{"id":"https://openalex.org/W4408564167","doi":"https://doi.org/10.1109/tetci.2025.3548787","title":"TUCA-HER: An Improved HER for Robot Manipulation Skill Learning via Trajectory Utility and Conservative Advantage","display_name":"TUCA-HER: An Improved HER for Robot Manipulation Skill Learning via Trajectory Utility and Conservative Advantage","publication_year":2025,"publication_date":"2025-03-18","ids":{"openalex":"https://openalex.org/W4408564167","doi":"https://doi.org/10.1109/tetci.2025.3548787"},"language":"en","primary_location":{"id":"doi:10.1109/tetci.2025.3548787","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetci.2025.3548787","pdf_url":null,"source":{"id":"https://openalex.org/S4210210251","display_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","issn_l":"2471-285X","issn":["2471-285X"],"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 Emerging Topics in Computational Intelligence","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/A5029620144","display_name":"Peiliang Wu","orcid":"https://orcid.org/0000-0003-1228-2757"},"institutions":[{"id":"https://openalex.org/I39333907","display_name":"Yanshan University","ror":"https://ror.org/02txfnf15","country_code":"CN","type":"education","lineage":["https://openalex.org/I39333907"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peiliang Wu","raw_affiliation_strings":["Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province, School of Information Science and Engineering, Yanshan University, Qinhuangdao, China"],"raw_orcid":"https://orcid.org/0000-0003-1228-2757","affiliations":[{"raw_affiliation_string":"Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province, School of Information Science and Engineering, Yanshan University, Qinhuangdao, China","institution_ids":["https://openalex.org/I39333907"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115588003","display_name":"Zhaoqi Wang","orcid":"https://orcid.org/0009-0008-3849-1649"},"institutions":[{"id":"https://openalex.org/I39333907","display_name":"Yanshan University","ror":"https://ror.org/02txfnf15","country_code":"CN","type":"education","lineage":["https://openalex.org/I39333907"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoqi Wang","raw_affiliation_strings":["Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province, School of Information Science and Engineering, Yanshan University, Qinhuangdao, China"],"raw_orcid":"https://orcid.org/0009-0008-3849-1649","affiliations":[{"raw_affiliation_string":"Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province, School of Information Science and Engineering, Yanshan University, Qinhuangdao, China","institution_ids":["https://openalex.org/I39333907"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106222680","display_name":"Yao Li","orcid":"https://orcid.org/0009-0006-7631-2459"},"institutions":[{"id":"https://openalex.org/I39333907","display_name":"Yanshan University","ror":"https://ror.org/02txfnf15","country_code":"CN","type":"education","lineage":["https://openalex.org/I39333907"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Li","raw_affiliation_strings":["Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province, School of Information Science and Engineering, Yanshan University, Qinhuangdao, China"],"raw_orcid":"https://orcid.org/0009-0006-7631-2459","affiliations":[{"raw_affiliation_string":"Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province, School of Information Science and Engineering, Yanshan University, Qinhuangdao, China","institution_ids":["https://openalex.org/I39333907"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045361189","display_name":"Wenbai Chen","orcid":"https://orcid.org/0000-0001-7683-2776"},"institutions":[{"id":"https://openalex.org/I78675632","display_name":"Beijing Information Science & Technology University","ror":"https://ror.org/04xnqep60","country_code":"CN","type":"education","lineage":["https://openalex.org/I78675632"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbai Chen","raw_affiliation_strings":["School of Automation, Beijing Information Science and Technology University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7683-2776","affiliations":[{"raw_affiliation_string":"School of Automation, Beijing Information Science and Technology University, Beijing, China","institution_ids":["https://openalex.org/I78675632"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018660055","display_name":"Guowei Gao","orcid":"https://orcid.org/0000-0003-3437-4265"},"institutions":[{"id":"https://openalex.org/I78675632","display_name":"Beijing Information Science & Technology University","ror":"https://ror.org/04xnqep60","country_code":"CN","type":"education","lineage":["https://openalex.org/I78675632"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guowei Gao","raw_affiliation_strings":["School of Automation, Beijing Information Science and Technology University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3437-4265","affiliations":[{"raw_affiliation_string":"School of Automation, Beijing Information Science and Technology University, Beijing, China","institution_ids":["https://openalex.org/I78675632"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04648975,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":"5","first_page":"3560","last_page":"3571"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9868000149726868,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9868000149726868,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9616000056266785,"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/trajectory","display_name":"Trajectory","score":0.7448047995567322},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5455694794654846},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5200269222259521},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5180264115333557},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.334524929523468},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06501844525337219}],"concepts":[{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.7448047995567322},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5455694794654846},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5200269222259521},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5180264115333557},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.334524929523468},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06501844525337219},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tetci.2025.3548787","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetci.2025.3548787","pdf_url":null,"source":{"id":"https://openalex.org/S4210210251","display_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","issn_l":"2471-285X","issn":["2471-285X"],"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 Emerging Topics in Computational Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1331161382","display_name":null,"funder_award_id":"U20A20167","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1484327127","display_name":null,"funder_award_id":"62276028","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":12,"referenced_works":["https://openalex.org/W1902261929","https://openalex.org/W3026486560","https://openalex.org/W3086270667","https://openalex.org/W3105044139","https://openalex.org/W3128011616","https://openalex.org/W4210444794","https://openalex.org/W4285145746","https://openalex.org/W4285294350","https://openalex.org/W4308459823","https://openalex.org/W4367281935","https://openalex.org/W4383109432","https://openalex.org/W4385462854"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2903025760","https://openalex.org/W4289147272"],"abstract_inverted_index":{"In":[0],"the":[1,67,89,140,150,168],"realm":[2],"of":[3,70,170],"multi-goal":[4],"reinforcement":[5],"learning":[6,49,87,105],"for":[7,45,62,74],"robot":[8,46,102],"manipulation,":[9],"effectively":[10],"addressing":[11],"sparse":[12],"rewards":[13,93],"has":[14,25],"been":[15],"a":[16,145],"key":[17],"challenge.":[18],"The":[19],"hindsight":[20],"experience":[21,63,152],"replay":[22,153],"(HER)":[23],"mechanism":[24],"provided":[26],"notable":[27],"advancements":[28],"in":[29,66,127,139,172],"this":[30],"domain,":[31],"yet":[32],"its":[33],"efficiency":[34,129],"and":[35,53,77,112,120,130],"adaptability":[36],"still":[37],"require":[38],"further":[39],"improvement.":[40],"This":[41],"paper":[42],"introduces":[43],"TUCA-HER":[44,100,143,171],"manipulation":[47,103],"skill":[48,104],"via":[50],"Trajectory":[51],"Utility":[52],"Conservative":[54],"Advantage.":[55],"We":[56],"start":[57],"by":[58],"computing":[59],"trajectory":[60],"utility":[61],"samples":[64],"collected":[65],"early":[68],"stages":[69],"training,":[71],"which":[72],"allows":[73],"dynamic":[75],"relabeling":[76],"significantly":[78],"enhances":[79],"sample":[80,128],"efficiency.":[81],"Furthermore,":[82,161],"we":[83,98],"integrate":[84],"conservative":[85],"advantage":[86],"into":[88],"actor-critic":[90],"framework,":[91],"reshaping":[92],"to":[94,101,135,166],"construct":[95],"TUCA-HER.":[96],"Finally,":[97],"apply":[99],"tasks,":[106],"providing":[107],"details":[108],"on":[109,117],"algorithmic":[110],"implementation":[111],"complexity":[113],"analysis.":[114],"Evaluations":[115],"conducted":[116,165],"OpenAI":[118],"Fetch":[119],"Hand":[121],"environments":[122],"demonstrate":[123],"TUCA-HER's":[124],"superior":[125],"performance":[126],"task":[131],"success":[132],"rate":[133],"compared":[134],"other":[136],"algorithms.":[137],"Notably,":[138],"FetchPickAndPlace":[141],"task,":[142],"showcases":[144],"remarkable":[146],"46%":[147],"improvement":[148],"over":[149],"Double":[151],"buffer":[154],"Adaptive":[155],"Soft":[156],"Hindsight":[157],"Experience":[158],"Replay":[159],"(DAS-HER).":[160],"Sim-to-Real":[162],"experiments":[163],"are":[164],"validate":[167],"effectiveness":[169],"real-world":[173],"environments.":[174]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
