{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T16:03:28Z","timestamp":1772208208999,"version":"3.50.1"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Major Research Project of National Natural Science Foundation of China","award":["92267110"],"award-info":[{"award-number":["92267110"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476225"],"award-info":[{"award-number":["62476225"]}],"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":["62076202"],"award-info":[{"award-number":["62076202"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2023YFF0905604"],"award-info":[{"award-number":["2023YFF0905604"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shaanxi Province Key Research and Development Program of China","award":["2023-YBGY-354"],"award-info":[{"award-number":["2023-YBGY-354"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tcds.2024.3471645","type":"journal-article","created":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T14:27:23Z","timestamp":1727879243000},"page":"495-509","source":"Crossref","is-referenced-by-count":3,"title":["PDRL: Towards Deeper States and Further Behaviors in Unsupervised Skill Discovery by Progressive Diversity"],"prefix":"10.1109","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-2218-8550","authenticated-orcid":false,"given":"Ziming","family":"He","sequence":"first","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8378-1209","authenticated-orcid":false,"given":"Chao","family":"Song","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0905-0816","authenticated-orcid":false,"given":"Jingchen","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2180-8941","authenticated-orcid":false,"given":"Haobin","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1561\/2200000071"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2023.3326551"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2019.2957831"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3323307"},{"key":"ref5","first-page":"1430","article-title":"Goal-conditioned reinforcement learning with imagined subgoals","volume-title":"Int. Conf. Mach. Learn.","author":"Chane-Sane","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2805379"},{"key":"ref7","first-page":"1518","article-title":"Actionable models: Unsupervised offline reinforcement learning of robotic skills","volume-title":"Int. Conf. Mach. Learn.","author":"Chebotar","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3397704"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-53734-9_4"},{"key":"ref10","first-page":"1317","article-title":"Explore, discover and learn: Unsupervised discovery of state-covering skills","volume-title":"Int. Conf. Mach. Learn.","author":"Campos","year":"2020"},{"key":"ref11","article-title":"Action noise in off-policy deep reinforcement learning: Impact on exploration and performance","volume-title":"Trans. Machine Learn. Res.","author":"Hollenstein","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29139"},{"key":"ref13","first-page":"5572","article-title":"Unsupervised skill discovery with bottleneck option learning","volume-title":"Int. Conf. Mach. Learn.","author":"Kim","year":"2021"},{"key":"ref14","first-page":"1009","article-title":"Self-consistent trajectory autoencoder: Hierarchical reinforcement learning with trajectory embeddings","author":"Co-Reyes","year":"2018","journal-title":"Int. Conf. Mach. Learn."},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3171915"},{"key":"ref16","article-title":"Urlb: Unsupervised reinforcement learning benchmark","author":"Laskin","year":"2021"},{"key":"ref17","article-title":"A survey of meta-reinforcement learning","author":"Beck","year":"2023"},{"key":"ref18","article-title":"Unsupervised learning for reinforcement learning","author":"Srinivas","year":"2021"},{"key":"ref19","article-title":"Diversity is all you need: Learning skills without a reward function","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Eysenbach","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3453160"},{"key":"ref21","first-page":"3418","article-title":"Compile: Compositional imitation learning and execution","volume-title":"Int. Conf. Mach. Learn","author":"Kipf","year":"2019"},{"key":"ref22","article-title":"Variational option discovery algorithms","author":"Achiam","year":"2018"},{"key":"ref23","article-title":"Dynamics-aware unsupervised discovery of skills","volume-title":"Int. Conf. Learn. Representations","author":"Sharma","year":"2019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2022.3182877"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3296166"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3265200"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2022.3177691"},{"key":"ref28","first-page":"39034","article-title":"Unsupervised skill discovery via recurrent skill training","volume":"35","author":"Jiang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref29","first-page":"1515","article-title":"Automatic goal generation for reinforcement learning agents","author":"Florensa","year":"2018","journal-title":"Int. Conf. Mach. Learn."},{"key":"ref30","first-page":"4999","article-title":"Continual learning of control primitives: Skill discovery via reset-games","volume":"33","author":"Xu","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref31","article-title":"The information geometry of unsupervised reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Eysenbach","year":"2021"},{"key":"ref32","article-title":"Variational intrinsic control","author":"Gregor","year":"2016"},{"key":"ref33","article-title":"Deep recurrent q-learning for partially observable MDPS","volume-title":"Proc. AAAI fall Symp. Ser.","author":"Hausknecht","year":"2015"},{"issue":"320","key":"ref34","first-page":"201","article-title":"The im algorithm: A variational approach to information maximization","volume":"16","author":"Barber","year":"2004","journal-title":"Adv. Neur. Inf. Process. Syst."},{"key":"ref35","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018","journal-title":"Int. Conf. Mach. Learn"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.15703"},{"key":"ref37","article-title":"Hindsight experience replay","volume":"30","author":"Andrychowicz","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref38","article-title":"The information geometry of unsupervised reinforcement learning","volume-title":"Int. Conf. Learn. Representations","author":"Eysenbach","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/MWSCAS.2017.8053243"},{"key":"ref40","article-title":"Theory and evaluation metrics for learning disentangled representations","author":"Do","year":"2019"},{"key":"ref41","article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","author":"Plappert","year":"2018"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-06116-1"},{"key":"ref43","first-page":"8532","article-title":"Plangan: Model-based planning with sparse rewards and multiple goals","volume":"33","author":"Charlesworth","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref44","article-title":"Bilinear value networks","author":"Hong","year":"2022"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7274989\/11023974\/10704571.pdf?arnumber=10704571","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T18:33:00Z","timestamp":1765909980000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10704571\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":44,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2024.3471645","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"value":"2379-8920","type":"print"},{"value":"2379-8939","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}