{"id":"https://openalex.org/W2899620415","doi":"https://doi.org/10.1609/aaai.v33i01.33014992","title":"Diversity-Driven Extensible Hierarchical Reinforcement Learning","display_name":"Diversity-Driven Extensible Hierarchical Reinforcement Learning","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2899620415","doi":"https://doi.org/10.1609/aaai.v33i01.33014992","mag":"2899620415"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33014992","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33014992","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4430/4308","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4430/4308","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004775934","display_name":"Yuhang Song","orcid":"https://orcid.org/0000-0002-7999-0291"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yuhang Song","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101615046","display_name":"Jianyi Wang","orcid":"https://orcid.org/0000-0001-7025-3626"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianyi Wang","raw_affiliation_strings":["Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091549352","display_name":"Thomas Lukasiewicz","orcid":"https://orcid.org/0000-0002-7644-1668"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Thomas Lukasiewicz","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022889808","display_name":"Zhenghua Xu","orcid":"https://orcid.org/0000-0002-6719-7333"},"institutions":[{"id":"https://openalex.org/I184843921","display_name":"Hebei University of Technology","ror":"https://ror.org/018hded08","country_code":"CN","type":"education","lineage":["https://openalex.org/I184843921"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenghua Xu","raw_affiliation_strings":["Hebei University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hebei University of Technology","institution_ids":["https://openalex.org/I184843921"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079385534","display_name":"Mai Xu","orcid":"https://orcid.org/0000-0002-0277-3301"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mai Xu","raw_affiliation_strings":["Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7285,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.87890559,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"33","issue":"01","first_page":"4992","last_page":"4999"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9918000102043152,"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":0.9918000102043152,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.920199990272522,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.8176906704902649},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7904603481292725},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7184313535690308},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.6627508401870728},{"id":"https://openalex.org/keywords/extensibility","display_name":"Extensibility","score":0.6292434334754944},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.6259622573852539},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.569414496421814},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41096821427345276},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3869704604148865},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.33992499113082886},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32340848445892334},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.27299273014068604},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.18668586015701294},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.07444638013839722}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8176906704902649},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7904603481292725},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7184313535690308},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.6627508401870728},{"id":"https://openalex.org/C32833848","wikidata":"https://www.wikidata.org/wiki/Q4115054","display_name":"Extensibility","level":2,"score":0.6292434334754944},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.6259622573852539},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.569414496421814},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41096821427345276},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3869704604148865},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.33992499113082886},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32340848445892334},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.27299273014068604},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18668586015701294},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.07444638013839722},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1609/aaai.v33i01.33014992","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33014992","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4430/4308","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/4430","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:ora.ox.ac.uk:uuid:9ab9cb8b-1af0-472d-93da-1f5bc0c9d7d1","is_oa":false,"landing_page_url":"https://ora.ox.ac.uk/objects/uuid:9ab9cb8b-1af0-472d-93da-1f5bc0c9d7d1","pdf_url":null,"source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference item"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33014992","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33014992","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4430/4308","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4399999976158142,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1633672591","display_name":null,"funder_award_id":"N510129","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G1874276316","display_name":null,"funder_award_id":"EP/N510129/1","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"},{"id":"https://openalex.org/G3855435662","display_name":null,"funder_award_id":"N510129","funder_id":"https://openalex.org/F4320313467","funder_display_name":"Alan Turing Institute"},{"id":"https://openalex.org/G4072067573","display_name":null,"funder_award_id":"EP/N510129/1","funder_id":"https://openalex.org/F4320313467","funder_display_name":"Alan Turing Institute"},{"id":"https://openalex.org/G444630160","display_name":null,"funder_award_id":"EP/N510129/","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G4500485203","display_name":"The Alan Turing Institute","funder_award_id":"EP/N510129/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G777199097","display_name":null,"funder_award_id":"EPSRC grant EP/N510129/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320313467","display_name":"Alan Turing Institute","ror":"https://ror.org/035dkdb55"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320324851","display_name":"Hebei University","ror":"https://ror.org/01p884a79"},{"id":"https://openalex.org/F4320326691","display_name":"Hebei University of Technology","ror":"https://ror.org/018hded08"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2899620415.pdf","grobid_xml":"https://content.openalex.org/works/W2899620415.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W1968768508","https://openalex.org/W2083954950","https://openalex.org/W2085679424","https://openalex.org/W2109910161","https://openalex.org/W2118688707","https://openalex.org/W2121517924","https://openalex.org/W2130535800","https://openalex.org/W2158548602","https://openalex.org/W2344023930","https://openalex.org/W2403054493","https://openalex.org/W2442341664","https://openalex.org/W2523124567","https://openalex.org/W2556477470","https://openalex.org/W2604373826","https://openalex.org/W2605016475","https://openalex.org/W2606433045","https://openalex.org/W2614839826","https://openalex.org/W2730274928","https://openalex.org/W2736601468","https://openalex.org/W2758731390","https://openalex.org/W2762014360","https://openalex.org/W2762872434","https://openalex.org/W2765194618","https://openalex.org/W2766354286","https://openalex.org/W2766654018","https://openalex.org/W2796206912","https://openalex.org/W2884414611","https://openalex.org/W2949267040","https://openalex.org/W2950727559","https://openalex.org/W2950794298","https://openalex.org/W2963161674","https://openalex.org/W2963438456","https://openalex.org/W2963523627","https://openalex.org/W2963722050","https://openalex.org/W2963887494","https://openalex.org/W2964055695","https://openalex.org/W2964118262","https://openalex.org/W2964227312","https://openalex.org/W2964311356","https://openalex.org/W3011570961","https://openalex.org/W4294578467","https://openalex.org/W6672332246","https://openalex.org/W6676560026","https://openalex.org/W6683443546","https://openalex.org/W6727349600","https://openalex.org/W6730153900","https://openalex.org/W6744935223","https://openalex.org/W6745151139"],"related_works":["https://openalex.org/W1948607442","https://openalex.org/W4247766898","https://openalex.org/W2044615423","https://openalex.org/W4244765761","https://openalex.org/W2361584951","https://openalex.org/W3004004161","https://openalex.org/W2365327041","https://openalex.org/W4225348249","https://openalex.org/W31122515","https://openalex.org/W2610007503"],"abstract_inverted_index":{"Hierarchical":[0],"reinforcement":[1],"learning":[2],"(HRL)":[3],"has":[4],"recently":[5],"shown":[6],"promising":[7],"advances":[8],"on":[9,25],"speeding":[10],"up":[11],"learning,":[12],"improving":[13],"the":[14,164,170],"exploration,":[15],"and":[16,80,85],"discovering":[17],"intertask":[18],"transferable":[19],"skills.":[20],"Most":[21],"recent":[22],"works":[23],"focus":[24],"HRL":[26,43,75,90,133],"with":[27,44,91,134,155],"two":[28,162],"levels,":[29],"i.e.,":[30,103],"a":[31,72,96,141],"master":[32],"policy":[33],"manipulates":[34],"subpolicies,":[35],"which":[36,128],"in":[37,50,67,149,161,173],"turn":[38],"manipulate":[39],"primitive":[40],"actions.":[41],"However,":[42,116],"multiple":[45,92,135],"levels":[46],"is":[47,83],"usually":[48,123],"needed":[49],"many":[51],"real-world":[52],"scenarios,":[53],"whose":[54],"ultimate":[55],"goals":[56],"are":[57,63,101,105,113],"highly":[58],"abstract,":[59],"while":[60],"their":[61,125],"actions":[62],"very":[64],"primitive.":[65],"Therefore,":[66],"this":[68,120,147],"paper,":[69],"we":[70,138],"propose":[71,140],"diversitydriven":[73],"extensible":[74,79],"(DEHRL),":[76],"where":[77],"an":[78],"scalable":[81],"framework":[82],"built":[84],"learned":[86],"levelwise":[87],"to":[88,107,132,145],"realize":[89],"levels.":[93,136],"DEHRL":[94,154,168],"follows":[95],"popular":[97],"assumption:":[98],"diverse":[99],"subpolicies":[100,104],"useful,":[102],"believed":[106],"be":[108],"more":[109,114],"useful":[110],"if":[111],"they":[112],"diverse.":[115],"existing":[117],"implementations":[118],"of":[119],"diversity":[121],"assumption":[122,148],"have":[124],"own":[126],"drawbacks,":[127],"makes":[129],"them":[130],"inapplicable":[131],"Consequently,":[137],"further":[139],"novel":[142],"diversity-driven":[143],"solution":[144],"achieve":[146],"DEHRL.":[150],"Experimental":[151],"studies":[152],"evaluate":[153],"nine":[156],"baselines":[157,172],"from":[158],"four":[159,175],"perspectives":[160],"domains;":[163],"results":[165],"show":[166],"that":[167],"outperforms":[169],"state-of-the-art":[171],"all":[174],"aspects.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}