{"id":"https://openalex.org/W4384519313","doi":"https://doi.org/10.1109/tase.2023.3288037","title":"Hierarchical Reinforcement Learning Integrating With Human Knowledge for Practical Robot Skill Learning in Complex Multi-Stage Manipulation","display_name":"Hierarchical Reinforcement Learning Integrating With Human Knowledge for Practical Robot Skill Learning in Complex Multi-Stage Manipulation","publication_year":2023,"publication_date":"2023-07-17","ids":{"openalex":"https://openalex.org/W4384519313","doi":"https://doi.org/10.1109/tase.2023.3288037"},"language":"en","primary_location":{"id":"doi:10.1109/tase.2023.3288037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2023.3288037","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","raw_type":"journal-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/A5100381466","display_name":"Xing Liu","orcid":"https://orcid.org/0000-0002-5327-4908"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xing Liu","raw_affiliation_strings":["Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, School of Astronautics, Northwestern Polytechnical University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0000-0002-5327-4908","affiliations":[{"raw_affiliation_string":"Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, School of Astronautics, Northwestern Polytechnical University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016266277","display_name":"Gaozhao Wang","orcid":"https://orcid.org/0009-0003-4184-0903"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaozhao Wang","raw_affiliation_strings":["Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, School of Astronautics, Northwestern Polytechnical University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0009-0003-4184-0903","affiliations":[{"raw_affiliation_string":"Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, School of Astronautics, Northwestern Polytechnical University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100323067","display_name":"Zihao Liu","orcid":"https://orcid.org/0000-0001-5306-6626"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihao Liu","raw_affiliation_strings":["Beijing Institute of Tracking and Telecommunications Technology (BITTT), Beijing, China","Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, School of Astronautics, Northwestern Polytechnical University, Xi&#x2019;an, China","School of Astronautics, Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Tracking and Telecommunications Technology (BITTT), Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, School of Astronautics, Northwestern Polytechnical University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Astronautics, Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090913078","display_name":"Yu Liu","orcid":"https://orcid.org/0000-0002-2550-928X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Liu","raw_affiliation_strings":["Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, School of Astronautics, Northwestern Polytechnical University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0000-0002-2550-928X","affiliations":[{"raw_affiliation_string":"Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, School of Astronautics, Northwestern Polytechnical University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083493899","display_name":"Zhengxiong Liu","orcid":"https://orcid.org/0000-0002-9427-4066"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengxiong Liu","raw_affiliation_strings":["Beijing Institute of Tracking and Telecommunications Technology (BITTT), Beijing, China","Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, School of Astronautics, Northwestern Polytechnical University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0000-0002-9427-4066","affiliations":[{"raw_affiliation_string":"Beijing Institute of Tracking and Telecommunications Technology (BITTT), Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, School of Astronautics, Northwestern Polytechnical University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091127758","display_name":"Panfeng Huang","orcid":"https://orcid.org/0000-0002-5132-9602"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Panfeng Huang","raw_affiliation_strings":["Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, School of Astronautics, Northwestern Polytechnical University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0000-0002-5132-9602","affiliations":[{"raw_affiliation_string":"Research Center for Intelligent Robotics and the National Key Laboratory of Aerospace Flight Dynamics, School of Astronautics, Northwestern Polytechnical University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100381466"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":3.9028,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.94787147,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"21","issue":"3","first_page":"3852","last_page":"3862"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9944000244140625,"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":0.9944000244140625,"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/T11663","display_name":"Viral Infectious Diseases and Gene Expression in Insects","score":0.900600016117096,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.691644012928009},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46973928809165955},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4494039714336395},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.43367907404899597},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4213337302207947},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4196925461292267},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.37112951278686523},{"id":"https://openalex.org/keywords/algebra-over-a-field","display_name":"Algebra over a field","score":0.3261628746986389},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.20032018423080444},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.1564807891845703}],"concepts":[{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.691644012928009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46973928809165955},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4494039714336395},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43367907404899597},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4213337302207947},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4196925461292267},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37112951278686523},{"id":"https://openalex.org/C136119220","wikidata":"https://www.wikidata.org/wiki/Q1000660","display_name":"Algebra over a field","level":2,"score":0.3261628746986389},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.20032018423080444},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.1564807891845703},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2023.3288037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2023.3288037","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6700000166893005,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5198280451","display_name":null,"funder_award_id":"62103334","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7676250215","display_name":null,"funder_award_id":"62273280","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1539716820","https://openalex.org/W2126909264","https://openalex.org/W2133224499","https://openalex.org/W2605102758","https://openalex.org/W2795550549","https://openalex.org/W2877093712","https://openalex.org/W2913938871","https://openalex.org/W2967717386","https://openalex.org/W2968116426","https://openalex.org/W3037429136","https://openalex.org/W3037476194","https://openalex.org/W3039116038","https://openalex.org/W3090612618","https://openalex.org/W3093922502","https://openalex.org/W3104876774","https://openalex.org/W3109467707","https://openalex.org/W3118300017","https://openalex.org/W3126300335","https://openalex.org/W3134939669","https://openalex.org/W3175313230","https://openalex.org/W3207576362","https://openalex.org/W3208343193","https://openalex.org/W4205123165","https://openalex.org/W4207069129","https://openalex.org/W4226397702","https://openalex.org/W4288885957","https://openalex.org/W4312403563","https://openalex.org/W4312523590","https://openalex.org/W6749061090","https://openalex.org/W6761443123","https://openalex.org/W6764125455"],"related_works":["https://openalex.org/W2504004674","https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W1595229445","https://openalex.org/W2498744856","https://openalex.org/W4390482104","https://openalex.org/W322408318","https://openalex.org/W149041114","https://openalex.org/W2963177394","https://openalex.org/W1965815883"],"abstract_inverted_index":{"This":[0,301,349],"paper":[1,302],"proposes":[2,303],"a":[3,207,290,304,333,351],"novel":[4,305,334],"hierarchical":[5],"reinforcement":[6],"learning":[7],"(HRL)":[8],"framework":[9,21,199,307],"of":[10,64,78,134,142,165,232,248,258,273,299],"complex":[11,259,274],"manipulation":[12,35,260,275,279],"tasks":[13,280],"which":[14,176,228,308,354],"integrates":[15],"the":[16,23,62,84,113,121,127,131,163,179,183,203,219,222,230,233,245,252,267,312,325,344,356,361,371,377],"human":[17,44,91,249,313],"prior":[18,45,314],"knowledge.":[19,46,92,315],"The":[20,34,75,101,262],"involves":[22],"following":[24],"steps:":[25],"<inline-formula":[26,47,67,93,150],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[27,48,68,94,151,237],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[28,49,69,95,152],"<tex-math":[29,50,70,96,153],"notation=\"LaTeX\">$":[30,51,71,97,154],"\\textbf{1)}":[31],"$</tex-math>":[32,53,73,99,156],"</inline-formula>":[33,54,74,100,157],"process":[36],"is":[37,109,174,265,289,321,339],"divided":[38],"into":[39,221,284],"several":[40],"stages":[41,58],"based":[42],"on":[43],"\\textbf{2)}":[52],"Transition":[55],"conditions":[56],"between":[57,185,363],"are":[59,81,88,145,190],"determined":[60],"in":[61,210,251,255],"form":[63],"\u201cif-then\u201d":[65],"rules.":[66],"\\textbf{3)}":[72],"key":[76],"features":[77],"each":[79],"stage":[80],"selected,":[82],"and":[83,139,182,187,193,215,287,292,346,365,368],"corresponding":[85],"control":[86],"policies":[87],"designed":[89],"via":[90],"\\textbf{4)}":[98],"policy":[102,114,122,327,378],"gradient":[103],"with":[104,202,206,225],"parameter-based":[105],"exploration":[106,143],"(PGPE)":[107],"method":[108,173,294,320,338],"employed":[110,146],"to":[111,123,147,161,168,239,323,341,359,374],"optimize":[112,376],"parameters":[115,328],"because":[116],"it":[117],"does":[118],"not":[119],"require":[120],"be":[124,282],"derivable":[125],"for":[126,295],"parameters.":[128,379],"To":[129],"increase":[130],"convergence":[132],"speed":[133],"this":[135,159,297],"framework,":[136],"importance":[137],"sampling":[138],"adaptive":[140],"adjustment":[141],"variance":[144],"improve":[148],"it.":[149],"\\textbf{5)}":[155],"On":[158],"basis,":[160],"facilitate":[162],"transfer":[164,337],"simulation":[166,180,186,345,357],"results":[167,358,373],"practical":[169,223,366],"experiments,":[170],"half":[171,335],"sim-to-real":[172,336],"presented,":[175],"fully":[177],"utilizes":[178,370],"results,":[181],"differences":[184],"experimental":[188,194],"environments":[189],"considered.":[191],"Simulation":[192],"studies":[195],"show":[196],"that":[197,266],"our":[198],"can":[200,216,281,309],"deal":[201],"peg-hole-insertion":[204],"task":[205],"high":[208],"quality":[209],"less":[211],"than":[212],"1600":[213],"episodes":[214],"safely":[217],"adapt":[218],"skill":[220,276],"scene":[224],"little":[226],"iterations,":[227],"verify":[229],"efficiency":[231],"presented":[234,340],"method.":[235],"<italic":[236],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Note":[238],"Practitioners</i>":[240],"\u2014Intelligent":[241],"robots":[242,268],"will":[243],"become":[244],"right":[246],"assistants":[247],"beings":[250],"future,":[253],"especially":[254],"various":[256],"areas":[257],"occasions.":[261],"important":[263],"premise":[264],"should":[269],"have":[270],"certain":[271],"ability":[272],"learning.":[277],"Complex":[278],"decomposed":[283],"multiple":[285],"stages,":[286],"HRL":[288,306],"suitable":[291],"efficient":[293],"solving":[296],"kind":[298],"problems.":[300],"better":[310,342],"integrate":[311,343],"In":[316],"addition,":[317],"improved":[318],"PGPE":[319],"proposed":[322],"obtain":[324],"optimized":[326],"more":[329],"quickly.":[330],"More":[331],"importantly,":[332],"experiment":[347,372],"results.":[348],"provides":[350],"common":[352],"paradigm,":[353],"leverages":[355],"reduce":[360],"interaction":[362],"robot":[364],"environment":[367],"then":[369],"further":[375]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":8}],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-10T00:00:00"}