{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T19:52:35Z","timestamp":1780084355137,"version":"3.54.0"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100015539","name":"Australian Government Higher Education Scholarship","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015539","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council Discovery Project","doi-asserted-by":"publisher","award":["DP160102037"],"award-info":[{"award-number":["DP160102037"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2021,6]]},"DOI":"10.1109\/tcds.2019.2948025","type":"journal-article","created":{"date-parts":[[2019,10,17]],"date-time":"2019-10-17T20:08:40Z","timestamp":1571342920000},"page":"262-273","source":"Crossref","is-referenced-by-count":4,"title":["Intrinsically Motivated Hierarchical Policy Learning in Multiobjective Markov Decision Processes"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2890-8929","authenticated-orcid":false,"given":"Sherif","family":"Abdelfattah","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7187-0474","authenticated-orcid":false,"given":"Kathryn","family":"Merrick","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0230-1432","authenticated-orcid":false,"given":"Jiankun","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref10","first-page":"3675","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","author":"kulkarni","year":"2016","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref12","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc 4th Int Conf Learn Represent (ICLR)"},{"key":"ref13","first-page":"695","article-title":"Efficient reinforcement learning with multiple reward functions for randomized controlled trial analysis","author":"lizotte","year":"2010","journal-title":"Proc 27th Int Conf Mach Learn (ICML)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2013.6615007"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24873-3_15"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2006.890271"},{"key":"ref18","first-page":"1","article-title":"What is intrinsic motivation? a typology of computational approaches","volume":"1","author":"oudeyer","year":"2009","journal-title":"Front Neurorobot"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1287\/moor.12.3.441"},{"key":"ref28","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-014-5458-8"},{"key":"ref27","article-title":"Intrinsic motivation and automatic curricula via asymmetric self-play","author":"sukhbaatar","year":"2017","journal-title":"arXiv e-prints arXiv 1703 05407"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2009.2015575"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2891792"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5232-5"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1002\/wrcr.20295"},{"key":"ref8","first-page":"197","article-title":"Multi-criteria reinforcement learning","volume":"98","author":"g\u00e1bor","year":"1998","journal-title":"Proc ICML"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1287\/moor.20.2.302"},{"key":"ref2","volume":"7","author":"altman","year":"1999","journal-title":"Constrained Markov Decision Processes"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/11871842_63"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2018.00065"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/0165-0114(94)90003-5"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696520"},{"key":"ref21","first-page":"969","article-title":"On finding compromise solutions in multiobjective Markov decision processes","author":"perny","year":"2010","journal-title":"Proc 19th Eur Conf Artif Intell (ECAI)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3987"},{"key":"ref23","first-page":"1297","article-title":"Linear support for multi-objective coordination graphs","author":"roijers","year":"2014","journal-title":"Proc Int Conf Auton Agents Multi agent Syst (AAMAS)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref25","first-page":"579","author":"schmidhuber","year":"2003","journal-title":"Exploring the Predictable"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274989\/9448369\/08873594.pdf?arnumber=8873594","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:54:26Z","timestamp":1652194466000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8873594\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6]]},"references-count":30,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2019.2948025","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"value":"2379-8920","type":"print"},{"value":"2379-8939","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6]]}}}