{"id":"https://openalex.org/W4317383457","doi":"https://doi.org/10.1109/robio55434.2022.10011930","title":"Efficient Hierarchical Exploration with An Active Subgoal Generation Strategy","display_name":"Efficient Hierarchical Exploration with An Active Subgoal Generation Strategy","publication_year":2022,"publication_date":"2022-12-05","ids":{"openalex":"https://openalex.org/W4317383457","doi":"https://doi.org/10.1109/robio55434.2022.10011930"},"language":"en","primary_location":{"id":"doi:10.1109/robio55434.2022.10011930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio55434.2022.10011930","pdf_url":null,"source":{"id":"https://openalex.org/S4363607789","display_name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"},"type":"article","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/A5101989275","display_name":"Xin Xu","orcid":"https://orcid.org/0000-0003-1551-5587"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xin Xu","raw_affiliation_strings":["Beijing University of Technology,Faculty of Information Technology,Beijing,China,100124","Beijing Key Laboratory of Computing Intelligence and Intelligent Systems, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Faculty of Information Technology,Beijing,China,100124","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"Beijing Key Laboratory of Computing Intelligence and Intelligent Systems, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017790030","display_name":"Guoyu Zuo","orcid":"https://orcid.org/0000-0002-7624-4728"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoyu Zuo","raw_affiliation_strings":["Beijing University of Technology,Faculty of Information Technology,Beijing,China,100124","Beijing Key Laboratory of Computing Intelligence and Intelligent Systems, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Faculty of Information Technology,Beijing,China,100124","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"Beijing Key Laboratory of Computing Intelligence and Intelligent Systems, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069607848","display_name":"Jiangeng Li","orcid":"https://orcid.org/0000-0001-5715-7824"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangeng Li","raw_affiliation_strings":["Beijing University of Technology,Faculty of Information Technology,Beijing,China,100124","Beijing Key Laboratory of Computing Intelligence and Intelligent Systems, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Faculty of Information Technology,Beijing,China,100124","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"Beijing Key Laboratory of Computing Intelligence and Intelligent Systems, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013240918","display_name":"Gao Huang","orcid":"https://orcid.org/0000-0002-7251-0988"},"institutions":[{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]},{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gao Huang","raw_affiliation_strings":["Beijing University of Technology,Faculty of Information,Beijing,China,100124","Beijing Advanced Innovation Center for Intelligent Robots and Systems, Beijing, China","Beijing Key Laboratory of Computing Intelligence and Intelligent Systems, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Faculty of Information,Beijing,China,100124","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"Beijing Advanced Innovation Center for Intelligent Robots and Systems, Beijing, China","institution_ids":["https://openalex.org/I4210165198"]},{"raw_affiliation_string":"Beijing Key Laboratory of Computing Intelligence and Intelligent Systems, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101989275"],"corresponding_institution_ids":["https://openalex.org/I37796252"],"apc_list":null,"apc_paid":null,"fwci":0.3118,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.5380306,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1335","last_page":"1340"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9815000295639038,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9779999852180481,"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/novelty","display_name":"Novelty","score":0.7940160036087036},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7497700452804565},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6924403309822083},{"id":"https://openalex.org/keywords/inefficiency","display_name":"Inefficiency","score":0.5718651413917542},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5392621159553528},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5034565329551697},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.49533405900001526},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4949457049369812},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39481672644615173}],"concepts":[{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.7940160036087036},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7497700452804565},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6924403309822083},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.5718651413917542},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5392621159553528},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5034565329551697},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.49533405900001526},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4949457049369812},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39481672644615173},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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":1,"locations":[{"id":"doi:10.1109/robio55434.2022.10011930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio55434.2022.10011930","pdf_url":null,"source":{"id":"https://openalex.org/S4363607789","display_name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2138621090","https://openalex.org/W2158782408","https://openalex.org/W2806098286","https://openalex.org/W2810785043","https://openalex.org/W2899205164","https://openalex.org/W2902907165","https://openalex.org/W2903630557","https://openalex.org/W2920215304","https://openalex.org/W2950614095","https://openalex.org/W2962974944","https://openalex.org/W2964067469","https://openalex.org/W2967293465","https://openalex.org/W2989847975","https://openalex.org/W3034296891","https://openalex.org/W3036125317","https://openalex.org/W3118210634","https://openalex.org/W3128416529","https://openalex.org/W3170298552","https://openalex.org/W3208334305","https://openalex.org/W4294225490","https://openalex.org/W4300799055","https://openalex.org/W6740801417","https://openalex.org/W6748848655","https://openalex.org/W6752089545","https://openalex.org/W6759871227","https://openalex.org/W6779780899","https://openalex.org/W6802965437"],"related_works":["https://openalex.org/W2381242807","https://openalex.org/W2264067234","https://openalex.org/W3124243301","https://openalex.org/W3126131230","https://openalex.org/W1571502335","https://openalex.org/W1589409554","https://openalex.org/W2759038785","https://openalex.org/W2172232600","https://openalex.org/W2347541121","https://openalex.org/W2080951048"],"abstract_inverted_index":{"Goal-conditioned":[0],"hierarchical":[1,128],"reinforcement":[2],"learning":[3,85],"(HRL)":[4],"is":[5,71],"a":[6,49,142],"promising":[7],"approach":[8],"in":[9,35,115],"long-horizon":[10,37],"and":[11,87,93],"complex":[12],"tasks.":[13,147],"It":[14],"has":[15],"been":[16],"successfully":[17],"used":[18],"by":[19],"decomposing":[20],"tasks":[21,38],"via":[22],"subgoals.":[23,98],"However,":[24],"the":[25,36,69,102,106,110,116,120,152,155],"existing":[26],"goal-conditioned":[27],"HRL":[28,157],"methods":[29],"often":[30],"suffer":[31],"from":[32],"training":[33],"inefficiency":[34],"with":[39,58,131],"sparse":[40,113],"external":[41],"rewards.":[42],"For":[43],"this":[44,46,123],"problem,":[45],"paper":[47,124],"proposes":[48],"novel":[50],"framework":[51,70,107],"that":[52,151],"can":[53],"train":[54],"high-level":[55,83],"policy":[56,84],"efficiently":[57],"an":[59,72,81,126,132],"effective":[60,97],"sub":[61],"goal":[62],"generation":[63,75,135],"method.":[64,136],"The":[65],"key":[66],"component":[67],"of":[68,79,91,112,144],"active":[73,127],"subgoal":[74,134],"strategy":[76,130,153],"which":[77],"consists":[78],"(a)":[80],"efficient":[82,133],"mechanism":[86,104],"(b)":[88],"two":[89],"measures":[90],"novelty":[92],"coverage":[94],"for":[95],"filtering":[96],"We":[99,137],"also":[100],"introduce":[101],"HER":[103],"to":[105,108],"solve":[109],"problem":[111],"reward":[114],"environment.":[117],"Building":[118],"upon":[119],"proposed":[121],"framework,":[122],"develops":[125],"exploration":[129],"test":[138],"our":[139],"method":[140],"on":[141],"variety":[143],"continuous":[145],"control":[146],"Experimental":[148],"results":[149],"demonstrate":[150],"outperforms":[154],"state-of-the-art":[156],"approaches.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}