{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T14:43:07Z","timestamp":1784644987087,"version":"3.55.0"},"reference-count":119,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"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":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/tnnls.2022.3213246","type":"journal-article","created":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T22:25:49Z","timestamp":1667514349000},"page":"6322-6337","source":"Crossref","is-referenced-by-count":107,"title":["Imitation Learning: Progress, Taxonomies and Challenges"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1223-9230","authenticated-orcid":false,"given":"Boyuan","family":"Zheng","sequence":"first","affiliation":[{"name":"Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sunny","family":"Verma","sequence":"additional","affiliation":[{"name":"Commonwealth Bank of Australia, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6034-644X","authenticated-orcid":false,"given":"Jianlong","family":"Zhou","sequence":"additional","affiliation":[{"name":"Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2211-8176","authenticated-orcid":false,"given":"Ivor W.","family":"Tsang","sequence":"additional","affiliation":[{"name":"Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4971-8729","authenticated-orcid":false,"given":"Fang","family":"Chen","sequence":"additional","affiliation":[{"name":"Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref2","first-page":"305","article-title":"ALVINN: An autonomous land vehicle in a neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Pomerleau"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.88"},{"key":"ref4","article-title":"Imitation learning for end to end vehicle longitudinal control with forward camera","author":"George","year":"2018","journal-title":"arXiv:1812.05841"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2019.1911825"},{"issue":"18","key":"ref6","doi-asserted-by":"crossref","first-page":"5034","DOI":"10.3390\/s20185034","article-title":"Modeling car-following behaviors and driving styles with generative adversarial imitation learning","volume":"20","author":"Zhou","year":"2020","journal-title":"Sensors"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"ref8","first-page":"66","article-title":"Learning by cheating","volume-title":"Proc. Conf. Robot Learn.","author":"Chen"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340639"},{"key":"ref10","first-page":"49","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917713116"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2014.X.011"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2017.2676018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989247"},{"key":"ref15","first-page":"3309","article-title":"Deeply aggrevated: Differentiable imitation learning for sequential prediction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sun"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461249"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2653850"},{"key":"ref18","first-page":"661","article-title":"Efficient reductions for imitation learning","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist.","author":"Ross"},{"key":"ref19","article-title":"Deep Q-learning from demonstrations","author":"Hester","year":"2017","journal-title":"arXiv:1704.03732"},{"key":"ref20","first-page":"2930","article-title":"Playing hard exploration games by watching YouTube","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Aytar"},{"key":"ref21","first-page":"1755","article-title":"Imitating latent policies from observation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Edwards"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-017-3241-z"},{"key":"ref23","first-page":"5320","article-title":"Robust imitation of diverse behaviors","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/j.trc.2019.12.005","article-title":"Optimal passenger-seeking policies on E-hailing platforms using Markov decision process and imitation learning","volume":"111","author":"Shou","year":"2020","journal-title":"Transp. Res. C, Emerg. Technol."},{"key":"ref25","first-page":"6237","article-title":"An imitation learning approach for cache replacement","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref26","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/279943.279964"},{"key":"ref28","first-page":"103","article-title":"A framework for behavioural cloning","volume-title":"Machine Intelligence 15","author":"Bain"},{"key":"ref29","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":"ref30","first-page":"11698","article-title":"Causal confusion in imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"de Haan"},{"key":"ref31","article-title":"Reinforcement and imitation learning via interactive no-regret learning","author":"Ross","year":"2014","journal-title":"arXiv:1406.5979"},{"key":"ref32","article-title":"Maximum mean discrepancy imitation learning","volume-title":"Robotics: Science and Systems","author":"Kim","year":"2013"},{"key":"ref33","first-page":"2058","article-title":"Learning to search better than your teacher","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chang"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910371999"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3053136"},{"key":"ref36","first-page":"2","article-title":"Algorithms for inverse reinforcement learning","volume-title":"Proc. ICML","volume":"1","author":"Ng"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-009-9121-3"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103500"},{"key":"ref40","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume-title":"Proc. AAAI","volume":"8","author":"Ziebart"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2543000"},{"key":"ref42","first-page":"783","article-title":"Extrapolating beyond suboptimal demonstrations via inverse reinforcement learning from observations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Brown"},{"key":"ref43","article-title":"SQIL: Imitation learning via reinforcement learning with sparse rewards","author":"Reddy","year":"2019","journal-title":"arXiv:1905.11108"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561411"},{"key":"ref45","first-page":"4565","article-title":"Generative adversarial imitation learning","volume-title":"Proc. Adv. Neural Inf. Processing Syst.","author":"Ho"},{"key":"ref46","article-title":"Third-person imitation learning","author":"Stadie","year":"2017","journal-title":"arXiv:1703.01703"},{"key":"ref47","article-title":"Goal-conditioned imitation learning","author":"Ding","year":"2019","journal-title":"arXiv:1906.05838"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2020.1778521"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462901"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/687"},{"key":"ref51","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref52","first-page":"1087","article-title":"One-shot imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Duan"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3029220"},{"key":"ref54","article-title":"Generating multi-agent trajectories using programmatic weak supervision","author":"Zhan","year":"2018","journal-title":"arXiv:1803.07612"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593758"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref59","first-page":"7461","article-title":"Multi-agent generative adversarial imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Song"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106795"},{"key":"ref61","first-page":"1","article-title":"Sample efficient imitation learning for continuous control","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Sasaki"},{"key":"ref62","first-page":"3138","article-title":"Sample-efficient imitation learning via generative adversarial nets","volume-title":"Proc. 22nd Int. Conf. Artif. Intell. Statist.","author":"Blond\u00e9"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00942"},{"key":"ref64","article-title":"Robust maximum entropy behavior cloning","author":"Hussein","year":"2021","journal-title":"arXiv:2101.01251"},{"key":"ref65","article-title":"On the sample complexity of stability constrained imitation learning","author":"Tu","year":"2021","journal-title":"arXiv:2102.09161"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10857"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CASE49439.2021.9551469"},{"issue":"1","key":"ref68","first-page":"1","article-title":"An algorithmic perspective on imitation learning","volume":"7","author":"Osa","year":"2018","journal-title":"Found. Trends Robot."},{"key":"ref69","article-title":"Imitation learning for variable speed contact motion for operation up to control bandwidth","author":"Sakaino","year":"2021","journal-title":"arXiv:2102.10283"},{"key":"ref70","article-title":"Model-based inverse reinforcement learning from visual demonstrations","author":"Das","year":"2020","journal-title":"arXiv:2010.09034"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.023"},{"key":"ref72","article-title":"Reward learning from human preferences and demonstrations in Atari","author":"Ibarz","year":"2018","journal-title":"arXiv:1811.06521"},{"key":"ref73","first-page":"3878","article-title":"Self-imitation learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Oh"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref75","first-page":"1165","article-title":"Safe imitation learning via fast Bayesian reward inference from preferences","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Brown"},{"key":"ref76","article-title":"Non-adversarial imitation learning and its connections to adversarial methods","author":"Arenz","year":"2020","journal-title":"arXiv:2008.03525"},{"key":"ref77","first-page":"390","article-title":"End-to-end differentiable adversarial imitation learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Baram"},{"key":"ref78","first-page":"3812","article-title":"InfoGAIL: Interpretable imitation learning from visual demonstrations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.01.016"},{"key":"ref80","article-title":"Generative adversarial imitation from observation","author":"Torabi","year":"2018","journal-title":"arXiv:1807.06158"},{"key":"ref81","first-page":"6036","article-title":"Provably efficient imitation learning from observation alone","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sun"},{"key":"ref82","article-title":"Learning temporal strategic relationships using generative adversarial imitation learning","author":"Fernando","year":"2018","journal-title":"arXiv:1805.04969"},{"key":"ref83","first-page":"10925","article-title":"Intrinsic reward driven imitation learning via generative model","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yu"},{"key":"ref84","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arjovsky"},{"key":"ref85","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462891"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00278"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/882"},{"key":"ref89","article-title":"Off-policy imitation learning from observations","author":"Zhu","year":"2021","journal-title":"arXiv:2102.13185"},{"key":"ref90","article-title":"Inverse reinforcement learning with multiple ranked experts","author":"Castro","year":"2019","journal-title":"arXiv:1907.13411"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01302"},{"key":"ref92","first-page":"5048","article-title":"Hindsight experience replay","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Andrychowicz"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.01.005"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.06.053"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.009"},{"key":"ref96","first-page":"2174","article-title":"Motion2 Vec: Semi-supervised representation learning from surgical videos","volume-title":"Proc. IEEE Int. Conf. Robot. Autom. (ICRA)","author":"Tanwani"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2996386"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.056"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/497"},{"key":"ref100","first-page":"330","article-title":"Better-than-demonstrator imitation learning via automatically-ranked demonstrations","volume-title":"Proc. Conf. Robot Learn.","author":"Brown"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.002"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3021530"},{"key":"ref103","article-title":"Learning Montezuma\u2019s revenge from a single demonstration","author":"Salimans","year":"2018","journal-title":"arXiv:1812.03381"},{"key":"ref104","volume-title":"DeepGTAV","author":"Ruano","year":"2016"},{"key":"ref105","article-title":"Deep reinforcement learning from policy-dependent human feedback","author":"Arumugam","year":"2019","journal-title":"arXiv:1902.04257"},{"key":"ref106","first-page":"67","article-title":"Sample efficient reinforcement learning through learning from demonstrations in minecraft","volume-title":"Proc. NeurIPS Competition Demonstration Track","author":"Scheller"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1177\/0278364918781001"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1007\/s10951-017-0534-0"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1515\/pjbr-2015-0002"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/CoG47356.2020.9231600"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/339"},{"key":"ref112","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume-title":"Proc. Conf. Robot Learn.","author":"Dosovitskiy"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref114","article-title":"OpenAI gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403186"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01397-w"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/599"},{"key":"ref118","first-page":"4415","article-title":"Reward-rational (implicit) choice: A unifying formalism for reward learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Jeon"},{"key":"ref119","first-page":"1113","article-title":"Learning latent plans from play","volume-title":"Proc. Conf. Robot Learn.","author":"Lynch"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10517792\/09927439.pdf?arnumber=9927439","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,3]],"date-time":"2024-09-03T04:40:19Z","timestamp":1725338419000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9927439\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":119,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3213246","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5]]}}}