{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:18:37Z","timestamp":1740169117304,"version":"3.37.3"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61671266","61836004"],"award-info":[{"award-number":["61671266","61836004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004147","name":"Tsinghua University","doi-asserted-by":"publisher","award":["20161080084"],"award-info":[{"award-number":["20161080084"]}],"id":[{"id":"10.13039\/501100004147","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2927028","type":"journal-article","created":{"date-parts":[[2019,7,7]],"date-time":"2019-07-07T19:03:23Z","timestamp":1562526203000},"page":"106848-106860","source":"Crossref","is-referenced-by-count":3,"title":["Transferable Environment Model With Disentangled Dynamics"],"prefix":"10.1109","volume":"7","author":[{"given":"Qi","family":"Yan","sequence":"first","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shangqi","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dagui","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhile","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4813-2494","authenticated-orcid":false,"given":"Feng","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Transfer from multiple linear predictive state representations (PSR)","author":"sekharan","year":"2017","journal-title":"arXiv 1702 02184"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-87481-2_32"},{"key":"ref33","first-page":"iii-361","article-title":"Efficient planning in MDPs by small backups","volume":"28","author":"van seijen","year":"2013","journal-title":"Proc 30th Int Conf Mach Learn"},{"key":"ref32","first-page":"6118","article-title":"Value prediction network","author":"oh","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","first-page":"2154","article-title":"Value iteration networks","author":"tamar","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref30","first-page":"3191","article-title":"The predictron: End-to-end learning and planning","volume":"70","author":"silver","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref36","article-title":"Incentivizing exploration in reinforcement learning with deep predictive models","author":"stadie","year":"2015","journal-title":"arXiv 1507 00814"},{"key":"ref35","article-title":"Efficient model-based deep reinforcement learning with variational state tabulation","author":"corneil","year":"2018","journal-title":"arXiv 1802 04325"},{"key":"ref34","first-page":"5690","article-title":"Imagination-augmented agents for deep reinforcement learning","author":"weber","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1177\/105971239300100403"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993104"},{"key":"ref29","first-page":"2829","article-title":"Continuous deep Q-learning with model-based acceleration","author":"gu","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref2","first-page":"1555","article-title":"Predictive representations of state","author":"littman","year":"2002","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X01000115"},{"key":"ref20","first-page":"2108","article-title":"One-shot unsupervised cross domain translation","author":"benaim","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860433"},{"key":"ref21","first-page":"907","article-title":"Reinforced continual learning","author":"xu","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Overcoming catastrophic forgetting in neural networks","volume":"114","author":"james","year":"2017","journal-title":"Proc Nat Acad Sci USA"},{"key":"ref23","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref25","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"},{"key":"ref50","first-page":"1","article-title":"Unsupervised learning of state representations for multiple tasks","author":"h\u00f6fer","year":"2016","journal-title":"Proc Deep Learn Workshop Conf Neural Inf Process Syst (NIPS)"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2010.2091281"},{"key":"ref55","first-page":"700","article-title":"Unsupervised image-to-image translation networks","author":"liu","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref54","article-title":"FCNs in the wild: Pixel-level adversarial and constraint-based adaptation","author":"hoffman","year":"2016","journal-title":"arXiv 1612 02649"},{"key":"ref53","article-title":"Deep domain confusion: Maximizing for domain invariance","author":"tzeng","year":"2014","journal-title":"arXiv 1412 3474"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.463"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref11","article-title":"DeepMind lab","author":"beattie","year":"2016","journal-title":"arXiv 1612 03801"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1142\/S012906579100011X"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860433"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.6.863"},{"key":"ref15","first-page":"2172","article-title":"InfoGAN: Interpretable representation learning by information maximizing generative adversarial nets","author":"chen","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","first-page":"5040","article-title":"Disentangling factors of variation in deep representation using adversarial training","author":"mathieu","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","first-page":"1480","article-title":"DARLA: Improving zero-shot transfer in reinforcement learning","volume":"70","author":"higgins","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref18","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2013","journal-title":"arXiv 1312 6114"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmp.2008.12.005"},{"key":"ref6","first-page":"101","article-title":"Model-based reinforcement learning with an approximate, learned model","author":"kuvayev","year":"1996","journal-title":"Proc 9th Yale Workshop on Adaptive and Learning Syst"},{"key":"ref5","article-title":"Temporal difference variational auto-encoder","author":"gregor","year":"2018","journal-title":"arXiv 1806 03107"},{"key":"ref8","first-page":"2863","article-title":"Action-conditional video prediction using deep networks in Atari games","author":"oh","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2015.XI.012"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487173"},{"key":"ref9","article-title":"Recurrent environment simulators","author":"chiappa","year":"2017","journal-title":"arXiv 1704 02254"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126344"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_16"},{"key":"ref48","first-page":"3536","article-title":"LSDA: Large scale detection through adaptation","author":"hoffman","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref47","first-page":"2066","article-title":"Geodesic flow kernel for unsupervised domain adaptation","author":"gong","year":"2012","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref42","first-page":"1","article-title":"From pixels to torques: Policy learning with deep dynamical models","author":"wahlstr\u00f6m","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn Deep Learn Workshop (ICML)"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2011.2159412"},{"key":"ref44","article-title":"Spatio-temporal video autoencoder with differentiable memory","author":"patraucean","year":"2015","journal-title":"arXiv 1511 06309"},{"key":"ref43","first-page":"2746","article-title":"Embed to control: A locally linear latent dynamics model for control from raw images","author":"watter","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08755923.pdf?arnumber=8755923","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,8]],"date-time":"2022-09-08T19:43:15Z","timestamp":1662666195000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8755923\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2927028","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2019]]}}}