{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T00:27:15Z","timestamp":1770337635584,"version":"3.49.0"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"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":"crossref","award":["62136008"],"award-info":[{"award-number":["62136008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62293545"],"award-info":[{"award-number":["62293545"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"International Partnership Program of the Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["104GJHZ2022013GC"],"award-info":[{"award-number":["104GJHZ2022013GC"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tcyb.2025.3548821","type":"journal-article","created":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T22:44:04Z","timestamp":1743029044000},"page":"2234-2247","source":"Crossref","is-referenced-by-count":2,"title":["Balancing State Exploration and Skill Diversity in Unsupervised Skill Discovery"],"prefix":"10.1109","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7857-3058","authenticated-orcid":false,"given":"Xin","family":"Liu","sequence":"first","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9356-0610","authenticated-orcid":false,"given":"Yaran","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3560-5667","authenticated-orcid":false,"given":"Guixing","family":"Chen","sequence":"additional","affiliation":[{"name":"Industry Incubation Center, Nanjing Institute of Software Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2559-9585","authenticated-orcid":false,"given":"Haoran","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8218-9633","authenticated-orcid":false,"given":"Dongbin","family":"Zhao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3179775"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2023.3254596"},{"key":"ref4","first-page":"1","article-title":"Learning more skills through optimistic exploration","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Strouse"},{"key":"ref5","first-page":"1","article-title":"One after another: Learning incremental skills for a changing world","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Shafiullah"},{"key":"ref6","first-page":"16668","article-title":"Variational curriculum reinforcement learning for unsupervised discovery of skills","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref7","first-page":"1","article-title":"Lipschitz-constrained unsupervised skill discovery","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Park"},{"key":"ref8","first-page":"1","article-title":"Diversity is all you need: Learning skills without a reward function","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Eysenbach"},{"key":"ref9","first-page":"27225","article-title":"Controllability-aware unsupervised skill discovery","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Park"},{"key":"ref10","first-page":"1","article-title":"METRA: Scalable unsupervised RL with metric-aware abstraction","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Park"},{"key":"ref11","first-page":"39183","article-title":"Behavior contrastive learning for unsupervised skill discovery","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref12","first-page":"1","article-title":"Constrained ensemble exploration for unsupervised skill discovery","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Bai"},{"key":"ref13","first-page":"1","article-title":"URLB: Unsupervised reinforcement learning benchmark","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Laskin"},{"key":"ref14","first-page":"6736","article-title":"APS: Active pretraining with successor features","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref15","first-page":"34478","article-title":"Unsupervised reinforcement learning with contrastive intrinsic control","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Laskin"},{"key":"ref16","article-title":"Efficient exploration via state marginal matching","author":"Lee","year":"2019","journal-title":"arXiv:1906.05274"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2023.3324601"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927869"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2024.3385910"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3067028"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3198259"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref23","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctt4cgngj.10"},{"key":"ref25","first-page":"1","article-title":"Mastering visual continuous control: Improved data-augmented reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yarats"},{"key":"ref26","first-page":"9870","article-title":"Decoupling representation learning from reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Stooke"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tcns.2024.3401000"},{"key":"ref28","first-page":"1","article-title":"Adversarial imitation learning from visual observations using latent information","author":"Giammarino","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2024.3395626"},{"key":"ref30","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"},{"key":"ref31","first-page":"11920","article-title":"Reinforcement learning with prototypical representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yarats"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/tsmc.2025.3541926"},{"key":"ref33","first-page":"5062","article-title":"Self-supervised exploration via disagreement","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pathak"},{"key":"ref34","first-page":"1","article-title":"Exploration by random network distillation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Burda"},{"key":"ref35","first-page":"1","article-title":"Successor-predecessor intrinsic exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Yu"},{"key":"ref36","first-page":"1","article-title":"Task adaptation from skills: Information geometry, disentanglement, and new objectives for unsupervised reinforcement learning","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Yang"},{"key":"ref37","first-page":"1","article-title":"Learning to discover skills through guidance","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","volume":"36","author":"Kim"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.107981"},{"key":"ref39","article-title":"OpenAI gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref41","first-page":"1317","article-title":"Explore, discover and learn: Unsupervised discovery of state-covering skills","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Campos"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"ref43","first-page":"1","article-title":"Variational intrinsic control","volume-title":"Proc. Int. Conf. Learn. Represent. Workshop","author":"Gregor"},{"key":"ref44","first-page":"1","article-title":"Dynamics-aware unsupervised discovery of skills","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Sharma"},{"key":"ref45","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Stat.","author":"Gutmann"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1080\/01966324.2003.10737616"},{"key":"ref47","article-title":"Deepmind control suite","author":"Tassa","year":"2018","journal-title":"arXiv:1801.00690"},{"key":"ref48","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lillicrap"},{"key":"ref49","first-page":"1","article-title":"Fast task inference with variational intrinsic successor features","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hansen"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221036\/10974960\/10938934.pdf?arnumber=10938934","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T18:54:04Z","timestamp":1762455244000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10938934\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":49,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2025.3548821","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}