{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T20:43:15Z","timestamp":1777322595591,"version":"3.51.4"},"reference-count":31,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Research Computing Core Group Office of the Vice President for Research"},{"DOI":"10.13039\/100019687","name":"Hamad Bin Khalifa University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100019687","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/lra.2026.3683594","type":"journal-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T19:38:01Z","timestamp":1776109081000},"page":"6967-6974","source":"Crossref","is-referenced-by-count":0,"title":["Self-Evolved Imitation Learning in Simulated World"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1305-1014","authenticated-orcid":false,"given":"Yifan","family":"Ye","sequence":"first","affiliation":[{"name":"College of Science and Engineering, Hamad Bin Khalifa University, Education City, Doha, Qatar"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7578-7667","authenticated-orcid":false,"given":"Jun","family":"Cen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5206-1110","authenticated-orcid":false,"given":"Jing","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Physics and Optoelectric Engineering, Guangdong University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6917-8654","authenticated-orcid":false,"given":"Zhihe","family":"Lu","sequence":"additional","affiliation":[{"name":"College of Science and Engineering, Hamad Bin Khalifa University, Education City, Doha, Qatar"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4484"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref3","first-page":"158","article-title":"Implicit behavioral cloning","volume-title":"Proc. Conf. Robot Learn.","author":"Florence","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1668"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1939"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11701-024-02205-0"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920987859"},{"key":"ref10","first-page":"19360","article-title":"MAHALO: Unifying offline reinforcement learning and imitation learning from observations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref11","first-page":"11702","article-title":"Bridging offline reinforcement learning and imitation learning: A tale of pessimism","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Rashidinejad","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.egyai.2023.100255"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2023.104432"},{"key":"ref14","article-title":"Implicit offline reinforcement learning via supervised learning","author":"Piche","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812312"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/s23073762"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref18","article-title":"DemoDice: Offline imitation learning with supplementary imperfect demonstrations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kim","year":"2022"},{"key":"ref19","article-title":"Deep reinforcement learning from human preferences","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Christiano","year":"2017"},{"key":"ref20","first-page":"104","article-title":"An optimistic perspective on offline reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Agarwal","year":"2020"},{"key":"ref21","article-title":"What matters in learning from offline human demonstrations for robot manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Mandlekar","year":"2021"},{"key":"ref22","first-page":"4062","article-title":"QUEST: Self-supervised skill abstractions for learning continuous control","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Mete","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02576"},{"key":"ref24","first-page":"1","article-title":"Open-world object manipulation using pre-trained vision-language models","volume-title":"Proc. 7th Conf. Robot Learn.","author":"Stone","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.027"},{"key":"ref26","article-title":"Data scaling laws in imitation learning for robotic manipulation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lin","year":"2025"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01049"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0591"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref30","first-page":"4788","article-title":"RoboAgent: Generalization and efficiency in robot manipulation via semantic augmentations and action chunking","volume-title":"Proc. IEEE Int. Conf. Robot. Automat.","author":"Bharadhwaj","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11481819\/11480780.pdf?arnumber=11480780","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T19:51:22Z","timestamp":1777319482000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11480780\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":31,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3683594","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}