45","article-title":"OpenAI gym","volume-title":"arXiv:1606.01540","author":"Brockman","year":"2016"},{"key":"ref46","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref47","volume-title":"Spinning Up in Deep Reinforcement Learning","author":"Achiam","year":"2018"},{"key":"ref48","article-title":"An empirical investigation of the challenges of real-world reinforcement learning","volume-title":"arXiv:2003.11881","author":"Dulac-Arnold","year":"2020"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197465"},{"key":"ref50","volume-title":"Openai Baselines","author":"Dhariwal","year":"2017"},{"key":"ref51","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref52","volume-title":"TF2RL","author":"Ota","year":"2020"},{"key":"ref53","article-title":"Spectral normalization for generative adversarial networks","volume-title":"arXiv:1802.05957","author":"Miyato","year":"2018"},{"key":"ref54","article-title":"Continuous control with deep reinforcement learning","volume-title":"arXiv:1509.02971","author":"Lillicrap","year":"2015"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1126\/science.359.6377.725"},{"key":"ref57","article-title":"Ctrl-Z: Recovering from instability in reinforcement learning","volume-title":"arXiv:1910.03732","author":"Dasagi","year":"2019"},{"key":"ref58","first-page":"5767","article-title":"Improved training of wasserstein GANs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gulrajani"},{"key":"ref59","article-title":"Consistency regularization for generative adversarial networks","volume-title":"arXiv:1910.12027","author":"Zhang","year":"2019"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10036162\/09509344.pdf?arnumber=9509344","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T23:10:25Z","timestamp":1705014625000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9509344\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2]]},"references-count":59,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3099621","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2]]}}}