{"id":"https://openalex.org/W4385757466","doi":"https://doi.org/10.1109/tcyb.2023.3298195","title":"Task-Driven Reinforcement Learning With Action Primitives for Long-Horizon Manipulation Skills","display_name":"Task-Driven Reinforcement Learning With Action Primitives for Long-Horizon Manipulation Skills","publication_year":2023,"publication_date":"2023-08-11","ids":{"openalex":"https://openalex.org/W4385757466","doi":"https://doi.org/10.1109/tcyb.2023.3298195","pmid":"https://pubmed.ncbi.nlm.nih.gov/37566505"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2023.3298195","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2023.3298195","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"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 Cybernetics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5051494127","display_name":"Hao Wang","orcid":"https://orcid.org/0009-0001-3132-2809"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao Wang","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043877238","display_name":"Hao Zhang","orcid":"https://orcid.org/0000-0002-1669-6984"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Zhang","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412835","display_name":"Lin Li","orcid":"https://orcid.org/0000-0002-0533-7783"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018344952","display_name":"Zhen Kan","orcid":"https://orcid.org/0000-0003-2069-9544"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Kan","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035337020","display_name":"Yongduan Song","orcid":"https://orcid.org/0000-0002-2167-1861"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongduan Song","raw_affiliation_strings":["School of Automation, Chongqing University, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5051494127"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":4.7133,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.96014133,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"54","issue":"8","first_page":"4513","last_page":"4526"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.9975000023841858,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.9975000023841858,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9952999949455261,"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":0.9912999868392944,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.790740430355072},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7623094916343689},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7322374582290649},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6180918216705322},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.603623628616333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.584514856338501},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.5310293436050415},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4685559868812561},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.42901840806007385},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.4162234663963318},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33647263050079346},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.18785586953163147},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1781485378742218},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07937070727348328},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.06771230697631836}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.790740430355072},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7623094916343689},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7322374582290649},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6180918216705322},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.603623628616333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.584514856338501},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.5310293436050415},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4685559868812561},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.42901840806007385},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.4162234663963318},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33647263050079346},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.18785586953163147},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1781485378742218},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07937070727348328},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.06771230697631836},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcyb.2023.3298195","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2023.3298195","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"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 Cybernetics","raw_type":"journal-article"},{"id":"pmid:37566505","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37566505","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on cybernetics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6899999976158142,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1051832680","display_name":null,"funder_award_id":"62173314","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":49,"referenced_works":["https://openalex.org/W1498432697","https://openalex.org/W1540883472","https://openalex.org/W1647671624","https://openalex.org/W2036637075","https://openalex.org/W2141088850","https://openalex.org/W2256420211","https://openalex.org/W2791797404","https://openalex.org/W2905277694","https://openalex.org/W2975504670","https://openalex.org/W2986925736","https://openalex.org/W2990747716","https://openalex.org/W3034655091","https://openalex.org/W3039276491","https://openalex.org/W3039865636","https://openalex.org/W3088304681","https://openalex.org/W3090054427","https://openalex.org/W3130777366","https://openalex.org/W3132564992","https://openalex.org/W3134939669","https://openalex.org/W3150384095","https://openalex.org/W3158638107","https://openalex.org/W3202327308","https://openalex.org/W3204657926","https://openalex.org/W3211437739","https://openalex.org/W4206520121","https://openalex.org/W4206742989","https://openalex.org/W4226277223","https://openalex.org/W4281620612","https://openalex.org/W4287758155","https://openalex.org/W4289987806","https://openalex.org/W4295745363","https://openalex.org/W4321366759","https://openalex.org/W4385245566","https://openalex.org/W6636915900","https://openalex.org/W6697359928","https://openalex.org/W6747473740","https://openalex.org/W6752089545","https://openalex.org/W6752155926","https://openalex.org/W6752216738","https://openalex.org/W6761754428","https://openalex.org/W6771398375","https://openalex.org/W6771989576","https://openalex.org/W6782766965","https://openalex.org/W6784521679","https://openalex.org/W6784712800","https://openalex.org/W6790722625","https://openalex.org/W6802864926","https://openalex.org/W6838573628","https://openalex.org/W6849619839"],"related_works":["https://openalex.org/W2930863966","https://openalex.org/W2126211886","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W4220829754","https://openalex.org/W2165180011","https://openalex.org/W3165944253","https://openalex.org/W2351343564","https://openalex.org/W2170052867","https://openalex.org/W2171010636"],"abstract_inverted_index":{"It":[0],"is":[1,75],"an":[2,84],"interesting":[3],"open":[4],"problem":[5],"to":[6,9,18,64,78],"enable":[7],"robots":[8],"efficiently":[10],"and":[11,51,95,131],"effectively":[12],"learn":[13],"long-horizon":[14],"manipulation":[15,38,67,125],"skills.":[16,68],"Motivated":[17],"augment":[19],"robot":[20,89,115],"learning":[21,31,40,46,123,129],"via":[22,98],"more":[23],"effective":[24],"exploration,":[25],"this":[26],"work":[27],"develops":[28],"task-driven":[29],"reinforcement":[30,45],"with":[32,48],"action":[33,53,108],"primitives":[34],"(TRAPs),":[35],"a":[36,71,103],"new":[37],"skill":[39],"framework":[41],"that":[42,119,140],"augments":[43,121],"standard":[44],"algorithms":[47],"formal":[49],"methods":[50],"parameterized":[52],"space":[54],"(PAS).":[55],"In":[56],"particular,":[57],"TRAPs":[58,120,141],"uses":[59],"linear":[60],"temporal":[61],"logic":[62],"(LTL)":[63],"specify":[65],"complex":[66],"LTL":[69],"progression,":[70],"semantics-preserving":[72],"rewriting":[73],"operation,":[74],"then":[76],"used":[77],"decompose":[79],"the":[80,88,112,122],"training":[81],"task":[82,93,134],"at":[83],"abstract":[85],"level,":[86],"informs":[87],"about":[90],"their":[91],"current":[92],"progress,":[94],"guides":[96],"them":[97],"reward":[99],"functions.":[100],"The":[101],"PAS,":[102],"predefined":[104],"library":[105],"of":[106,114,124],"heterogeneous":[107],"primitives,":[109],"further":[110],"improves":[111],"efficiency":[113,130],"exploration.":[116],"We":[117],"highlight":[118],"skills":[126],"in":[127],"both":[128],"effectiveness":[132],"(i.e.,":[133],"constraints).":[135],"Extensive":[136],"empirical":[137],"studies":[138],"demonstrate":[139],"outperforms":[142],"most":[143],"existing":[144],"methods.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":10}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
