{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:33:30Z","timestamp":1730266410092,"version":"3.28.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650465","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive Skill Selection for Effective Exploration of Action Space"],"prefix":"10.1109","author":[{"given":"Haoke","family":"Zhang","sequence":"first","affiliation":[{"name":"Sun Yat-Sen University,School of Systems Science and Engineering,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiyong","family":"Huang","sequence":"additional","affiliation":[{"name":"National Innovation Institute of Defense Technology Academy of Military Science,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Han","sequence":"additional","affiliation":[{"name":"National Innovation Institute of Defense Technology Academy of Military Science,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Xiong","sequence":"additional","affiliation":[{"name":"National Innovation Institute of Defense Technology Academy of Military Science,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuanfu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University,School of Systems Science and Engineering,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanjie","family":"Yang","sequence":"additional","affiliation":[{"name":"National Innovation Institute of Defense Technology Academy of Military Science,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3046646"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3142822"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3116063"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811698"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561927"},{"key":"ref9","first-page":"138","article-title":"Deep whole-body control: learning a unified policy for manipulation and locomotion","volume-title":"Conference on Robot Learning","author":"Fu"},{"key":"ref10","first-page":"2095","article-title":"Residual skill policies: Learning an adaptable skill-based action space for reinforcement learning for robotics","volume-title":"Conference on Robot Learning","author":"Rana"},{"key":"ref11","first-page":"188","article-title":"Accelerating reinforcement learning with learned skill priors","volume-title":"Conference on robot learning","author":"Pertsch"},{"key":"ref12","first-page":"38 600","article-title":"Aspire: Adaptive skill priors for reinforcement learning","volume":"35","author":"Xu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3160509"},{"article-title":"Neural probabilistic motor primitives for humanoid control","year":"2018","author":"Merel","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-13239-6"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160751"},{"article-title":"Parrot: Data-driven behavioral priors for reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Singh","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160751"},{"article-title":"Hierarchical few-shot imitation with skill transition models","volume-title":"International Conference on Learning Representations","author":"Hakhamaneshi","key":"ref19"},{"key":"ref20","first-page":"1317","article-title":"Explore, discover and learn: Unsupervised discovery of state-covering skills","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Campos"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3184805"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812140"},{"key":"ref23","first-page":"5058","article-title":"Neural dynamic policies for end-to-end sensorimotor learning","volume":"33","author":"Bahl","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"{OPAL}: Offline primitive discovery for accelerating offline reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Ajay","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00709-2"},{"key":"ref26","first-page":"3885","article-title":"Discrete compositional representations as an abstraction for goal conditioned reinforcement learning","volume":"35","author":"Islam","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3190100"},{"article-title":"Sample complexity of goal-conditioned hierarchical reinforcement learning","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Robert","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3192418"},{"key":"ref30","first-page":"1838","article-title":"Latent plans for task-agnostic offline reinforcement learning","volume-title":"Proceedings of The 6th Conference on Robot Learning","volume":"205","author":"Rosete-Beas"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981999"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3143198"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121467"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20663"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342335"},{"key":"ref36","article-title":"Data-efficient hierarchical reinforcement learning","volume":"31","author":"Nachum","year":"2018","journal-title":"Advances in neural information processing systems"},{"article-title":"Learning multi-level hierarchies with hindsight","volume-title":"International Conference on Learning Representations","author":"Levy","key":"ref37"},{"issue":"1","key":"ref38","first-page":"9989","article-title":"Behavior priors for efficient reinforcement learning","volume":"23","author":"Tirumala","year":"2022","journal-title":"The Journal of Machine Learning Research"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2024,6,30]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10650465.pdf?arnumber=10650465","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T05:21:48Z","timestamp":1725945708000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650465\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650465","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}