{"id":"https://openalex.org/W3168892396","doi":"https://doi.org/10.1145/3453160","title":"Hierarchical Reinforcement Learning","display_name":"Hierarchical Reinforcement Learning","publication_year":2021,"publication_date":"2021-06-05","ids":{"openalex":"https://openalex.org/W3168892396","doi":"https://doi.org/10.1145/3453160","mag":"3168892396"},"language":"en","primary_location":{"id":"doi:10.1145/3453160","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3453160","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"type":"review","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081835375","display_name":"Shubham Pateria","orcid":"https://orcid.org/0000-0002-6507-4479"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Shubham Pateria","raw_affiliation_strings":["Nanyang Technological University, Nanyang Avenue, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Nanyang Avenue, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062773086","display_name":"Budhitama Subagdja","orcid":"https://orcid.org/0000-0001-9774-0264"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Budhitama Subagdja","raw_affiliation_strings":["Singapore Management University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Management University, Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004167801","display_name":"Ah\u2010Hwee Tan","orcid":"https://orcid.org/0000-0003-0378-4069"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ah-hwee Tan","raw_affiliation_strings":["Singapore Management University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Management University, Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063229067","display_name":"Chai Quek","orcid":"https://orcid.org/0000-0002-7313-4339"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chai Quek","raw_affiliation_strings":["Nanyang Technological University, Nanyang Avenue, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Nanyang Avenue, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5081835375"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":28.1228,"has_fulltext":false,"cited_by_count":398,"citation_normalized_percentile":{"value":0.9974212,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":"54","issue":"5","first_page":"1","last_page":"35"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9908999800682068,"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"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9901000261306763,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.806079089641571},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7477505207061768},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.5441814661026001},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4818619191646576},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4454861879348755},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.43845972418785095},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42998069524765015},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3558555543422699},{"id":"https://openalex.org/keywords/ecology","display_name":"Ecology","score":0.10919931530952454},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.0614088773727417}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.806079089641571},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7477505207061768},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.5441814661026001},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4818619191646576},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4454861879348755},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.43845972418785095},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42998069524765015},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3558555543422699},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.10919931530952454},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0614088773727417},{"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3453160","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3453160","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W158722652","https://openalex.org/W426708554","https://openalex.org/W774034202","https://openalex.org/W1536990779","https://openalex.org/W1556824961","https://openalex.org/W1641379095","https://openalex.org/W1680797894","https://openalex.org/W1847903816","https://openalex.org/W1971483538","https://openalex.org/W1982678075","https://openalex.org/W2064675550","https://openalex.org/W2086699924","https://openalex.org/W2090170171","https://openalex.org/W2097828232","https://openalex.org/W2109910161","https://openalex.org/W2111020392","https://openalex.org/W2116611063","https://openalex.org/W2121517924","https://openalex.org/W2145339207","https://openalex.org/W2157822203","https://openalex.org/W2241862190","https://openalex.org/W2417280899","https://openalex.org/W2498991332","https://openalex.org/W2560674852","https://openalex.org/W2565989828","https://openalex.org/W2602856279","https://openalex.org/W2614099519","https://openalex.org/W2623293810","https://openalex.org/W2765148997","https://openalex.org/W2791797404","https://openalex.org/W2907537824","https://openalex.org/W2914949695","https://openalex.org/W2963523627","https://openalex.org/W2964199361","https://openalex.org/W2964599462","https://openalex.org/W2989068617","https://openalex.org/W2997250483","https://openalex.org/W2999905431","https://openalex.org/W3008894209","https://openalex.org/W4210966338","https://openalex.org/W4238510270","https://openalex.org/W4249441547","https://openalex.org/W6638734688","https://openalex.org/W6884300163"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2024136090","https://openalex.org/W2366903352"],"abstract_inverted_index":{"Hierarchical":[0],"Reinforcement":[1],"Learning":[2],"(HRL)":[3],"enables":[4],"autonomous":[5],"decomposition":[6],"of":[7,21,34,51,59,81,90,121,125],"challenging":[8],"long-horizon":[9],"decision-making":[10],"tasks":[11],"into":[12],"simpler":[13],"subtasks.":[14],"During":[15],"the":[16,19,52,57,82,86,98,113,122,128],"past":[17],"years,":[18],"landscape":[20,37],"HRL":[22,42,54,114,126],"research":[23,100],"has":[24],"grown":[25],"profoundly,":[26],"resulting":[27],"in":[28,43,101,127],"copious":[29],"approaches.":[30,83],"A":[31],"comprehensive":[32],"overview":[33],"this":[35],"vast":[36],"is":[38,74,94],"necessary":[39],"to":[40,77,96],"study":[41],"an":[44],"organized":[45],"manner.":[46],"We":[47],"provide":[48],"a":[49,78,88,106,117],"survey":[50,73],"diverse":[53],"approaches":[55,115],"concerning":[56],"challenges":[58],"learning":[60,69],"hierarchical":[61],"policies,":[62],"subtask":[63],"discovery,":[64],"transfer":[65],"learning,":[66],"and":[67,116],"multi-agent":[68],"using":[70],"HRL.":[71,102],"The":[72],"presented":[75],"according":[76],"novel":[79],"taxonomy":[80],"Based":[84],"on":[85],"survey,":[87],"set":[89],"important":[91],"open":[92],"problems":[93],"proposed":[95],"motivate":[97],"future":[99],"Furthermore,":[103],"we":[104],"outline":[105],"few":[107,118],"suitable":[108],"task":[109],"domains":[110],"for":[111],"evaluating":[112],"interesting":[119],"examples":[120],"practical":[123],"applications":[124],"Supplementary":[129],"Material.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":45},{"year":2025,"cited_by_count":152},{"year":2024,"cited_by_count":96},{"year":2023,"cited_by_count":66},{"year":2022,"cited_by_count":36},{"year":2021,"cited_by_count":3}],"updated_date":"2026-06-02T09:04:35.204637","created_date":"2025-10-10T00:00:00"}