{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:24:22Z","timestamp":1760711062068,"version":"3.37.3"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62250001","62231002","61922009","61876013","61925105"],"award-info":[{"award-number":["62250001","62231002","61922009","61876013","61925105"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2023,3]]},"DOI":"10.1109\/tsmc.2022.3209070","type":"journal-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:45:49Z","timestamp":1664567149000},"page":"1932-1944","source":"Crossref","is-referenced-by-count":9,"title":["A Task-Agnostic Regularizer for Diverse Subpolicy Discovery in Hierarchical Reinforcement Learning"],"prefix":"10.1109","volume":"53","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0703-3978","authenticated-orcid":false,"given":"Liangyu","family":"Huo","sequence":"first","affiliation":[{"name":"School of Electronic and Information Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zulin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0277-3301","authenticated-orcid":false,"given":"Mai","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhang","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Oxford, Oxford, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. ICML","author":"Mnih"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2931946"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2020.3041775"},{"key":"ref5","article-title":"Meta learning shared hierarchies","volume-title":"arXiv:1710.09767","author":"Frans","year":"2017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10744"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2017.2723483"},{"key":"ref9","article-title":"Learning and transfer of modulated locomotor controllers","volume-title":"arXiv:1610.05182","author":"Heess","year":"2016"},{"key":"ref10","first-page":"3540","article-title":"FeUdal networks for hierarchical reinforcement learning","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Vezhnevets"},{"key":"ref11","article-title":"Stochastic neural networks for hierarchical reinforcement learning","volume-title":"arXiv:1704.03012","author":"Florensa","year":"2017"},{"key":"ref12","article-title":"Near-optimal representation learning for hierarchical reinforcement learning","volume-title":"arXiv:1810.01257","author":"Nachum","year":"2018"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref15","article-title":"Diversity is all you need: Learning skills without a reward function","volume-title":"arXiv:1802.06070","author":"Eysenbach","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053393"},{"key":"ref17","first-page":"271","article-title":"Feudal reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dayan"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2014.2358639"},{"key":"ref19","first-page":"895","article-title":"Building portable options: Skill transfer in reinforcement learning","volume-title":"Proc. IJCAI","volume":"7","author":"Konidaris"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3453160"},{"key":"ref21","article-title":"FeUdal networks for hierarchical reinforcement learning","volume-title":"arXiv:1703.01161","author":"Vezhnevets","year":"2017"},{"key":"ref22","article-title":"Unsupervised skill discovery with bottleneck option learning","volume-title":"arXiv:2106.14305","author":"Kim","year":"2021"},{"key":"ref23","article-title":"Dynamics-aware unsupervised discovery of skills","volume-title":"arXiv:1907.01657","author":"Sharma","year":"2019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.053"},{"key":"ref25","first-page":"7740","article-title":"Retrieval-augmented reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Goyal"},{"key":"ref26","article-title":"Latent space policies for hierarchical reinforcement learning","volume-title":"arXiv:1804.02808","author":"Haarnoja","year":"2018"},{"key":"ref27","first-page":"6736","article-title":"APS: Active pretraining with successor features","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref28","first-page":"3486","article-title":"Strategic attentive writer for learning macro-actions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vezhnevets"},{"key":"ref29","first-page":"29861","article-title":"Discovery of options via meta-learned subgoals","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Veeriah"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref31","article-title":"Learning robust rewards with adversarial inverse reinforcement learning","volume-title":"arXiv:1710.11248","author":"Fu","year":"2017"},{"key":"ref32","article-title":"Meta-reinforcement learning of structured exploration strategies","volume-title":"arXiv:1802.07245","author":"Gupta","year":"2018"},{"key":"ref33","first-page":"1","article-title":"Learning an embedding space for transferable robot skills","volume-title":"Proc. ICLR","author":"Hausman"},{"key":"ref34","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rakelly"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3156\/jsoft.29.5_177_2"},{"key":"ref36","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"arXiv:1801.01290","author":"Haarnoja","year":"2018"},{"key":"ref37","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume-title":"Proc. AAAI","volume":"8","author":"Ziebart"},{"key":"ref38","article-title":"Continuous control with deep reinforcement learning","volume-title":"arXiv:1509.02971","author":"Lillicrap","year":"2015"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2926806"},{"key":"ref40","first-page":"685","article-title":"Deep learning with elastic averaging SGD","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref41","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"arXiv:1703.03400","author":"Finn","year":"2017"},{"key":"ref42","article-title":"Proximal policy optimization algorithms","volume-title":"arXiv:1707.06347","author":"Schulman","year":"2017"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref44","article-title":"Simulated car racing championship: Competition software manual","volume-title":"arXiv:1304.1672","author":"Loiacono","year":"2013"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221021\/10045571\/09906972.pdf?arnumber=9906972","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T22:33:03Z","timestamp":1705962783000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9906972\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3]]},"references-count":44,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2022.3209070","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"type":"print","value":"2168-2216"},{"type":"electronic","value":"2168-2232"}],"subject":[],"published":{"date-parts":[[2023,3]]}}}