{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:44:35Z","timestamp":1777657475521,"version":"3.51.4"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Amazon Research Award and gifts from Qualcomm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1109\/lra.2023.3259681","type":"journal-article","created":{"date-parts":[[2023,3,20]],"date-time":"2023-03-20T18:01:59Z","timestamp":1679335319000},"page":"2890-2897","source":"Crossref","is-referenced-by-count":24,"title":["Visual Reinforcement Learning With Self-Supervised 3D Representations"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8422-8923","authenticated-orcid":false,"given":"Yanjie","family":"Ze","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9897-4003","authenticated-orcid":false,"given":"Nicklas","family":"Hansen","sequence":"additional","affiliation":[{"name":"University of California San Diego, San Diego, CA, USA"}]},{"given":"Yinbo","family":"Chen","sequence":"additional","affiliation":[{"name":"University of California San Diego, San Diego, CA, USA"}]},{"given":"Mohit","family":"Jain","sequence":"additional","affiliation":[{"name":"University of California San Diego, San Diego, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3150-778X","authenticated-orcid":false,"given":"Xiaolong","family":"Wang","sequence":"additional","affiliation":[{"name":"University of California San Diego, San Diego, CA, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref2","article-title":"Mastering chess and shogi by self-play with a general reinforcement learning algorithm","author":"Silver","year":"2017"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref4","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17276"},{"key":"ref6","first-page":"5639","article-title":"CURL: Contrastive unsupervised representations for reinforcement learning","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Laskin","year":"2020"},{"key":"ref7","first-page":"1480","article-title":"DARLA: Improving zero-shot transfer in reinforcement learning","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Higgins","year":"2017"},{"key":"ref8","first-page":"9209","article-title":"Visual reinforcement learning with imagined goals","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Nair","year":"2018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561103"},{"key":"ref10","article-title":"Masked visual pre-training for motor control","author":"Xiao","year":"2022"},{"key":"ref11","first-page":"17359","article-title":"The unsurprising effectiveness of pre-trained vision models for control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Parisi","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1126\/science.281.5376.552"},{"key":"ref13","first-page":"422","article-title":"Reinforcement learning of active vision for manipulating objects under occlusions","volume-title":"Proc. 2nd Conf. Robot Learn.","author":"Cheng","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197181"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196679"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00270"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00959"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01072"},{"key":"ref19","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Yu","year":"2019"},{"key":"ref20","article-title":"Dream to control: Learning behaviors by latent imagination","author":"Hafner","year":"2020"},{"key":"ref21","first-page":"1","article-title":"Self-supervised policy adaptation during deployment","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hansen","year":"2021"},{"key":"ref22","first-page":"25476","article-title":"Mastering atari games with limited data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ye","year":"2021"},{"key":"ref23","first-page":"19884","article-title":"Reinforcement learning with augmented data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Laskin","year":"2020"},{"key":"ref24","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kostrikov","year":"2020"},{"key":"ref25","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","year":"2021"},{"key":"ref26","article-title":"R3M: A universal visual representation for robot manipulation","author":"Nair","year":"2022"},{"key":"ref27","first-page":"1539","article-title":"Unsupervised learning of visual 3D keypoints for control","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Chen","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00494"},{"key":"ref29","article-title":"3D-OES: Viewpoint-invariant object-factorized environment simulators","author":"Tung","year":"2020"},{"key":"ref30","article-title":"Learning long-term visual dynamics with region proposal interaction networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Qi","year":"2021"},{"key":"ref31","article-title":"MoNet: Unsupervised scene decomposition and representation","author":"Burgess","year":"2019"},{"key":"ref32","first-page":"112","article-title":"3D neural scene representations for visuomotor control","volume-title":"Proc. Conf. Robot Learn.","author":"Li","year":"2021"},{"key":"ref33","first-page":"526","article-title":"Dex-NeRF: Using a neural radiance field to grasp transparent objects","volume-title":"Proc. Conf. Robot Learn.","author":"Ichnowski","year":"2021"},{"key":"ref34","article-title":"Reinforcement learning with neural radiance fields","author":"Driess","year":"2022"},{"key":"ref35","first-page":"7968","article-title":"Improving generalization in reinforcement learning with mixture regularization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3062311"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9562091"},{"key":"ref38","article-title":"Never stop learning: The effectiveness of fine-tuning in robotic reinforcement learning","author":"Julian","year":"2020"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.011"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3144512"},{"key":"ref41","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","year":"2018"},{"key":"ref42","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020"},{"issue":"1","key":"ref43","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":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/34.88573"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/10073596\/10077386.pdf?arnumber=10077386","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T15:21:31Z","timestamp":1707837691000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10077386\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5]]},"references-count":44,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/lra.2023.3259681","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5]]}}}