{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T17:42:04Z","timestamp":1788284524346,"version":"build-2803163510"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2022ZD0119802"],"award-info":[{"award-number":["2022ZD0119802"]}]},{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004739","id-type":"DOI","asserted-by":"publisher"}]},{"name":"GPU"},{"name":"MCC Lab of Information Science and Technology Institution"},{"DOI":"10.13039\/501100009076","name":"University of Science and Technology of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009076","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Supercomputing Center of USTC"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tpami.2025.3631231","type":"journal-article","created":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T18:59:47Z","timestamp":1764010787000},"page":"3070-3081","source":"Crossref","is-referenced-by-count":2,"title":["J-Mac: Jacobian Matrix Meets Masked Contrastive Learning for Generalization in Reinforcement Learning"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8181-3764","authenticated-orcid":false,"given":"Yi","family":"Jiang","sequence":"first","affiliation":[{"name":"EEIS Department, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1690-9836","authenticated-orcid":false,"given":"Wengang","family":"Zhou","sequence":"additional","affiliation":[{"name":"EEIS Department, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8007-0479","authenticated-orcid":false,"given":"Yufeng","family":"Shi","sequence":"additional","affiliation":[{"name":"EEIS Department, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8348-0588","authenticated-orcid":false,"given":"Mingxiao","family":"Feng","sequence":"additional","affiliation":[{"name":"EEIS Department, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2188-3028","authenticated-orcid":false,"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[{"name":"EEIS Department, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.12.001"},{"issue":"39","key":"ref2","first-page":"1","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref3","article-title":"Using RGB image as visual input for mapless robot navigation","author":"Ma","year":"2019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3070543"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3204708"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3324320"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.008"},{"key":"ref9","first-page":"1282","article-title":"Quantifying generalization in reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cobbe"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793789"},{"key":"ref11","article-title":"Temporal disentanglement of representations for improved generalisation in reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dunion","year":"2023"},{"key":"ref12","first-page":"80111","article-title":"Conditional mutual information for disentangled representations in reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dunion"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561103"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3144512"},{"key":"ref15","first-page":"3680","article-title":"Stabilizing deep Q-learning with ConvNets and vision transformers under data augmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hansen"},{"key":"ref16","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","author":"Kostrikov","year":"2020"},{"key":"ref17","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00393"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17276"},{"key":"ref20","article-title":"Loss is its own reward: Self-supervision for reinforcement learning","author":"Shelhamer","year":"2016"},{"key":"ref21","article-title":"Data-efficient reinforcement learning with self-predictive representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Schwarzer","year":"2020"},{"key":"ref22","first-page":"5276","article-title":"PlayVirtual: Augmenting cycle-consistent virtual trajectories for reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref23","first-page":"7968","article-title":"Improving generalization in reinforcement learning with mixture regularization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref24","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"ref26","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref27","first-page":"30693","article-title":"Look where you look! Saliency-guided Q-networks for generalization in visual reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bertoin"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctt4cgngj.10"},{"key":"ref29","first-page":"19884","article-title":"Reinforcement learning with augmented data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Laskin"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref32","first-page":"741","article-title":"Stochastic latent actor-critic: Deep reinforcement learning with a latent variable model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref33","first-page":"1480","article-title":"DARLA: Improving zero-shot transfer in reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Higgins"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3176413"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref37","article-title":"A tutorial on energy-based learning","author":"LeCun","year":"2006","journal-title":"Predicting Structured Data"},{"key":"ref38","article-title":"Beta-VAE: Learning basic visual concepts with a constrained variational framework","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Higgins","year":"2017"},{"key":"ref39","first-page":"2180","article-title":"InfoGAN: Interpretable representation learning by information maximizing generative adversarial nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref40","article-title":"Network randomization: A simple technique for generalization in deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee","year":"2020"},{"key":"ref41","first-page":"4182","article-title":"Data-efficient image recognition with contrastive predictive coding","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Henaff"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.320"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2010.5596468"},{"key":"ref45","first-page":"7424","article-title":"Can increasing input dimensionality improve deep reinforcement learning?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ota"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00661"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/514"},{"key":"ref48","first-page":"48203","article-title":"Temporal latent action-driven contrastive loss for visual reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zheng"},{"key":"ref49","article-title":"Mastering visual continuous control: Improved data-augmented reinforcement learning","volume-title":"Proc. Deep RL Workshop NeurIPS","author":"Yarats","year":"2021"},{"key":"ref50","first-page":"25117","article-title":"Mask-based latent reconstruction for reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00654"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3416179"},{"key":"ref53","first-page":"35603","article-title":"Contrastive learning as goal-conditioned reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Eysenbach"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16914"},{"key":"ref55","first-page":"959","article-title":"Contrastive variational reinforcement learning for complex observations","volume-title":"Proc. Conf. Robot Learn.","author":"Ma"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3713"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11372200\/11267178.pdf?arnumber=11267178","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:05:42Z","timestamp":1770671142000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11267178\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":56,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3631231","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}