{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:17:04Z","timestamp":1776885424720,"version":"3.51.2"},"reference-count":94,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"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":["FL-170100117"],"award-info":[{"award-number":["FL-170100117"]}],"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":[[2024,10]]},"DOI":"10.1109\/tnnls.2023.3275075","type":"journal-article","created":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T13:38:27Z","timestamp":1685367507000},"page":"14190-14204","source":"Crossref","is-referenced-by-count":3,"title":["Quantum Imitation Learning"],"prefix":"10.1109","volume":"35","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, The University of Sydney, Darlington, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1321-1582","authenticated-orcid":false,"given":"Kaining","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Faculty of Engineering, The University of Sydney, Darlington, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5659-3464","authenticated-orcid":false,"given":"Li","family":"Shen","sequence":"additional","affiliation":[{"name":"JD Explore Academy, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"School of Computer Science, Faculty of Engineering, The University of Sydney, Darlington, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"651","article-title":"Imitation: Social, cognitive, and theoretical perspectives","volume-title":"The Oxford Handbook of Developmental Psychology: Mind and Body","volume":"1","author":"Meltzoff","year":"2013"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198538677.003.0006"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201311"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s41315-019-00103-5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105636"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919880273"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref9","first-page":"1","article-title":"Sample efficient imitation learning for continuous control","volume-title":"Proc. Int. Conf. Learn. Represent","author":"Sasaki"},{"key":"ref10","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":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2018.11.002"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1126\/science.abe8770"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1666-5"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/nature23474"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-0980-2"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2018.112130030"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2933394"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/s42254-021-00348-9"},{"key":"ref19","article-title":"An empirical investigation of the challenges of real-world reinforcement learning","author":"Dulac-Arnold","year":"2020","journal-title":"arXiv:2003.11881"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3099621"},{"key":"ref21","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":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2543000"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102352"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref25","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume-title":"Proc. AAAI","volume":"8","author":"Ziebart"},{"key":"ref26","first-page":"4565","article-title":"Generative adversarial imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref27","article-title":"Generative adversarial imitation from observation","author":"Torabi","year":"2018","journal-title":"arXiv:1807.06158"},{"key":"ref28","first-page":"1259","article-title":"A divergence minimization perspective on imitation learning methods","volume-title":"Proc. Conf. Robot Learn.","author":"Ghasemipour"},{"key":"ref29","first-page":"12805","article-title":"f-GAIL: Learning f-divergence for generative adversarial imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref30","first-page":"1","article-title":"Primal Wasserstein imitation learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dadashi"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7_2"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7_14"},{"key":"ref33","volume-title":"Introduction to Reinforcement Learning","volume":"135","author":"Sutton","year":"1998"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/nphys3029"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.113.130503"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084467"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICTC49870.2020.9289439"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-012-5316-5"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2020.03.204"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.925743"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03242-7"},{"key":"ref42","first-page":"1","article-title":"Parametrized quantum policies for reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jerbi"},{"key":"ref43","article-title":"Quantum agents in the gym: A variational quantum algorithm for deep Q-learning","author":"Skolik","year":"2021","journal-title":"arXiv:2103.15084"},{"key":"ref44","article-title":"Unentangled quantum reinforcement learning agents in the OpenAI gym","author":"Hsiao","year":"2022","journal-title":"arXiv:2203.14348"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.8.031086"},{"key":"ref46","article-title":"Using reinforcement learning to find efficient qubit routing policies for deployment in near-term quantum computers","author":"Herbert","year":"2018","journal-title":"arXiv:1812.11619"},{"key":"ref47","article-title":"Reinforcement learning for optimization of variational quantum circuit architectures","author":"Ostaszewski","year":"2021","journal-title":"arXiv:2103.16089"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"},{"key":"ref49","first-page":"1","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":"ref50","doi-asserted-by":"publisher","DOI":"10.1561\/2300000053"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/18.61115"},{"key":"ref53","first-page":"547","article-title":"On measures of entropy and information","volume-title":"Proc. 4th Berkeley Symp. Math. Statist. Probab.","volume":"1","author":"R\u00e9nyi"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3096966"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref56","article-title":"Quantum computing: Lecture notes","author":"de Wolf","year":"2019","journal-title":"arXiv:1907.09415"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v16i1.7437"},{"key":"ref58","article-title":"Quantum computing and the entanglement frontier","author":"Preskill","year":"2012","journal-title":"arXiv:1203.5813"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4020-8265-8_1230"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1002\/9780470510520"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.1998.0159"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1201\/9781420035377"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1103\/RevModPhys.85.623"},{"key":"ref64","article-title":"How transferable are features in deep neural networks?","author":"Yosinski","year":"2014","journal-title":"arXiv:1411.1792"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1088\/2058-9565\/ab4eb5"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.103.L030401"},{"key":"ref67","article-title":"An end-to-end trainable hybrid classical-quantum classifier","author":"Yen-Chi Chen","year":"2021","journal-title":"arXiv:2102.02416"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICSA-C52384.2021.00025"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.122.040504"},{"key":"ref70","volume-title":"Quantum Algorithms for Linear Algebra and Machine Learning","author":"Prakash","year":"2014"},{"key":"ref71","article-title":"Do wide and deep networks learn the same things? Uncovering how neural network representations vary with width and depth","author":"Nguyen","year":"2020","journal-title":"arXiv:2010.15327"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.22331\/q-2020-02-06-226"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.104.012405"},{"key":"ref74","first-page":"661","article-title":"Efficient reductions for imitation learning","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist.","author":"Ross"},{"key":"ref75","first-page":"2914","article-title":"Toward the fundamental limits of imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Rajaraman"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevApplied.16.024051"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.121.040502"},{"key":"ref78","article-title":"Spectral normalization for generative adversarial networks","author":"Miyato","year":"2018","journal-title":"arXiv:1802.05957"},{"key":"ref79","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref80","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref81","first-page":"4511","article-title":"Hyperparameter selection for imitation learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hussenot"},{"key":"ref82","article-title":"Spinning up in deep reinforcement learning","author":"Achiam","year":"2018"},{"key":"ref83","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Duan"},{"key":"ref84","article-title":"OpenAI gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref85","volume-title":"Guide to the Carnegie Mellon University multimodal activity (CMU-MMAC) database","author":"De la Torre Frade","year":"2008"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2003.02989"},{"key":"ref87","volume-title":"CIRQ: A Python Framework for Creating, Editing, and Invoking Quantum Circuits","author":"Hancock","year":"2019"},{"key":"ref88","volume-title":"OpenAI Baselines","author":"Dhariwal","year":"2017"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/584091.584093"},{"key":"ref90","volume-title":"Quantum Computing & Reinforcement Learning: Partners in Achieving Artificial General Intelligence","author":"Agunbiade","year":"2022"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.107.2100469"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-32550-3"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1126\/science.1177838"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511921889"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10707065\/10138016.pdf?arnumber=10138016","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T18:32:21Z","timestamp":1767810741000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10138016\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":94,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3275075","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}