{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:03:31Z","timestamp":1777655011258,"version":"3.51.4"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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"}]},{"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. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2024.3523798","type":"journal-article","created":{"date-parts":[[2025,1,6]],"date-time":"2025-01-06T19:58:28Z","timestamp":1736193508000},"page":"379-393","source":"Crossref","is-referenced-by-count":2,"title":["Constrained Visual Representation Learning With Bisimulation Metrics for Safe Reinforcement Learning"],"prefix":"10.1109","volume":"34","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":"10.1145\/3551349.3560507"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00573-6"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3069728"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3318937"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3148868"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020211"},{"key":"ref7","article-title":"A review of safe reinforcement learning: Methods, theory and applications","author":"Gu","year":"2022","journal-title":"arXiv:2205.10330"},{"key":"ref8","volume-title":"Constrained Markov Decision Processes","author":"Altman","year":"1999"},{"key":"ref9","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Achiam"},{"key":"ref10","first-page":"1","article-title":"Projection-based constrained policy optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yang"},{"issue":"1","key":"ref11","first-page":"6070","article-title":"Risk-constrained reinforcement learning with percentile risk criteria","volume":"18","author":"Chow","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref12","article-title":"Benchmarking batch deep reinforcement learning algorithms","author":"Fujimoto","year":"2019","journal-title":"arXiv:1910.01708"},{"key":"ref13","first-page":"1110","article-title":"Learning to walk in the real world with minimal human effort","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Ha"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"ref15","first-page":"1","article-title":"Constrained policy optimization via Bayesian world models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"As"},{"key":"ref16","first-page":"1","article-title":"Safe reinforcement learning from pixels using a stochastic latent representation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hogewind"},{"key":"ref17","article-title":"A comprehensive survey of data augmentation in visual reinforcement learning","author":"Ma","year":"2022","journal-title":"arXiv:2210.04561"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3176537"},{"key":"ref19","article-title":"Unsupervised representation learning in deep reinforcement learning: A review","author":"Botteghi","year":"2022","journal-title":"arXiv:2208.14226"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3176413"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17276"},{"key":"ref22","first-page":"741","article-title":"Stochastic latent actor-critic: Deep reinforcement learning with a latent variable model","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Lee"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctt4cgngj.10"},{"key":"ref24","first-page":"1","article-title":"Temporal disentanglement of representations for improved generalisation in reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dunion"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/408"},{"key":"ref26","first-page":"162","article-title":"Metrics for finite Markov decision processes","volume-title":"Proc. 20th Conf. Uncertainty Artif. Intell.","author":"Ferns"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1137\/10080484X"},{"key":"ref28","first-page":"2170","article-title":"DeepMDP: Learning continuous latent space models for representation learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"97","author":"Gelada"},{"key":"ref29","first-page":"1","article-title":"Learning invariant representations for reinforcement learning without reconstruction","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref30","first-page":"1","article-title":"Beta-VAE: Learning basic visual concepts with a constrained variational framework","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Higgins"},{"key":"ref31","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":"ref32","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref34","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref35","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref36","first-page":"1","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kostrikov"},{"key":"ref37","volume-title":"Algorithms for Optimization","author":"Kochenderfer","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(02)00376-4"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i06.6564"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-19670-7"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/10829536.pdf?arnumber=10829536","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T19:09:54Z","timestamp":1737400194000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10829536\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/tip.2024.3523798","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}