{"id":"https://openalex.org/W2981300409","doi":"https://doi.org/10.1109/tcds.2019.2948025","title":"Intrinsically Motivated Hierarchical Policy Learning in Multiobjective Markov Decision Processes","display_name":"Intrinsically Motivated Hierarchical Policy Learning in Multiobjective Markov Decision Processes","publication_year":2019,"publication_date":"2019-10-17","ids":{"openalex":"https://openalex.org/W2981300409","doi":"https://doi.org/10.1109/tcds.2019.2948025","mag":"2981300409"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2019.2948025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2019.2948025","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cognitive and Developmental Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://unsworks.unsw.edu.au/bitstreams/b77d48a1-4521-49c5-abf0-2f0c595f0a46/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066773785","display_name":"Sherif Abdelfattah","orcid":"https://orcid.org/0000-0003-2890-8929"},"institutions":[{"id":"https://openalex.org/I188329596","display_name":"University of Canberra","ror":"https://ror.org/04s1nv328","country_code":"AU","type":"education","lineage":["https://openalex.org/I188329596"]},{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sherif Abdelfattah","raw_affiliation_strings":["School of Engineering and Information Technology, University of New South Wales, Canberra, ACT, Australia"],"raw_orcid":"https://orcid.org/0000-0003-2890-8929","affiliations":[{"raw_affiliation_string":"School of Engineering and Information Technology, University of New South Wales, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I188329596","https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111548712","display_name":"Kathryn Merrick","orcid":null},"institutions":[{"id":"https://openalex.org/I188329596","display_name":"University of Canberra","ror":"https://ror.org/04s1nv328","country_code":"AU","type":"education","lineage":["https://openalex.org/I188329596"]},{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Kathryn Merrick","raw_affiliation_strings":["School of Engineering and Information Technology, University of New South Wales, Canberra, ACT, Australia"],"raw_orcid":"https://orcid.org/0000-0001-7187-0474","affiliations":[{"raw_affiliation_string":"School of Engineering and Information Technology, University of New South Wales, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I188329596","https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075234257","display_name":"Jiankun Hu","orcid":"https://orcid.org/0000-0003-0230-1432"},"institutions":[{"id":"https://openalex.org/I188329596","display_name":"University of Canberra","ror":"https://ror.org/04s1nv328","country_code":"AU","type":"education","lineage":["https://openalex.org/I188329596"]},{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jiankun Hu","raw_affiliation_strings":["School of Engineering and Information Technology, University of New South Wales, Canberra, ACT, Australia"],"raw_orcid":"https://orcid.org/0000-0003-0230-1432","affiliations":[{"raw_affiliation_string":"School of Engineering and Information Technology, University of New South Wales, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I188329596","https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4339,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.7263033,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"13","issue":"2","first_page":"262","last_page":"273"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9549000263214111,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9437999725341797,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8457080125808716},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8454626798629761},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.828359842300415},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6424407958984375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5135464668273926},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48928043246269226},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.48752257227897644},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.45200082659721375},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4236016869544983},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08824461698532104}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8457080125808716},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8454626798629761},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.828359842300415},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6424407958984375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5135464668273926},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48928043246269226},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.48752257227897644},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.45200082659721375},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4236016869544983},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08824461698532104},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcds.2019.2948025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2019.2948025","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cognitive and Developmental Systems","raw_type":"journal-article"},{"id":"pmh:oai:unsworks.library.unsw.edu.au:1959.4/unsworks_61809","is_oa":true,"landing_page_url":"http://hdl.handle.net/1959.4/unsworks_61809","pdf_url":"https://unsworks.unsw.edu.au/bitstreams/b77d48a1-4521-49c5-abf0-2f0c595f0a46/download","source":{"id":"https://openalex.org/S4306401737","display_name":"UNSWorks (University of New South Wales, Sydney, Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40053085","host_organization_name":"Australian Defence Force Academy","host_organization_lineage":["https://openalex.org/I40053085"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Cognitive and Developmental Systems, Special Issue on Continual Unsupervised Sensorimotor Learning, 13, 2, 262-273","raw_type":"http://purl.org/coar/resource_type/c_6501"}],"best_oa_location":{"id":"pmh:oai:unsworks.library.unsw.edu.au:1959.4/unsworks_61809","is_oa":true,"landing_page_url":"http://hdl.handle.net/1959.4/unsworks_61809","pdf_url":"https://unsworks.unsw.edu.au/bitstreams/b77d48a1-4521-49c5-abf0-2f0c595f0a46/download","source":{"id":"https://openalex.org/S4306401737","display_name":"UNSWorks (University of New South Wales, Sydney, Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40053085","host_organization_name":"Australian Defence Force Academy","host_organization_lineage":["https://openalex.org/I40053085"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Cognitive and Developmental Systems, Special Issue on Continual Unsupervised Sensorimotor Learning, 13, 2, 262-273","raw_type":"http://purl.org/coar/resource_type/c_6501"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1627854046","display_name":"User-task co-adaptation for effective interactive simulation environments","funder_award_id":"DP160102037","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2981300409.pdf","grobid_xml":"https://content.openalex.org/works/W2981300409.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W194486498","https://openalex.org/W291243768","https://openalex.org/W1482041209","https://openalex.org/W1506085041","https://openalex.org/W1518318201","https://openalex.org/W1518931405","https://openalex.org/W1569930087","https://openalex.org/W2000514530","https://openalex.org/W2004883573","https://openalex.org/W2012612381","https://openalex.org/W2032100464","https://openalex.org/W2032950725","https://openalex.org/W2047777882","https://openalex.org/W2060846151","https://openalex.org/W2082511574","https://openalex.org/W2101524054","https://openalex.org/W2102660061","https://openalex.org/W2117428849","https://openalex.org/W2127474646","https://openalex.org/W2145339207","https://openalex.org/W2173248099","https://openalex.org/W2182714085","https://openalex.org/W2257979135","https://openalex.org/W2603088459","https://openalex.org/W2897714018","https://openalex.org/W2919115771","https://openalex.org/W2963262099","https://openalex.org/W2963577640","https://openalex.org/W2963761387","https://openalex.org/W2963864421","https://openalex.org/W3103262232","https://openalex.org/W4214717370","https://openalex.org/W6610454638","https://openalex.org/W6628934745","https://openalex.org/W6650587873","https://openalex.org/W6684921986","https://openalex.org/W6685713626","https://openalex.org/W6703271639","https://openalex.org/W6735789912"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W4225269853"],"abstract_inverted_index":{"The":[0],"multiobjective":[1,42,224],"Markov":[2],"decision":[3],"processes":[4],"(MOMDPs)":[5],"are":[6],"sequential":[7],"decision-making":[8],"problems":[9],"that":[10,16,54,122,216],"involve":[11],"multiple":[12],"conflicting":[13],"reward":[14,90],"functions":[15],"cannot":[17,28,69],"be":[18,29],"optimized":[19],"simultaneously":[20],"without":[21],"a":[22,32,48,115,119,143,172,185,228],"compromise.":[23],"This":[24,95],"type":[25],"of":[26,51,66,85,127,188],"problem":[27],"solved":[30],"by":[31],"single":[33],"optimal":[34,52],"policy":[35,105,129,165,203],"as":[36],"in":[37,60,76,98,135,193,209],"the":[38,62,77,83,86,103,125,128,136,168,182,194,210,217,222],"conventional":[39],"case.":[40],"Alternatively,":[41],"reinforcement":[43,225],"learning":[44,145,163],"(RL)":[45],"methods":[46,68,226],"evolve":[47,159],"coverage":[49,72,130,204],"set":[50,131,187,198],"policies":[53],"can":[55,123,141],"satisfy":[56],"all":[57],"possible":[58],"preferences":[59],"solving":[61],"problem.":[63],"However,":[64],"many":[65],"these":[67,81],"generalize":[70],"their":[71],"sets":[73,205],"to":[74,109,117,158,166,177,201],"work":[75],"nonstationary":[78],"environments.":[79],"In":[80,107,147,181],"environments,":[82],"parameters":[84],"state":[87],"transition":[88],"and":[89],"distribution":[91],"vary":[92],"over":[93],"time.":[94],"limitation":[96],"results":[97],"significant":[99],"performance":[100],"degradation":[101],"for":[102,132,162,206],"evolved":[104],"sets.":[106],"order":[108],"overcome":[110],"this":[111,148,179,197],"limitation,":[112],"there":[113],"is":[114,190,199],"need":[116],"learn":[118],"generic":[120,160,186],"skillset":[121],"bootstrap":[124,202],"evolution":[126],"each":[133,207],"shift":[134,208],"environment":[137,211],"dynamics,":[138],"therefore,":[139],"it":[140],"facilitate":[142],"continuous":[144],"process.":[146],"article,":[149],"intrinsically":[150],"motivated":[151],"RL":[152],"(IMRL)":[153],"has":[154],"been":[155],"successfully":[156],"deployed":[157],"skillsets":[161],"hierarchical":[164],"solve":[167],"MOMDPs.":[169],"We":[170,213],"propose":[171],"novel":[173],"dual-phase":[174],"IMRL":[175],"method":[176,219],"address":[178],"limitation.":[180],"first":[183],"phase,":[184,196],"skills":[189],"learned,":[191],"while":[192],"second":[195],"used":[200],"dynamics.":[212],"show":[214],"experimentally":[215],"proposed":[218],"significantly":[220],"outperforms":[221],"state-of-the-art":[223],"on":[227],"dynamic":[229],"robotics":[230],"environment.":[231]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}