{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:26:49Z","timestamp":1766068009088,"version":"3.44.0"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2021ZD0112904"],"award-info":[{"award-number":["2021ZD0112904"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172426"],"award-info":[{"award-number":["62172426"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/tai.2024.3413692","type":"journal-article","created":{"date-parts":[[2024,6,13]],"date-time":"2024-06-13T14:27:43Z","timestamp":1718288863000},"page":"5530-5539","source":"Crossref","is-referenced-by-count":2,"title":["Self-Supervised Exploration via Temporal Inconsistency in Reinforcement Learning"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5151-3381","authenticated-orcid":false,"given":"Zijian","family":"Gao","sequence":"first","affiliation":[{"name":"School of Computer, National University of Defense Technology, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5997-5169","authenticated-orcid":false,"given":"Kele","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer, National University of Defense Technology, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1385-0074","authenticated-orcid":false,"given":"Yuanzhao","family":"Zhai","sequence":"additional","affiliation":[{"name":"School of Computer, National University of Defense Technology, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1236-8318","authenticated-orcid":false,"given":"Bo","family":"Ding","sequence":"additional","affiliation":[{"name":"School of Computer, National University of Defense Technology, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7587-8905","authenticated-orcid":false,"given":"Dawei","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Computer, National University of Defense Technology, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6003-5748","authenticated-orcid":false,"given":"Xinjun","family":"Mao","sequence":"additional","affiliation":[{"name":"School of Computer, National University of Defense Technology, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3245-1901","authenticated-orcid":false,"given":"Huaimin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer, National University of Defense Technology, Changsha, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/203330.203343"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121959"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121897"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121234"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.108100"},{"key":"ref8","article-title":"Exploration by random network distillation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Burda","year":"2019"},{"key":"ref9","article-title":"Large-scale study of curiosity-driven learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Burda","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1006\/ceps.1999.1020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/1064546053278973"},{"key":"ref12","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":"ref13","first-page":"5062","article-title":"Self-supervised exploration via disagreement","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pathak","year":"2019"},{"key":"ref14","first-page":"1471","article-title":"Unifying count-based exploration and intrinsic motivation","volume":"29","author":"Bellemare","year":"2016","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/344"},{"key":"ref16","first-page":"2721","article-title":"Count-based exploration with neural density models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ostrovski","year":"2017"},{"key":"ref17","first-page":"206","article-title":"Exploration in model-based reinforcement learning by empirically estimating learning progress","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Lopes","year":"2012"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143932"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"article-title":"Incentivizing exploration in reinforcement learning with deep predictive models","year":"2015","author":"Stadie","key":"ref20"},{"key":"ref21","first-page":"5306","article-title":"Active world model learning with progress curiosity","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-55509-6_4"},{"key":"ref23","first-page":"13285","article-title":"Reducing variance in temporal-difference value estimation via ensemble of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liang","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.simpa.2020.100022"},{"key":"ref25","first-page":"14961","article-title":"See, hear, explore: Curiosity via audio-visual association","volume":"33","author":"Dean","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"article-title":"Curiosity-driven exploration in deep reinforcement learning via Bayesian neural networks","year":"2016","author":"Houthooft","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s12064-011-0142-z"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017984413808"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/509907.509965"},{"issue":"152","key":"ref30","first-page":"1","article-title":"Intrinsically motivated goal exploration processes with automatic curriculum learning","volume":"23","author":"Forestier","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2018.00030"},{"article-title":"Unsupervised learning of goal spaces for intrinsically motivated goal exploration","year":"2018","author":"P\u00e9r\u00e9","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45014-9_1"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/4275623"},{"key":"ref35","article-title":"URLB: Unsupervised reinforcement learning benchmark","volume-title":"Proc. Deep RL Workshop NeurIPS","author":"Laskin","year":"2021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2006.890271"},{"article-title":"Deep intrinsically motivated continuous actor-critic for efficient robotic visuomotor skill learning","year":"2018","author":"Hafez","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2011.6037356"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636297"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1504\/IJGUC.2020.110053"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1137\/18M1183480"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.09.021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3121765"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1137\/070697835"},{"key":"ref45","first-page":"1329","article-title":"Maximum-margin matrix factorization","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 17","author":"Srebro","year":"2005"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00400"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref47"},{"article-title":"Continuous control with deep reinforcement learning","year":"2015","author":"Lillicrap","key":"ref48"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref50","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yarats","year":"2020"},{"key":"ref51","article-title":"Data-efficient reinforcement learning with self-predictive representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Schwarzer","year":"2020"},{"key":"ref52","first-page":"11 920\u201311 931","article-title":"Reinforcement learning with prototypical representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yarats","year":"2021"},{"article-title":"Efficient exploration via state marginal matching","year":"2019","author":"Lee","key":"ref53"},{"article-title":"Diversity is all you need: Learning skills without a reward function","year":"2018","author":"Eysenbach","key":"ref54"},{"key":"ref55","first-page":"6736","article-title":"APS: Active pretraining with successor features","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu","year":"2021"},{"key":"ref56","first-page":"176","article-title":"Averaged-DQN: Variance reduction and stabilization for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Anschel","year":"2017"},{"article-title":"EUCLID: Towards efficient unsupervised reinforcement learning with multi-choice dynamics model","year":"2022","author":"Yuan","key":"ref57"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9078688\/10751744\/10557253.pdf?arnumber=10557253","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:09:15Z","timestamp":1755911355000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10557253\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":57,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tai.2024.3413692","relation":{},"ISSN":["2691-4581"],"issn-type":[{"type":"electronic","value":"2691-4581"}],"subject":[],"published":{"date-parts":[[2024,11]]}}}