{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:23:50Z","timestamp":1740169430864,"version":"3.37.3"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3491339","type":"journal-article","created":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T18:38:14Z","timestamp":1730745494000},"page":"163042-163055","source":"Crossref","is-referenced-by-count":0,"title":["Discovering and Exploiting Skills in Hierarchical Reinforcement Learning"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5828-5008","authenticated-orcid":false,"given":"Zhigang","family":"Huang","sequence":"first","affiliation":[{"name":"China Ship Scientific Research Center, Wuxi, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00433-9"},{"article-title":"Option discovery using deep skill chaining","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Bagaria","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981607"},{"article-title":"Composing complex skills by learning transition policies","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lee","key":"ref4"},{"key":"ref5","first-page":"5572","article-title":"Unsupervised skill discovery with bottleneck option learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3059912"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/401"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20645"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1002\/aisy.202200168"},{"key":"ref10","first-page":"1009","article-title":"Self-consistent trajectory autoencoder: Hierarchical reinforcement learning with trajectory embeddings","volume-title":"Proc. Int. Conf. Machin. Learn.","author":"Co-Reyes"},{"article-title":"Weakly-supervised learning of disentangled and interpretable skills for hierarchical reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3171915"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2022.3209070"},{"key":"ref14","article-title":"Learning diverse options via InfoMax termination critic","author":"Kanagawa","year":"2020","journal-title":"arXiv:2010.02756"},{"key":"ref15","first-page":"4999","article-title":"Continual learning of control primitives: Skill discovery via reset-games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Xu"},{"key":"ref16","first-page":"2295","article-title":"A Laplacian framework for option discovery in reinforcement learning","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Machado"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014992"},{"article-title":"Diversity is all you need: Learning skills without a reward function","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Eysenbach","key":"ref18"},{"key":"ref19","article-title":"Diversity-enriched option-critic","author":"Kamat","year":"2020","journal-title":"arXiv:2011.02565"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107130"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.32473\/flairs.v35i.130720"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.01.030"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.330110009"},{"article-title":"Efficient hierarchical exploration with stable subgoal representation learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","key":"ref24"},{"key":"ref25","first-page":"3675","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kulkarni"},{"article-title":"Learning subgoal representations with slow dynamics","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/433"},{"key":"ref28","first-page":"3540","article-title":"Feudal networks for hierarchical reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Vezhnevets"},{"key":"ref29","article-title":"Variational option discovery algorithms","author":"Achiam","year":"2018","journal-title":"arXiv:1807.10299"},{"article-title":"Stochastic neural networks for hierarchical reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Florensa","key":"ref30"},{"article-title":"Hierarchical reinforcement learning by discovering intrinsic options","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang","key":"ref31"},{"key":"ref32","first-page":"1","article-title":"Explore, discover and learn: Unsupervised discovery of state-covering skills","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cam\u00fa\u00f1ez"},{"article-title":"Dynamics-aware unsupervised discovery of skills","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Sharma","key":"ref33"},{"key":"ref34","article-title":"SOAC: The soft option actor-critic architecture","author":"Li","year":"2020","journal-title":"arXiv:2006.14363"},{"key":"ref35","first-page":"3173","article-title":"Learning with options that terminate off-policy","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Harutyunyan"},{"key":"ref36","first-page":"1409","article-title":"Hierarchical reinforcement learning with advantage-based auxiliary rewards","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6003"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888921000035"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11831"},{"key":"ref40","first-page":"2012","article-title":"DAC: The double actor-critic architecture for learning options","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/MWSCAS.2017.8053243"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5871"},{"key":"ref43","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref44","article-title":"Variational intrinsic control","author":"Gregor","year":"2016","journal-title":"arXiv:1611.07507"},{"key":"ref45","first-page":"158","article-title":"Unsupervised real-time control through variational empowerment","volume-title":"Proc. Int. Symp. Robot. Res.","author":"Karl"},{"key":"ref46","article-title":"Flexible option learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Klissarov"},{"article-title":"Hierarchical reinforcement learning via advantage-weighted information maximization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Osa","key":"ref47"},{"key":"ref48","first-page":"85","article-title":"Generating adjacency-constrained subgoals in hierarchical reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Zhang"},{"key":"ref49","first-page":"3303","article-title":"Data-efficient hierarchical reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Nachum"},{"key":"ref50","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.","author":"Haarnoja"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10742376.pdf?arnumber=10742376","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T05:27:21Z","timestamp":1732685241000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10742376\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3491339","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2024]]}}}