{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T14:08:28Z","timestamp":1784210908796,"version":"3.55.0"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"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":[[2025,4]]},"DOI":"10.1109\/tnnls.2024.3401170","type":"journal-article","created":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T13:30:58Z","timestamp":1717767058000},"page":"7145-7157","source":"Crossref","is-referenced-by-count":5,"title":["Diverse Imitation Learning via Self-Organizing Generative Models"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9256-5775","authenticated-orcid":false,"given":"Arash","family":"Vahabpour","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of California, Los Angeles, Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7263-5852","authenticated-orcid":false,"given":"Tianyi","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of California, Los Angeles, Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3038-256X","authenticated-orcid":false,"given":"Qiujing","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of California, Los Angeles, Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7891-0219","authenticated-orcid":false,"given":"Omead","family":"Pooladzandi","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of California, Los Angeles, Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0832-6489","authenticated-orcid":false,"given":"Vwani","family":"Roychowdhury","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of California, Los Angeles, Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3213246"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2543000"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3106635"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3142822"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s41315-019-00103-5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.88"},{"key":"ref7","first-page":"661","article-title":"Efficient reductions for imitation learning","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist.","author":"Ross"},{"key":"ref8","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":"ref9","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume-title":"Proc. AAAI","volume":"8","author":"Ziebart"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/EEBDA53927.2022.9744760"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3082568"},{"key":"ref13","first-page":"1","article-title":"Modeling interaction via the principle of maximum causal entropy","volume-title":"Proc. ICML","author":"Ziebart"},{"key":"ref14","article-title":"Generative adversarial imitation learning","author":"Ho","year":"2016","journal-title":"arXiv:1606.03476"},{"key":"ref15","article-title":"Generative adversarial networks","author":"Goodfellow","year":"2014","journal-title":"arXiv:1406.2661"},{"key":"ref16","article-title":"InfoGAIL: Interpretable imitation learning from visual demonstrations","author":"Li","year":"2017","journal-title":"arXiv:1703.08840"},{"key":"ref17","article-title":"Robust imitation of diverse behaviors","author":"Wang","year":"2017","journal-title":"arXiv:1707.02747"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2805379"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3087733"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3059912"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/405"},{"key":"ref22","article-title":"Learning human behaviors from motion capture by adversarial imitation","author":"Merel","year":"2017","journal-title":"arXiv:1707.02201"},{"key":"ref23","article-title":"Multi-modal imitation learning from unstructured demonstrations using generative adversarial nets","author":"Hausman","year":"2017","journal-title":"arXiv:1705.10479"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.18"},{"key":"ref25","article-title":"Optimizing the latent space of generative networks","author":"Bojanowski","year":"2017","journal-title":"arXiv:1707.05776"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00596"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3053840"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3071275"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/5.58325"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1989.118292"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2006.872354"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/72.846731"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/5.537105"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/72.143371"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/72.377962"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref37","article-title":"Augmenting GAIL with BC for sample efficient imitation learning","author":"Jena","year":"2020","journal-title":"arXiv:2001.07798"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7040156"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref40","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Rakelly"},{"key":"ref41","article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","author":"Plappert","year":"2018","journal-title":"arXiv:1802.09464"},{"key":"ref42","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref43","article-title":"Hindsight experience replay","author":"Andrychowicz","year":"2017","journal-title":"arXiv:1707.01495"},{"issue":"2","key":"ref44","first-page":"9","article-title":"Sample estimate of the entropy of a random vector","volume":"23","author":"Kozachenko","year":"1987","journal-title":"Problemy Peredachi Informatsii"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.69.066138"},{"key":"ref46","volume-title":"Pattern Recognition and Machine Learning","author":"Bishop","year":"2006"},{"key":"ref47","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref48","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref49","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015","journal-title":"arXiv:1506.02438"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/10949581\/10551852.pdf?arnumber=10551852","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:39:11Z","timestamp":1764959951000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10551852\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":49,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3401170","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}