{"id":"https://openalex.org/W7084068363","doi":"https://doi.org/10.1109/tie.2025.3603083","title":"Action-Based Contrastive Unsupervised Representations for Reinforcement Learning Toward Robotic Manipulation","display_name":"Action-Based Contrastive Unsupervised Representations for Reinforcement Learning Toward Robotic Manipulation","publication_year":2025,"publication_date":"2025-10-01","ids":{"openalex":"https://openalex.org/W7084068363","doi":"https://doi.org/10.1109/tie.2025.3603083"},"language":"en","primary_location":{"id":"doi:10.1109/tie.2025.3603083","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tie.2025.3603083","pdf_url":null,"source":{"id":"https://openalex.org/S58031724","display_name":"IEEE Transactions on Industrial Electronics","issn_l":"0278-0046","issn":["0278-0046","1557-9948"],"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 Electronics","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":null,"display_name":"Qi Chen","orcid":"https://orcid.org/0009-0009-0298-8474"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Chen","raw_affiliation_strings":["Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0009-0009-0298-8474","affiliations":[{"raw_affiliation_string":"Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chao Ye","orcid":"https://orcid.org/0000-0003-2263-8286"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Ye","raw_affiliation_strings":["Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0003-2263-8286","affiliations":[{"raw_affiliation_string":"Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Weiyang Lin","orcid":"https://orcid.org/0000-0002-0493-1289"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiyang Lin","raw_affiliation_strings":["Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-0493-1289","affiliations":[{"raw_affiliation_string":"Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhitai Liu","orcid":"https://orcid.org/0000-0002-5533-0774"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhitai Liu","raw_affiliation_strings":["Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-5533-0774","affiliations":[{"raw_affiliation_string":"Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xinghu Yu","orcid":"https://orcid.org/0000-0001-8181-6199"},"institutions":[{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinghu Yu","raw_affiliation_strings":["Intelligent Control and System Research Center, Yongjiang Laboratory, Ningbo, China"],"raw_orcid":"https://orcid.org/0000-0001-8181-6199","affiliations":[{"raw_affiliation_string":"Intelligent Control and System Research Center, Yongjiang Laboratory, Ningbo, China","institution_ids":["https://openalex.org/I13591777"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jianbin Qiu","orcid":"https://orcid.org/0000-0001-7707-6159"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianbin Qiu","raw_affiliation_strings":["Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0001-7707-6159","affiliations":[{"raw_affiliation_string":"Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":null,"display_name":"Huijun Gao","orcid":"https://orcid.org/0000-0001-5554-5452"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huijun Gao","raw_affiliation_strings":["Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0001-5554-5452","affiliations":[{"raw_affiliation_string":"Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8041,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.80874889,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"73","issue":"2","first_page":"3104","last_page":"3113"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12859","display_name":"Cell Image Analysis Techniques","score":0.23389999568462372,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"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"}},"topics":[{"id":"https://openalex.org/T12859","display_name":"Cell Image Analysis Techniques","score":0.23389999568462372,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"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"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.08730000257492065,"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"}},{"id":"https://openalex.org/T10120","display_name":"Bacterial Genetics and Biotechnology","score":0.07129999995231628,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7942000031471252},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4756999909877777},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4690000116825104},{"id":"https://openalex.org/keywords/curl","display_name":"Curl (programming language)","score":0.44699999690055847},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4059000015258789},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.3544999957084656},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.33480000495910645},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3336000144481659}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7942000031471252},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7457000017166138},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7085000276565552},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5479000210762024},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4756999909877777},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4690000116825104},{"id":"https://openalex.org/C147663694","wikidata":"https://www.wikidata.org/wiki/Q1144631","display_name":"Curl (programming language)","level":2,"score":0.44699999690055847},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4059000015258789},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3544999957084656},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.326200008392334},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3140000104904175},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26579999923706055},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.25060001015663147},{"id":"https://openalex.org/C115903097","wikidata":"https://www.wikidata.org/wiki/Q7094097","display_name":"Online machine learning","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tie.2025.3603083","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tie.2025.3603083","pdf_url":null,"source":{"id":"https://openalex.org/S58031724","display_name":"IEEE Transactions on Industrial Electronics","issn_l":"0278-0046","issn":["0278-0046","1557-9948"],"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 Electronics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5225740075111389}],"awards":[{"id":"https://openalex.org/G3205815922","display_name":null,"funder_award_id":"62521005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5335238104","display_name":null,"funder_award_id":"62427812","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":22,"referenced_works":["https://openalex.org/W2915988335","https://openalex.org/W3035524453","https://openalex.org/W3093210455","https://openalex.org/W3127561923","https://openalex.org/W3155193730","https://openalex.org/W3175558129","https://openalex.org/W4221055893","https://openalex.org/W4223476016","https://openalex.org/W4229002925","https://openalex.org/W4252279978","https://openalex.org/W4283794074","https://openalex.org/W4297964528","https://openalex.org/W4312288659","https://openalex.org/W4320713280","https://openalex.org/W4367663188","https://openalex.org/W4376607964","https://openalex.org/W4385245566","https://openalex.org/W4385732018","https://openalex.org/W4400579200","https://openalex.org/W4402265443","https://openalex.org/W4406728015","https://openalex.org/W4408099470"],"related_works":[],"abstract_inverted_index":{"Although":[0],"deep":[1],"reinforcement":[2],"learning":[3,43,89,128],"(DRL)":[4],"has":[5],"made":[6],"massive":[7],"progress":[8],"in":[9,110,137,172],"policy":[10,127],"learning,":[11],"its":[12],"reliance":[13],"on":[14,48],"a":[15,23,59,78,98,118,155],"large":[16],"number":[17],"of":[18,52,87,101,105,158,175],"real-world":[19,111,161],"data":[20,32,96,134],"samples":[21],"presents":[22],"significant":[24],"barrier":[25],"to":[26,116,170],"broader":[27],"practical":[28],"applications.":[29],"To":[30],"improve":[31],"efficiency,":[33],"we":[34,83],"propose":[35],"an":[36],"innovative":[37],"algorithm,":[38],"action-based":[39],"contrastive":[40],"unsupervised":[41],"representation":[42],"(Action-CURL).":[44],"This":[45],"method":[46,123,148,166],"builds":[47],"the":[49,53,65,75,85,102,133,146,150,176,179],"fundamental":[50],"principles":[51],"classical":[54],"CURL":[55,152,171],"algorithm":[56,153],"by":[57],"introducing":[58],"novel":[60],"loss":[61],"function":[62],"that":[63,129,145],"quantifies":[64],"correlation":[66],"between":[67],"continuous":[68],"states":[69],"while":[70],"integrating":[71],"action":[72],"information":[73],"into":[74],"model":[76],"as":[77],"constraint.":[79],"In":[80],"this":[81],"work,":[82],"tackle":[84],"challenge":[86,136],"efficiently":[88],"robotic":[90,125],"manipulation":[91,126],"policies":[92],"from":[93,141],"visual":[94],"observation":[95],"through":[97],"critical":[99],"appraisal":[100],"inherent":[103],"limitations":[104],"DRL":[106],"algorithms":[107],"when":[108],"applied":[109],"scenarios.":[112],"Our":[113],"goal":[114],"is":[115],"develop":[117],"more":[119],"efficient":[120],"and":[121,160],"pragmatic":[122],"for":[124],"can":[130],"effectively":[131],"mitigate":[132],"scarcity":[135],"DRL.":[138],"Empirical":[139],"evidence":[140],"our":[142,165],"experiments":[143],"indicates":[144],"proposed":[147],"outperforms":[149],"original":[151],"across":[154,178],"diverse":[156],"range":[157],"simulated":[159],"environments.":[162],"On":[163],"average,":[164],"achieves":[167],"comparable":[168],"performance":[169],"just":[173],"58.85%":[174],"time":[177],"DMControl":[180],"suite\u2019s":[181],"500k":[182],"benchmark.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}