{"id":"https://openalex.org/W4409560911","doi":"https://doi.org/10.1109/tnnls.2025.3556838","title":"Visual Reinforcement Learning Control With Instance-Reweighted Alignment and Instance-Dimension Uniformity","display_name":"Visual Reinforcement Learning Control With Instance-Reweighted Alignment and Instance-Dimension Uniformity","publication_year":2025,"publication_date":"2025-04-17","ids":{"openalex":"https://openalex.org/W4409560911","doi":"https://doi.org/10.1109/tnnls.2025.3556838","pmid":"https://pubmed.ncbi.nlm.nih.gov/40244840"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2025.3556838","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3556838","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","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/A5100733180","display_name":"Rongrong Wang","orcid":"https://orcid.org/0000-0003-0615-0838"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongrong Wang","raw_affiliation_strings":["Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-0615-0838","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091364297","display_name":"Yuhu Cheng","orcid":"https://orcid.org/0000-0003-2022-9999"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhu Cheng","raw_affiliation_strings":["Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2022-9999","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108064895","display_name":"Xuesong Wang","orcid":"https://orcid.org/0000-0002-5327-1088"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuesong Wang","raw_affiliation_strings":["Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-5327-1088","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I25757504"],"apc_list":null,"apc_paid":null,"fwci":1.2282,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83103037,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"36","issue":"6","first_page":"9905","last_page":"9918"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9986000061035156,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9986000061035156,"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":0.9962999820709229,"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/T12676","display_name":"Machine Learning and ELM","score":0.9939000010490417,"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":0.780768632888794},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7209837436676025},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5202016234397888},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48573094606399536},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.46911054849624634},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.413678377866745},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3390948176383972},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3317190408706665},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15195506811141968}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.780768632888794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7209837436676025},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5202016234397888},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48573094606399536},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46911054849624634},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.413678377866745},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3390948176383972},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3317190408706665},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15195506811141968},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2025.3556838","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3556838","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:40244840","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40244840","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 neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5699999928474426}],"awards":[{"id":"https://openalex.org/G4756161396","display_name":null,"funder_award_id":"62176259","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4823360002","display_name":null,"funder_award_id":"62373364","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6172462902","display_name":null,"funder_award_id":"BE2022095","funder_id":"https://openalex.org/F4320327780","funder_display_name":"Key Research and Development Program of Jiangxi Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327780","display_name":"Key Research and Development Program of Jiangxi Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W2102661631","https://openalex.org/W2157881843","https://openalex.org/W2163998574","https://openalex.org/W2165131254","https://openalex.org/W2736601468","https://openalex.org/W2781585732","https://openalex.org/W2842511635","https://openalex.org/W2916743882","https://openalex.org/W2963864421","https://openalex.org/W2998249317","https://openalex.org/W3035524453","https://openalex.org/W3045059767","https://openalex.org/W3093210455","https://openalex.org/W3171007011","https://openalex.org/W3203504876","https://openalex.org/W3207924272","https://openalex.org/W4200038771","https://openalex.org/W4214689175","https://openalex.org/W4214717370","https://openalex.org/W4252279978","https://openalex.org/W4287393217","https://openalex.org/W4295308578","https://openalex.org/W4297808394","https://openalex.org/W4307092192","https://openalex.org/W4320525814","https://openalex.org/W4323065138","https://openalex.org/W4362631131","https://openalex.org/W4364375123","https://openalex.org/W4382237565","https://openalex.org/W4384499218","https://openalex.org/W4396816783","https://openalex.org/W4401567346","https://openalex.org/W4402435476","https://openalex.org/W6684921986","https://openalex.org/W6741002519","https://openalex.org/W6747387971","https://openalex.org/W6747473740","https://openalex.org/W6754162236","https://openalex.org/W6759534164","https://openalex.org/W6776867236","https://openalex.org/W6780730929","https://openalex.org/W6787713516","https://openalex.org/W6788031615","https://openalex.org/W6791742336","https://openalex.org/W6795754764","https://openalex.org/W6796422976","https://openalex.org/W6798331393","https://openalex.org/W6799458897","https://openalex.org/W6800570120","https://openalex.org/W6852559736","https://openalex.org/W6852637071","https://openalex.org/W6860491890","https://openalex.org/W6860567475","https://openalex.org/W6866729449"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"Visual":[0],"reinforcement":[1],"learning":[2,9,86],"(VRL)":[3],"has":[4],"demonstrated":[5],"remarkable":[6],"capabilities":[7],"in":[8,34,213],"behaviors":[10],"directly":[11],"from":[12,199],"intricate":[13],"high-dimensional":[14],"visual":[15],"inputs.":[16],"Despite":[17],"these":[18],"advancements,":[19],"existing":[20],"VRL":[21,67,79],"methods":[22],"still":[23],"encounter":[24],"obstacles":[25],"such":[26],"as":[27],"complete":[28,47],"collapse":[29,48,138],"and":[30,37,73,103,150,157,174,195,217],"dimensional":[31,38],"collapse,":[32],"resulting":[33],"representation":[35,85],"degradation":[36],"redundancy.":[39],"Contrastive":[40],"learning,":[41],"while":[42],"helping":[43],"to":[44,52,113,135,191],"mitigate":[45],"the":[46,53,59,82,91,96,118,137,145,155,162,179,193,200],"issue,":[49],"is":[50,87,133,141,222],"prone":[51],"class":[54,125,183],"collision":[55,184],"dilemma.":[56],"To":[57],"tackle":[58],"aforementioned":[60],"challenges,":[61],"this":[62,78],"article":[63],"proposes":[64],"a":[65],"novel":[66],"control":[68,80,202],"method":[69],"with":[70,189,210],"instance-reweighted":[71,83],"alignment":[72,84,173],"instance-dimension":[74,129],"uniformity":[75,130,175,188],"(IAIU).":[76],"In":[77,168],"method,":[81],"introduced":[88],"by":[89,143],"minimizing":[90],"Kullback-Leibler":[92],"(KL)":[93],"divergence":[94],"between":[95],"distributions":[97],"of":[98,164,172,182],"predicted":[99],"next":[100],"state":[101,115,166],"representations":[102,116],"their":[104],"weighted":[105],"actual":[106],"counterparts.":[107],"By":[108],"doing":[109],"so,":[110],"we":[111],"aim":[112],"align":[114],"within":[117],"same":[119],"semantic":[120],"class,":[121],"thereby":[122],"effectively":[123],"alleviating":[124],"collision.":[126],"Meanwhile,":[127],"an":[128],"regularization":[131],"mechanism":[132],"adopted":[134],"suppress":[136],"phenomenon.":[139],"This":[140],"realized":[142],"leveraging":[144],"Hilbert-Schmidt":[146],"independence":[147],"criterion":[148],"(HSIC)":[149],"standard":[151],"orthogonal":[152],"constraint":[153],"at":[154,224],"instance":[156],"dimension":[158],"levels,":[159],"respectively,":[160],"ensuring":[161],"extraction":[163],"task-relevant":[165],"representations.":[167],"essence,":[169],"IAIU's":[170,207],"dual-strategy":[171],"not":[176],"only":[177],"addresses":[178],"critical":[180],"issue":[181],"but":[185],"also":[186],"guarantees":[187],"respect":[190],"both":[192,214],"instances":[194],"dimensions.":[196],"Simulation":[197],"results":[198],"distracting":[201],"suite":[203],"(DCS)":[204],"benchmark":[205],"demonstrate":[206],"superior":[208],"performance,":[209],"substantial":[211],"enhancements":[212],"representational":[215],"ability":[216],"policy":[218],"efficacy.":[219],"The":[220],"code":[221],"available":[223],"https://github.com/anonymousforcode/IAIU.":[225]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}