{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T14:39:58Z","timestamp":1782484798220,"version":"3.54.5"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Plan of China","award":["2020AAA0108902"],"award-info":[{"award-number":["2020AAA0108902"]}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61627808"],"award-info":[{"award-number":["61627808"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Strategic Priority Research Program of Chinese Academy of Science","doi-asserted-by":"publisher","award":["XDB32050100"],"award-info":[{"award-number":["XDB32050100"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Dongguan Core Technology Research Frontier Project","award":["2019622101001"],"award-info":[{"award-number":["2019622101001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1109\/tcds.2022.3187186","type":"journal-article","created":{"date-parts":[[2022,6,29]],"date-time":"2022-06-29T19:44:45Z","timestamp":1656531885000},"page":"819-831","source":"Crossref","is-referenced-by-count":5,"title":["SURRL: Structural Unsupervised Representations for Robot Learning"],"prefix":"10.1109","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7485-109X","authenticated-orcid":false,"given":"Fengyi","family":"Zhang","sequence":"first","affiliation":[{"name":"National Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yurou","family":"Chen","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6384-3687","authenticated-orcid":false,"given":"Hong","family":"Qiao","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Multimodal Artificial Intelligence Systems and Beijing Key Laboratory of Research and Application for Robotic Intelligence, Hand-Eye-Brain Interaction Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2148-1846","authenticated-orcid":false,"given":"Zhiyong","family":"Liu","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462891"},{"key":"ref12","article-title":"Beta-VAE: Learning basic visual concepts with a constrained variational framework","author":"higgins","year":"2017","journal-title":"Proc Int Conf Represent Learn"},{"key":"ref15","author":"anderson","year":"2009","journal-title":"How Can the Human Mind Occur in the Physical Universe?"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X08003543"},{"key":"ref52","first-page":"1263","article-title":"Neural message passing for quantum chemistry","author":"gilmer","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2017.8080408"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/nature13665"},{"key":"ref17","first-page":"4742","article-title":"Structured control nets for deep reinforcement learning","author":"srouji","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aay6276"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2020.103555"},{"key":"ref18","article-title":"Deep reinforcement learning with graph-based state representations","author":"waradpande","year":"2020","journal-title":"arXiv 2004 13965"},{"key":"ref51","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015","journal-title":"arXiv 1506 02438 [cs]"},{"key":"ref50","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref46","first-page":"1","article-title":"NerveNet: Learning structured policy with graph neural networks","author":"wang","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref45","article-title":"PVEs: Position-velocity encoders for unsupervised learning of structured state representations","author":"jonschkowski","year":"2017","journal-title":"arXiv 1705 09805"},{"key":"ref48","first-page":"1","article-title":"Deep reinforcement learning with relational inductive biases","author":"zambaldi","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref47","first-page":"1","article-title":"Relational inductive bias for physical construction in humans and machines","author":"hamrick","year":"2018","journal-title":"Proc 40th Annu Conf of Cogn Sci Soc"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005141"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759578"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2981333"},{"key":"ref43","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","article-title":"The graph neural network model","volume":"20","author":"scarselli","year":"2009","journal-title":"IEEE Trans Neural Netw"},{"key":"ref49","first-page":"4470","article-title":"Graph networks as learnable physics engines for inference and control","author":"sanchez-gonzalez","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.07.006"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630809"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-018-0109-9"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593871"},{"key":"ref3","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460655"},{"key":"ref40","article-title":"Robot skill learning in latent space of a deep autoencoder neural network","volume":"135","author":"lon?arevi?","year":"2021","journal-title":"Robot Auton Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793485"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7798980"},{"key":"ref37","first-page":"1","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2014","journal-title":"Proc Int Conf Represent Learn"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967938"},{"key":"ref31","first-page":"4732","article-title":"Universal planning networks: Learning generalizable representations for visuomotor control","author":"srinivas","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2800101"},{"key":"ref33","article-title":"Learning to navigate in complex environments","author":"mirowski","year":"2016","journal-title":"arXiv 1611 03673"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s13218-015-0356-1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1515\/pjbr-2019-0005"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487173"},{"key":"ref24","first-page":"6739","article-title":"Behavior self-organization supports task inference for continual robot learning","author":"hafez","year":"2021","journal-title":"Proc IEEE\/RSJ Int Conf Intell Robots Syst (IROS)"},{"key":"ref23","first-page":"1","article-title":"Distral: Robust multitask reinforcement learning","volume":"30","author":"teh","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref26","first-page":"991","article-title":"BC-z: Zero-shot task generalization with robotic imitation learning","author":"jang","year":"2022","journal-title":"Proc Conf Robot Learn"},{"key":"ref25","article-title":"Language conditioned imitation learning over unstructured data","author":"lynch","year":"2020","journal-title":"arXiv 2005 07648"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CCDC49329.2020.9164162"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630771"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989250"},{"key":"ref27","article-title":"Learning context-aware task reasoning for efficient meta-reinforcement learning","author":"wang","year":"2020","journal-title":"arXiv 2003 01373"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2890974"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274989\/10146524\/09810505.pdf?arnumber=9810505","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,26]],"date-time":"2023-06-26T18:53:57Z","timestamp":1687805637000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9810505\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6]]},"references-count":52,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2022.3187186","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"value":"2379-8920","type":"print"},{"value":"2379-8939","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6]]}}}