{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T18:23:15Z","timestamp":1767378195670,"version":"3.48.0"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62133005"],"award-info":[{"award-number":["62133005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62027810"],"award-info":[{"award-number":["62027810"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62103141"],"award-info":[{"award-number":["62103141"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019081","name":"Science and Technology Innovation Program of Hunan Province","doi-asserted-by":"publisher","award":["2025RC3088"],"award-info":[{"award-number":["2025RC3088"]}],"id":[{"id":"10.13039\/501100019081","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004735","name":"Natural Science Foundation of Hunan Province","doi-asserted-by":"publisher","award":["2025JJ50336"],"award-info":[{"award-number":["2025JJ50336"]}],"id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jiangxi Province 03 Special Project and 5G Project","award":["20232ABC03A09"],"award-info":[{"award-number":["20232ABC03A09"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tits.2025.3612273","type":"journal-article","created":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T18:45:42Z","timestamp":1763059542000},"page":"960-971","source":"Crossref","is-referenced-by-count":0,"title":["Self-Expert Imitation With Purifying Latent Feature for Generalization in Visual Reinforcement Learning"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5363-7441","authenticated-orcid":false,"given":"Lin","family":"Chen","sequence":"first","affiliation":[{"name":"School of Software Engineering, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6734-8691","authenticated-orcid":false,"given":"Yang","family":"Mo","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Robotics, Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0519-6458","authenticated-orcid":false,"given":"Yaonan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Robotics, Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0899-1537","authenticated-orcid":false,"given":"Zhiqiang","family":"Miao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Robotics, Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2745-1253","authenticated-orcid":false,"given":"Kai","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Robotics, Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0384-3743","authenticated-orcid":false,"given":"Mingtao","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2112-3742","authenticated-orcid":false,"given":"Zhen","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Robotics, Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0997-340X","authenticated-orcid":false,"given":"Sifei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Robotics, Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3400-0079","authenticated-orcid":false,"given":"Danwei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electrical and Electrical Engineering, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"VTNet: Visual transformer network for object goal navigation","author":"Du","year":"2021","journal-title":"arXiv:2105.09447"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3057424"},{"key":"ref3","article-title":"Adversarial reinforced instruction attacker for robust vision-language navigation","author":"Lin","year":"2021","journal-title":"arXiv:2107.11252"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3122579"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17251"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3167688"},{"key":"ref7","first-page":"2063","article-title":"Transfer learning for related reinforcement learning tasks via image-to-image translation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gamrian"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.07.156"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45855.2022.9838583"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"article-title":"Robust domain randomization for reinforcement learning","year":"2020","author":"Slaoui","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.11"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-43089-4_44"},{"key":"ref15","article-title":"SECANT: Self-expert cloning for zero-shot generalization of visual policies","author":"Fan","year":"2021","journal-title":"arXiv:2106.09678"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801730"},{"key":"ref17","first-page":"5402","article-title":"Automatic data augmentation for generalization in reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Raileanu"},{"key":"ref18","article-title":"Model-invariant state abstractions for model-based reinforcement learning","author":"Tomar","year":"2021","journal-title":"arXiv:2102.09850"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tai.2021.3054609"},{"key":"ref20","first-page":"1480","article-title":"DARLA: Improving zero-shot transfer in reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Higgins"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-70679-1_5"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tcds.2023.3315513"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/iros51168.2021.9636294"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3552132"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3360712"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2025.3548788"},{"key":"ref27","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","author":"Kostrikov","year":"2020","journal-title":"arXiv:2004.13649"},{"key":"ref28","article-title":"Network randomization: A simple technique for generalization in deep reinforcement learning","author":"Lee","year":"2019","journal-title":"arXiv:1910.05396"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17276"},{"key":"ref30","first-page":"991","article-title":"BC-Z: Zero-shot task generalization with robotic imitation learning","volume-title":"Proc. 5th Conf. Robot Learn.","author":"Jang"},{"key":"ref31","first-page":"8583","article-title":"Planning to explore via self-supervised world models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Sekar"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2696121"},{"volume-title":"Deep Learning","year":"2016","author":"Goodfellow","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3195549"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00807"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00685"},{"key":"ref39","article-title":"Domain generalization with MixStyle","author":"Zhou","year":"2021","journal-title":"arXiv:2104.02008"},{"key":"ref40","article-title":"MixStyle neural networks for domain generalization and adaptation","author":"Zhou","year":"2021","journal-title":"arXiv:2107.02053"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1710.09412"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_28"},{"key":"ref43","first-page":"1647","article-title":"Conditional adversarial domain adaptation","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Long"},{"key":"ref44","article-title":"Semi-supervised domain generalization with stochastic StyleMatch","author":"Zhou","year":"2021","journal-title":"arXiv:2106.00592"},{"key":"ref45","article-title":"Frustratingly simple domain generalization via image stylization","author":"Somavarapu","year":"2020","journal-title":"arXiv:2006.11207"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412735"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561103"},{"key":"ref48","first-page":"19884","article-title":"Reinforcement learning with augmented data","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Laskin"},{"key":"ref49","article-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017","journal-title":"arXiv:1708.04552"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctt4cgngj.10"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref53","first-page":"700","article-title":"Unsupervised image-to-image translation networks","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref55","article-title":"Beta-VAE: Learning basic visual concepts with a constrained variational framework","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Higgins","year":"2017"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_49"},{"key":"ref57","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref58","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04898-2_643"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3051456"},{"key":"ref61","first-page":"3952","article-title":"Invariant causal imitation learning for generalizable policies","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Bica"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/icme55011.2023.00474"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6979\/11322649\/11247841.pdf?arnumber=11247841","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T18:17:53Z","timestamp":1767377873000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247841\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":62,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tits.2025.3612273","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"type":"print","value":"1524-9050"},{"type":"electronic","value":"1558-0016"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}