{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T14:49:22Z","timestamp":1784645362324,"version":"3.55.0"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"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":["62427812"],"award-info":[{"award-number":["62427812"]}],"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":["62521005"],"award-info":[{"award-number":["62521005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Ind. Electron."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tie.2025.3603083","type":"journal-article","created":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T17:39:06Z","timestamp":1759340346000},"page":"3104-3113","source":"Crossref","is-referenced-by-count":2,"title":["Action-Based Contrastive Unsupervised Representations for Reinforcement Learning Toward Robotic Manipulation"],"prefix":"10.1109","volume":"73","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0298-8474","authenticated-orcid":false,"given":"Qi","family":"Chen","sequence":"first","affiliation":[{"name":"Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2263-8286","authenticated-orcid":false,"given":"Chao","family":"Ye","sequence":"additional","affiliation":[{"name":"Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0493-1289","authenticated-orcid":false,"given":"Weiyang","family":"Lin","sequence":"additional","affiliation":[{"name":"Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5533-0774","authenticated-orcid":false,"given":"Zhitai","family":"Liu","sequence":"additional","affiliation":[{"name":"Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8181-6199","authenticated-orcid":false,"given":"Xinghu","family":"Yu","sequence":"additional","affiliation":[{"name":"Intelligent Control and System Research Center, Yongjiang Laboratory, Ningbo, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7707-6159","authenticated-orcid":false,"given":"Jianbin","family":"Qiu","sequence":"additional","affiliation":[{"name":"Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5554-5452","authenticated-orcid":false,"given":"Huijun","family":"Gao","sequence":"additional","affiliation":[{"name":"Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3207346"},{"key":"ref2","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2023.3274854"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abm6010"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981055"},{"key":"ref7","first-page":"1","article-title":"A framework for efficient robotic manipulation","volume-title":"Proc. Deep RL Workshop NeurIPS","author":"Zhan","year":"2021"},{"key":"ref8","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Hafner","year":"2019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adp0751"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2024.3440512"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2021.3070496"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2023.3243301"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2019.01.029"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2025.3540481"},{"key":"ref15","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":"Yarats","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3152245"},{"key":"ref17","first-page":"1992","article-title":"Visual imitation made easy","volume-title":"Proc. Conf. Robot Learn.","author":"Young","year":"2021"},{"key":"ref18","article-title":"Imitation learning: A survey of learning methods, environments and metrics","author":"Gavenski","year":"2024"},{"key":"ref19","first-page":"18459","article-title":"Behavior from the void: Unsupervised active pre-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Liu","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20729"},{"key":"ref21","first-page":"19561","article-title":"Reinforcement learning with action-free pre-training from videos","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Seo","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctt4cgngj.10"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3265607"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3176413"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3424331"},{"key":"ref28","first-page":"1","article-title":"Data-efficient reinforcement learning with self-predictive representations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Schwarzer","year":"2020"},{"key":"ref29","first-page":"1","article-title":"Prototypical contrastive learning of unsupervised representations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3289597"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.001"},{"key":"ref32","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.","volume":"5","author":"Haarnoja","year":"2018"},{"key":"ref33","article-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2019"},{"key":"ref34","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2019"},{"key":"ref35","article-title":"Deepmind control suite","author":"Tassa","year":"2018"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17276"},{"key":"ref37","first-page":"1","article-title":"Dream to control: Learning behaviors by latent imagination","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hafner","year":"2019"},{"key":"ref38","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2017"}],"container-title":["IEEE Transactions on Industrial Electronics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/41\/11385824\/11185291.pdf?arnumber=11185291","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T21:06:09Z","timestamp":1770757569000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11185291\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":38,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tie.2025.3603083","relation":{},"ISSN":["0278-0046","1557-9948"],"issn-type":[{"value":"0278-0046","type":"print"},{"value":"1557-9948","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}