{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:17:11Z","timestamp":1759331831699,"version":"3.37.3"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"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","62176259"],"award-info":[{"award-number":["62373364","62176259"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013064","name":"Key Research and Development Program of Jiangsu Province","doi-asserted-by":"publisher","award":["BE2022095"],"award-info":[{"award-number":["BE2022095"]}],"id":[{"id":"10.13039\/501100013064","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tsmc.2024.3449294","type":"journal-article","created":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T18:32:56Z","timestamp":1726079576000},"page":"7382-7395","source":"Crossref","is-referenced-by-count":3,"title":["Clustering-Driven State Embedding for Reinforcement Learning Under Visual Distractions"],"prefix":"10.1109","volume":"54","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0615-0838","authenticated-orcid":false,"given":"Rongrong","family":"Wang","sequence":"first","affiliation":[{"name":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"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, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5327-1088","authenticated-orcid":false,"given":"Xuesong","family":"Wang","sequence":"additional","affiliation":[{"name":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3089425"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3287655"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3098451"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1923-7"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1126\/science.abq1158"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-022-05172-4"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3245212"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2022.3214221"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2931946"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3259681"},{"article-title":"CURL: Contrastive unsupervised representations for reinforcement learning","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Laskin","key":"ref13"},{"key":"ref14","first-page":"1","article-title":"Data-efficient reinforcement learning with self-predictive representations","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"Schwarzer"},{"key":"ref15","first-page":"19884","article-title":"Reinforcement learning with augmented data","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Laskin"},{"key":"ref16","first-page":"1","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"Yarats"},{"key":"ref17","first-page":"1","article-title":"Mastering visual continuous control: Improved data-augmented reinforcement learning","volume-title":"Proc. 10th Int. Conf. Learn. Represent.","author":"Yarats"},{"key":"ref18","article-title":"The distracting control suite\u2014A challenging benchmark for reinforcement learning from pixels","author":"Stone","year":"2021","journal-title":"arXiv: 2101.02722"},{"key":"ref19","first-page":"1","article-title":"Learning invariant representations for reinforcement learning without reconstruction","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref20","first-page":"1","article-title":"Contrastive behavioral similarity embeddings for generalization in reinforcement learning","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"Agarwal"},{"key":"ref21","first-page":"4956","article-title":"DreamerPro: Reconstruction-free model-based reinforcement learning with prototypical representations","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Deng"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.26063"},{"key":"ref23","first-page":"478","article-title":"Unsupervised deep embedding for clustering analysis","volume-title":"Proc. 33th Int. Conf. Mach. Learn.","author":"Xie"},{"key":"ref24","first-page":"2292","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","volume-title":"Proc. 26th Int. Conf. Neural Inf. Process. Syst.","author":"Cuturi"},{"key":"ref25","article-title":"Deepmind control suite","author":"Tassa","year":"2018","journal-title":"arXiv:1801.00690"},{"key":"ref26","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/243"},{"key":"ref28","first-page":"3861","article-title":"Towards k-means friendly spaces: Simultaneous deep learning and clustering","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2019.2945232"},{"key":"ref30","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Caron"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539391"},{"key":"ref32","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref33","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref34","first-page":"11920","article-title":"Reinforcement learning with prototypical representations","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Yarats"},{"key":"ref35","article-title":"The 2017 DAVIS challenge on video object segmentation","author":"Pont-Tuset","year":"2017","journal-title":"arXiv:1704.00675"},{"key":"ref36","first-page":"30693","article-title":"Look where you look! Saliency-guided Q-networks for generalization in visual reinforcement learning","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Bertoin"},{"key":"ref37","first-page":"733","article-title":"MaDi: Learning to mask distractions for generalization in visual deep reinforcement learning","volume-title":"Proc. 23rd Int. Conf. Auton. Agents Multiagent Syst.","author":"Grooten"},{"key":"ref38","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Hafner"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3144512"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221021\/10758325\/10677476.pdf?arnumber=10677476","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:35:43Z","timestamp":1732667743000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10677476\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":39,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2024.3449294","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"type":"print","value":"2168-2216"},{"type":"electronic","value":"2168-2232"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}