{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T04:48:12Z","timestamp":1770353292025,"version":"3.49.0"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"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":["62373364"],"award-info":[{"award-number":["62373364"]}],"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":["62176259"],"award-info":[{"award-number":["62176259"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Program of Jiangsu Province","award":["BE2022095"],"award-info":[{"award-number":["BE2022095"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tcds.2025.3540115","type":"journal-article","created":{"date-parts":[[2025,2,7]],"date-time":"2025-02-07T13:46:27Z","timestamp":1738935987000},"page":"1011-1021","source":"Crossref","is-referenced-by-count":1,"title":["Visual Reinforcement Learning Based on Multiview Optimization Aggregation"],"prefix":"10.1109","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5327-1088","authenticated-orcid":false,"given":"Xuesong","family":"Wang","sequence":"first","affiliation":[{"name":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, Xuzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8771-7498","authenticated-orcid":false,"given":"Ruyi","family":"Lu","sequence":"additional","affiliation":[{"name":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, Xuzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3827-8363","authenticated-orcid":false,"given":"Hengrui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, Xuzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2022-9999","authenticated-orcid":false,"given":"Yuhu","family":"Cheng","sequence":"additional","affiliation":[{"name":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, Xuzhou, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hafner","year":"2019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17276"},{"key":"ref3","article-title":"Is a good representation sufficient for sample efficient reinforcement learning?","author":"Du","year":"2019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/mcs.2025.3534477"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17276"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3313206"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2024.3383952"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2022.3218940"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3157892"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3286465"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3272741"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3121078"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3156367"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2024.3390755"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3336525"},{"key":"ref17","article-title":"Observational overfitting in reinforcement learning","author":"Song","year":"2019"},{"key":"ref18","first-page":"23178","article-title":"Iso-dream: isolating and leveraging noncontrollable visual dynamics in world models","volume-title":"Proc. Neural Inf. Process. Syst.","volume":"35","author":"Pan","year":"2022"},{"key":"ref19","first-page":"1332","article-title":"Masked world models for visual control","volume-title":"Proc. Conf. Robot Learn.","author":"Seo","year":"2023"},{"key":"ref20","first-page":"25476","article-title":"Mastering atari games with limited data","volume-title":"Proc. Neural Inf. Process. Syst.","volume":"34","author":"Ye","year":"2021"},{"key":"ref21","article-title":"Image augmentation is all you need: regularizing deep reinforcement learning from pixels","author":"Kostrikov","year":"2020"},{"key":"ref22","first-page":"19884","article-title":"Reinforcement learning with augmented data","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Laskin","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561103"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3253799"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3327777"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447060"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3376720"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctt4cgngj.10"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref30","first-page":"5276","article-title":"Playvirtual: augmenting cycle-consistent virtual trajectories for reinforcement learning","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Yu","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3176413"},{"key":"ref32","first-page":"25117","article-title":"Mask-based latent reconstruction for reinforcement learning","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Yu","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3041469"},{"key":"ref34","first-page":"1856","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":"ref35","article-title":"Deepmind control suite","author":"Tassa","year":"2018"},{"key":"ref36","article-title":"Contrastive behavioral similarity embeddings for generalization in reinforcement learning","author":"Agarwal","year":"2021"},{"key":"ref37","first-page":"19561","article-title":"Reinforcement learning with action-free pre-training from videos","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Seo","year":"2022"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7274989\/11118941\/10878454.pdf?arnumber=10878454","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T17:46:08Z","timestamp":1754588768000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10878454\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":37,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2025.3540115","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"value":"2379-8920","type":"print"},{"value":"2379-8939","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}