{"id":"https://openalex.org/W4405598230","doi":"https://doi.org/10.1109/tii.2024.3495775","title":"Goal-Conditioned Reinforcement Learning With Adaptive Intrinsic Curiosity and Universal Value Network Fitting for Robotic Manipulation","display_name":"Goal-Conditioned Reinforcement Learning With Adaptive Intrinsic Curiosity and Universal Value Network Fitting for Robotic Manipulation","publication_year":2024,"publication_date":"2024-12-19","ids":{"openalex":"https://openalex.org/W4405598230","doi":"https://doi.org/10.1109/tii.2024.3495775"},"language":"en","primary_location":{"id":"doi:10.1109/tii.2024.3495775","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2024.3495775","pdf_url":null,"source":{"id":"https://openalex.org/S184777250","display_name":"IEEE Transactions on Industrial Informatics","issn_l":"1551-3203","issn":["1551-3203","1941-0050"],"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 Industrial Informatics","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/A5057493831","display_name":"Zihao Sun","orcid":"https://orcid.org/0000-0001-6337-1712"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihao Sun","raw_affiliation_strings":["School of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, China"],"raw_orcid":"https://orcid.org/0000-0001-6337-1712","affiliations":[{"raw_affiliation_string":"School of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035287663","display_name":"Xianfeng Yuan","orcid":"https://orcid.org/0000-0002-6217-6429"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianfeng Yuan","raw_affiliation_strings":["School of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, China"],"raw_orcid":"https://orcid.org/0000-0002-6217-6429","affiliations":[{"raw_affiliation_string":"School of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038384093","display_name":"Qingyang Xu","orcid":"https://orcid.org/0000-0003-3870-5551"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyang Xu","raw_affiliation_strings":["School of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, China"],"raw_orcid":"https://orcid.org/0000-0003-3870-5551","affiliations":[{"raw_affiliation_string":"School of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022572413","display_name":"Bao Pang","orcid":"https://orcid.org/0000-0002-1172-1036"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bao Pang","raw_affiliation_strings":["School of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, China"],"raw_orcid":"https://orcid.org/0000-0002-1172-1036","affiliations":[{"raw_affiliation_string":"School of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100651809","display_name":"Yong Song","orcid":"https://orcid.org/0000-0003-2505-2766"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Song","raw_affiliation_strings":["School of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, China"],"raw_orcid":"https://orcid.org/0000-0003-2505-2766","affiliations":[{"raw_affiliation_string":"School of Mechanical, Electrical and Information Engineering, Shandong University, Weihai, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101645277","display_name":"Rui Song","orcid":"https://orcid.org/0000-0002-4119-4433"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Song","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-4119-4433","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100724411","display_name":"Yibin Li","orcid":"https://orcid.org/0000-0002-5906-5074"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibin Li","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-5906-5074","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154099455"],"apc_list":null,"apc_paid":null,"fwci":0.8335,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.78808617,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"21","issue":"3","first_page":"2244","last_page":"2253"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8944000005722046,"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":0.8944000005722046,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.71334308385849},{"id":"https://openalex.org/keywords/curiosity","display_name":"Curiosity","score":0.6700541973114014},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5525264739990234},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5002107620239258},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4199445843696594},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.41875147819519043},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41478702425956726},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.36353349685668945},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3462420701980591},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2151373028755188},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.21048754453659058},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1437525451183319},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.09792691469192505},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.08641883730888367}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.71334308385849},{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.6700541973114014},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5525264739990234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5002107620239258},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4199445843696594},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.41875147819519043},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41478702425956726},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.36353349685668945},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3462420701980591},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2151373028755188},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.21048754453659058},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1437525451183319},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.09792691469192505},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.08641883730888367},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tii.2024.3495775","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2024.3495775","pdf_url":null,"source":{"id":"https://openalex.org/S184777250","display_name":"IEEE Transactions on Industrial Informatics","issn_l":"1551-3203","issn":["1551-3203","1941-0050"],"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 Industrial Informatics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G373194500","display_name":null,"funder_award_id":"U2013204","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5316204917","display_name":null,"funder_award_id":"62373225","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2158782408","https://openalex.org/W2522489477","https://openalex.org/W2766447205","https://openalex.org/W2963523627","https://openalex.org/W2979216345","https://openalex.org/W2979229105","https://openalex.org/W2995036248","https://openalex.org/W3000757491","https://openalex.org/W3026486560","https://openalex.org/W3086270667","https://openalex.org/W3134939669","https://openalex.org/W3181648466","https://openalex.org/W3191652410","https://openalex.org/W3197854638","https://openalex.org/W3205091198","https://openalex.org/W3207643345","https://openalex.org/W3207654079","https://openalex.org/W4214717370","https://openalex.org/W4225304231","https://openalex.org/W4229041186","https://openalex.org/W4285294350","https://openalex.org/W4285601030","https://openalex.org/W4319302764","https://openalex.org/W4385453680","https://openalex.org/W6616173779","https://openalex.org/W6740801417","https://openalex.org/W6747473740","https://openalex.org/W6748599296","https://openalex.org/W6754475338","https://openalex.org/W6778000925","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W3094054656","https://openalex.org/W4285676344","https://openalex.org/W4382584175","https://openalex.org/W2123270665","https://openalex.org/W2060310955","https://openalex.org/W2284924956","https://openalex.org/W3043413210","https://openalex.org/W2613740288","https://openalex.org/W4252460700","https://openalex.org/W4401386752"],"abstract_inverted_index":{"Hindsight":[0],"experience":[1],"replay":[2],"(HER)":[3],"has":[4],"greatly":[5],"increased":[6],"the":[7,42,77,100,126,130,137,140,145,150,155,172],"possibility":[8],"of":[9,111,139,147],"using":[10],"deep":[11],"reinforcement":[12],"learning":[13,28,81,180],"(DRL)":[14],"for":[15],"robotic":[16,57,165],"manipulation":[17,58,166],"with":[18,154],"sparse":[19],"rewards.":[20],"However,":[21],"there":[22],"are":[23],"still":[24],"concerns":[25],"about":[26],"low":[27],"efficiency":[29,178],"and":[30,39,66,80,97,107,179],"poor":[31],"performance":[32],"due":[33],"to":[34,51,74,91,124,143],"its":[35],"insufficient":[36],"exploration":[37,78,105],"ability":[38,79,106],"bias":[40,146],"against":[41],"initial":[43,127,141],"goal":[44,128,142],"introduced":[45],"by":[46],"HER.":[47],"In":[48,114],"this":[49,53,84],"article,":[50],"solve":[52],"problem,":[54],"a":[55,93,116],"multigoal":[56,164],"DRL":[59],"method":[60,85,174],"based":[61],"on":[62,163],"adaptive":[63],"intrinsic":[64,95],"curiosity":[65,89],"universal":[67,117],"value":[68,118,131,138],"network":[69,119],"fitting":[70,120,133],"(AIC-UVNF)":[71],"is":[72,122,161],"proposed":[73,123,173],"further":[75],"improve":[76],"performance.":[82,181],"Specifically,":[83],"utilizes":[86],"an":[87],"improved":[88],"mechanism":[90],"construct":[92],"joint":[94],"reward":[96],"adaptively":[98],"adjust":[99],"proportion,":[101],"which":[102,135],"can":[103],"enhance":[104],"avoid":[108],"excessive":[109],"pursuit":[110],"novel":[112],"states.":[113],"addition,":[115],"approach":[121],"incorporate":[125],"into":[129],"function":[132],"process,":[134],"employs":[136],"eliminate":[144],"HER":[148],"in":[149],"algorithm":[151],"update.":[152],"Combined":[153],"off-policy":[156],"soft":[157],"actor-critic":[158],"method,":[159],"AIC-UVNF":[160],"verified":[162],"tasks.":[167],"The":[168],"results":[169],"show":[170],"that":[171],"achieves":[175],"better":[176],"convergence":[177]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}