{"id":"https://openalex.org/W4402435476","doi":"https://doi.org/10.1109/tsmc.2024.3449294","title":"Clustering-Driven State Embedding for Reinforcement Learning Under Visual Distractions","display_name":"Clustering-Driven State Embedding for Reinforcement Learning Under Visual Distractions","publication_year":2024,"publication_date":"2024-09-11","ids":{"openalex":"https://openalex.org/W4402435476","doi":"https://doi.org/10.1109/tsmc.2024.3449294"},"language":"en","primary_location":{"id":"doi:10.1109/tsmc.2024.3449294","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2024.3449294","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Systems, Man, and Cybernetics: Systems","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":"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":null,"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":0.8152,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.71132013,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"54","issue":"12","first_page":"7382","last_page":"7395"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9412000179290771,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9412000179290771,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9294000267982483,"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/cluster-analysis","display_name":"Cluster analysis","score":0.7644225358963013},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6605691313743591},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5718130469322205},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43889230489730835},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.43065518140792847}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7644225358963013},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6605691313743591},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5718130469322205},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43889230489730835},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.43065518140792847}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsmc.2024.3449294","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2024.3449294","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"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":39,"referenced_works":["https://openalex.org/W2741943936","https://openalex.org/W2910568379","https://openalex.org/W2970999977","https://openalex.org/W2977618190","https://openalex.org/W2989847975","https://openalex.org/W2999044305","https://openalex.org/W3015437096","https://openalex.org/W3188220908","https://openalex.org/W4206944021","https://openalex.org/W4281392159","https://openalex.org/W4302010773","https://openalex.org/W4311887664","https://openalex.org/W4313136702","https://openalex.org/W4322730981","https://openalex.org/W4328007461","https://openalex.org/W4382237565","https://openalex.org/W4383752013","https://openalex.org/W6682962330","https://openalex.org/W6684921986","https://openalex.org/W6685380521","https://openalex.org/W6728550200","https://openalex.org/W6747387971","https://openalex.org/W6747473740","https://openalex.org/W6756256016","https://openalex.org/W6759534164","https://openalex.org/W6776867236","https://openalex.org/W6779827379","https://openalex.org/W6779997284","https://openalex.org/W6780470247","https://openalex.org/W6787713516","https://openalex.org/W6787959036","https://openalex.org/W6788031615","https://openalex.org/W6791000347","https://openalex.org/W6799458897","https://openalex.org/W6803185011","https://openalex.org/W6842723308","https://openalex.org/W6844194202","https://openalex.org/W6860567475","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2081900870","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109","https://openalex.org/W4362501864"],"abstract_inverted_index":{"Visual":[0],"reinforcement":[1,69],"learning":[2,31,70],"(VRL)":[3],"aims":[4],"to":[5,32,49,76,89,136,147,177],"optimize":[6],"policies":[7],"by":[8,103],"utilizing":[9],"information":[10],"derived":[11],"from":[12,182],"visual":[13,73,178,206],"sensory":[14],"inputs.":[15],"To":[16,127],"tackle":[17],"the":[18,64,91,98,105,109,120,131,145,149,167,183],"challenges":[19],"of":[20,151,169,213],"high":[21],"dimensionality":[22],"and":[23,58,113,215,226],"sample":[24],"efficiency,":[25],"numerous":[26],"studies":[27],"have":[28,42],"leveraged":[29],"self-supervised":[30],"encode":[33],"observations":[34,138],"into":[35,119,232],"latent":[36],"state":[37,66,80,110],"representations.":[38,81],"Though":[39],"these":[40],"algorithms":[41,202],"shown":[43],"promise,":[44],"they":[45],"may":[46],"be":[47],"susceptible":[48],"task-irrelevant":[50],"distractions,":[51],"such":[52],"as":[53],"changes":[54],"in":[55,166,203],"background,":[56],"color,":[57],"camera":[59],"angles.":[60],"Thus,":[61],"we":[62],"propose":[63],"clustering-driven":[65],"embedding":[67],"for":[68,125,238],"(RL)":[71],"under":[72],"distractions":[74],"(CSE-RL)":[75],"learn":[77],"more":[78,170],"robust":[79],"The":[82,141],"student\u2019s":[83],"t":[84],"distribution":[85],"is":[86,134],"first":[87],"utilized":[88],"model":[90],"predicted":[92,121],"clustering":[93,122],"assignment.":[94],"In":[95],"this":[96],"process,":[97],"reward":[99],"centers":[100,116],"are":[101,117,174],"defined":[102],"hardening":[104],"target":[106],"distribution.":[107],"Subsequently,":[108],"embeddings,":[111],"rewards,":[112],"their":[114],"respective":[115],"fed":[118],"assignment":[123],"function":[124],"clustering.":[126],"avoid":[128],"trivial":[129],"solutions,":[130],"Sinkhorn-Knopp":[132],"algorithm":[133],"adopted":[135],"balance":[137],"across":[139],"clusters.":[140],"proposed":[142],"CSE-RL":[143,190,209,231],"has":[144],"capacity":[146],"enhance":[148],"comprehension":[150],"inherent":[152],"relationships":[153],"among":[154],"different":[155],"states,":[156],"while":[157],"also":[158],"filtering":[159],"out":[160],"irrelevant":[161],"or":[162,193],"redundant":[163],"information,":[164],"resulting":[165],"creation":[168],"efficient":[171],"representations":[172],"that":[173,189],"less":[175],"prone":[176],"distractions.":[179,207],"Experimental":[180],"results":[181],"distracting":[184],"control":[185],"suite":[186],"(DCS)":[187],"indicate":[188],"achieves":[191],"comparable":[192],"even":[194],"better":[195],"performance":[196],"compared":[197],"with":[198],"several":[199],"state-of-the-art":[200],"VRL":[201],"handling":[204],"challenging":[205],"Notably,":[208],"exhibits":[210],"remarkable":[211],"improvements":[212],"31.82%":[214],"18.18%":[216],"on":[217,222],"DCS":[218],"over":[219],"baselines":[220],"based":[221],"data-regularized":[223],"Q":[224],"(DrQ)":[225],"DrQv2":[227],"frameworks,":[228],"respectively.":[229],"Integrating":[230],"offline":[233],"RL":[234],"offers":[235],"promising":[236],"avenues":[237],"future":[239],"study.":[240]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}