{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T04:53:15Z","timestamp":1749099195435,"version":"3.37.3"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"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":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1109\/tcds.2022.3177691","type":"journal-article","created":{"date-parts":[[2022,5,25]],"date-time":"2022-05-25T19:39:49Z","timestamp":1653507589000},"page":"1879-1890","source":"Crossref","is-referenced-by-count":2,"title":["Concurrent Skill Composition Using Ensemble of Primitive Skills"],"prefix":"10.1109","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4348-9937","authenticated-orcid":false,"given":"Paresh","family":"Dhakan","sequence":"first","affiliation":[{"name":"Intelligent Systems Research Centre, University of Ulster, Londonderry, U.K"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7187-0474","authenticated-orcid":false,"given":"Kathryn","family":"Kasmarik","sequence":"additional","affiliation":[{"name":"Australian Defence Force Academy, University of New South Wales at Canberra, Canberra, ACT, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2189-3608","authenticated-orcid":false,"given":"Philip","family":"Vance","sequence":"additional","affiliation":[{"name":"Intelligent Systems Research Centre, University of Ulster, Londonderry, U.K"}]},{"given":"I\u00f1aki","family":"Ra\u00f1\u00f3","sequence":"additional","affiliation":[{"name":"Department of Mærsk Mc Kinney Møller, University of Southern Denmark, Odense, Denmark"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0642-2357","authenticated-orcid":false,"given":"Nazmul","family":"Siddique","sequence":"additional","affiliation":[{"name":"Intelligent Systems Research Centre, University of Ulster, Londonderry, U.K"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/bfb0026762"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.7763\/IJCCE.2014.V3.299"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2019.00115"},{"key":"ref4","first-page":"1","article-title":"What\u2019s interesting","author":"Schmidhuber","year":"1997","journal-title":"Abstract Collection of SNOWBIRD: Machines That Learn"},{"key":"ref5","first-page":"127","article-title":"Intelligent adaptive curiosity: A source of self-development","volume":"117","author":"Oudeyer","year":"2004","journal-title":"Science"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32375-1_3"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2016.2538961"},{"key":"ref8","first-page":"6401","article-title":"Composing value functions in reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"van Niekerk"},{"key":"ref9","first-page":"93","article-title":"An approach to lifelong reinforcement learning through multiple environments","volume-title":"Proc. 6th Eur. Workshop Learn. Robot (EWLR)","author":"Tanaka"},{"key":"ref10","first-page":"2850","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. 33rd Int. Conf. Mach. Learn. (ICML)","volume":"4","author":"Mnih"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1613\/jair.898"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2010.936952"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_5"},{"key":"ref14","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"Taylor","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992700"},{"key":"ref16","first-page":"1","article-title":"Composing complex skills by learning transition policies","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lee"},{"key":"ref17","first-page":"1","article-title":"Composing ensembles of policies with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Qureshi"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065799000125"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2019.2947896"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21236\/ADA440079"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2018.00063"},{"key":"ref22","article-title":"Paired open-ended trailblazer (POET): Endlessly generating increasingly complex and diverse learning environments and their solutions","author":"Wang","year":"2019","journal-title":"arXiv:1901.01753"},{"key":"ref23","first-page":"220","article-title":"Hierarchical solution of Markov decision process using macro-actions","volume-title":"Proc. 14th Conf. Uncertainty Artif. Intell.","author":"Hauskrecht"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"volume-title":"Automated discovery of options in reinforcement learning","year":"2004","author":"Stolle","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44914-0_2"},{"issue":"3","key":"ref28","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1023\/A:1008858222277","article-title":"Module-based reinforcement learning: Experiments with a real robot","volume":"5","author":"Kalm\u00e1r","year":"1998","journal-title":"Auton. Robots"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.1996.568989"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0026708"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-23807-0_6"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10744"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-020-09451-0"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/tcds.2016.2607018"},{"key":"ref35","first-page":"1","article-title":"Progressive reinforcement learning with distillation for multi-skilled motion control","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Berseth"},{"key":"ref36","first-page":"1761","article-title":"Mix and match\u2014Agent curricula for reinforcement learning","volume-title":"Proc. 35th Int. Conf. Mach. Learn. (ICML)","volume":"3","author":"Czarnecki"},{"key":"ref37","first-page":"3686","article-title":"MCP: Learning Composable hierarchical control with multiplicative compositional policies","volume-title":"Advances in Neural Information Processing Systems","author":"Peng","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460756"},{"key":"ref39","first-page":"1856","article-title":"Compositionality of optimal control laws","volume":"3","author":"Todorov","year":"2009","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014975"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-89187-1"},{"key":"ref42","first-page":"656","article-title":"Q-decomposition for reinforcement learning agents","volume-title":"Proc. 20th Int. Conf. Mach. Learn.","author":"Russell"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1137\/0330046"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/S0031-3203(99)00138-7"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-32260-3_3"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5223-6"},{"key":"ref48","article-title":"Learning to compose skills","volume-title":"Advances in Neural Information Processing Systems","author":"Sahni","year":"2017"},{"key":"ref49","article-title":"Control what you can intrinsically motivated task-planning agent","volume-title":"Advances in Neural Information Processing Systems","author":"Blaes","year":"2019"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2019.8850713"},{"key":"ref51","first-page":"2372","article-title":"CURIOUS: Intrinsically motivated modular multi-goal reinforcement learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Colas"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274989\/10360134\/09781602.pdf?arnumber=9781602","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T23:49:58Z","timestamp":1705016998000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9781602\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":51,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2022.3177691","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"type":"print","value":"2379-8920"},{"type":"electronic","value":"2379-8939"}],"subject":[],"published":{"date-parts":[[2023,12]]}}}