{"id":"https://openalex.org/W4397026139","doi":"https://doi.org/10.1109/tnnls.2024.3397704","title":"Eliminating Primacy Bias in Online Reinforcement Learning by Self-Distillation","display_name":"Eliminating Primacy Bias in Online Reinforcement Learning by Self-Distillation","publication_year":2024,"publication_date":"2024-05-17","ids":{"openalex":"https://openalex.org/W4397026139","doi":"https://doi.org/10.1109/tnnls.2024.3397704","pmid":"https://pubmed.ncbi.nlm.nih.gov/38758623"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2024.3397704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3397704","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/A5037024339","display_name":"Jingchen Li","orcid":"https://orcid.org/0000-0003-0905-0816"},"institutions":[{"id":"https://openalex.org/I4210156423","display_name":"National Engineering Research Center for Information Technology in Agriculture","ror":"https://ror.org/04c3j3t84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210156423"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingchen Li","raw_affiliation_strings":["Information Technology Research Center, Beijing Academy of Agriculture and Forestry Science, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0905-0816","affiliations":[{"raw_affiliation_string":"Information Technology Research Center, Beijing Academy of Agriculture and Forestry Science, Beijing, China","institution_ids":["https://openalex.org/I4210156423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013665827","display_name":"Haobin Shi","orcid":"https://orcid.org/0000-0003-2180-8941"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haobin Shi","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xian, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0003-2180-8941","affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xian, Shaanxi, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101355904","display_name":"Huarui Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156423","display_name":"National Engineering Research Center for Information Technology in Agriculture","ror":"https://ror.org/04c3j3t84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210156423"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huarui Wu","raw_affiliation_strings":["Information Technology Research Center, Beijing Academy of Agriculture and Forestry Science, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Research Center, Beijing Academy of Agriculture and Forestry Science, Beijing, China","institution_ids":["https://openalex.org/I4210156423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110031123","display_name":"Chunjiang Zhao","orcid":"https://orcid.org/0009-0005-6314-7661"},"institutions":[{"id":"https://openalex.org/I4210156423","display_name":"National Engineering Research Center for Information Technology in Agriculture","ror":"https://ror.org/04c3j3t84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210156423"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunjiang Zhao","raw_affiliation_strings":["Information Technology Research Center, Beijing Academy of Agriculture and Forestry Science, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Research Center, Beijing Academy of Agriculture and Forestry Science, Beijing, China","institution_ids":["https://openalex.org/I4210156423"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061189209","display_name":"Kao\u2010Shing Hwang","orcid":"https://orcid.org/0000-0001-9234-4836"},"institutions":[{"id":"https://openalex.org/I142974352","display_name":"National Sun Yat-sen University","ror":"https://ror.org/00mjawt10","country_code":"TW","type":"education","lineage":["https://openalex.org/I142974352"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kao-Shing Hwang","raw_affiliation_strings":["Department of Electrical Engineering, National Sun Yat-sen University, Kaohsiung, Taiwan"],"raw_orcid":"https://orcid.org/0000-0001-9234-4836","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Sun Yat-sen University, Kaohsiung, Taiwan","institution_ids":["https://openalex.org/I142974352"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5273,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.84814335,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"36","issue":"4","first_page":"7449","last_page":"7461"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9958999752998352,"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":0.9958999752998352,"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":0.8688391447067261},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7815181016921997},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6063680052757263},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.570749819278717},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5444177389144897},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5247452259063721},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5101152062416077},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4772355854511261},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.45039573311805725},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.4308852553367615},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.22213903069496155},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.18370869755744934},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.11053460836410522},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09130701422691345}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8688391447067261},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7815181016921997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6063680052757263},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.570749819278717},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5444177389144897},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5247452259063721},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5101152062416077},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4772355854511261},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.45039573311805725},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.4308852553367615},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.22213903069496155},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.18370869755744934},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.11053460836410522},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09130701422691345},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2024.3397704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3397704","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:38758623","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38758623","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":[],"awards":[{"id":"https://openalex.org/G5857992849","display_name":null,"funder_award_id":"2021ZD0113604","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2109008048","https://openalex.org/W2135746467","https://openalex.org/W2754517384","https://openalex.org/W2766447205","https://openalex.org/W2952867909","https://openalex.org/W3030656010","https://openalex.org/W3157818736","https://openalex.org/W4252279978","https://openalex.org/W4283798937","https://openalex.org/W4289820419","https://openalex.org/W4311486598","https://openalex.org/W4315643571","https://openalex.org/W4387682202","https://openalex.org/W6687681856","https://openalex.org/W6743684492","https://openalex.org/W6747473740","https://openalex.org/W6750629867","https://openalex.org/W6751540476","https://openalex.org/W6759370769","https://openalex.org/W6759527892","https://openalex.org/W6760698134","https://openalex.org/W6771570156","https://openalex.org/W6773373605","https://openalex.org/W6776901495","https://openalex.org/W6777091672","https://openalex.org/W6780404908","https://openalex.org/W6780470247","https://openalex.org/W6780815668","https://openalex.org/W6782436372","https://openalex.org/W6782858274","https://openalex.org/W6787473312","https://openalex.org/W6791000347","https://openalex.org/W6796367035","https://openalex.org/W6800570120","https://openalex.org/W6801798027","https://openalex.org/W6802038118","https://openalex.org/W6810764721","https://openalex.org/W6838667504"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W4378510483","https://openalex.org/W3113091479"],"abstract_inverted_index":{"Excessive":[0],"invalid":[1],"explorations":[2],"at":[3,111],"the":[4,16,29,48,56,62,77,99,103,115,123,127,140,156,162,165,178,187,190,197,200,214,217,228],"beginning":[5],"of":[6,18,64,164,205],"training":[7],"lead":[8],"deep":[9],"reinforcement":[10,42,53,86,91,224],"learning":[11,87,92,157,198,225],"process":[12],"to":[13,71,76,101,121,143,160,169,185,195,219,236],"fall":[14],"into":[15,106],"risk":[17],"overfitting,":[19],"further":[20],"resulting":[21],"in":[22,28,40,51,126,155,177,208],"spurious":[23],"decisions,":[24],"which":[25],"obstruct":[26],"agents":[27,235],"following":[30,78,128],"states":[31,79],"and":[32,80,114,189,210,227],"explorations.":[33],"This":[34,44],"phenomenon":[35],"is":[36,67,119,136,193],"termed":[37,89],"primacy":[38,49,59,65,221],"bias":[39,50,66,222],"online":[41,52,85],"learning.":[43],"work":[45,135],"systematically":[46],"investigates":[47],"learning,":[54],"discussing":[55],"reason":[57],"for":[58,133,223],"bias,":[60],"while":[61],"characteristic":[63],"also":[68],"analyzed.":[69],"Besides,":[70],"learn":[72],"a":[73,107,151],"policy":[74,110,117,142,145,154,167,229],"generalized":[75,153],"explorations,":[81],"we":[82,172],"develop":[83],"an":[84,174],"framework,":[88],"self-distillation":[90],"(SDRL),":[93],"based":[94],"on":[95,199],"knowledge":[96,105,138,179,231],"distillation,":[97],"allowing":[98],"agent":[100],"transfer":[102],"learned":[104],"randomly":[108],"initialized":[109],"regular":[112],"intervals,":[113],"new":[116,166],"network":[118],"used":[120],"replace":[122],"original":[124],"one":[125],"training.":[129],"The":[130,203],"core":[131],"idea":[132],"this":[134],"distilling":[137],"from":[139],"trained":[141],"another":[144],"can":[146,233],"filter":[147],"biases":[148],"out,":[149],"generating":[150],"more":[152,240],"process.":[158],"Moreover,":[159],"avoid":[161],"overfitting":[163],"due":[168],"excessive":[170],"distillations,":[171],"add":[173],"additional":[175],"loss":[176],"distillation":[180,232],"process,":[181],"using":[182],"L2":[183],"regularization":[184],"improve":[186],"generalization,":[188],"self-imitation":[191],"mechanism":[192],"introduced":[194],"accelerate":[196],"current":[201],"experiences.":[202],"results":[204],"several":[206],"experiments":[207],"DMC":[209],"Atari":[211],"100k":[212],"suggest":[213],"proposal":[215],"has":[216],"ability":[218],"eliminate":[220],"methods,":[226],"after":[230],"urge":[234],"get":[237],"higher":[238],"scores":[239],"quickly.":[241]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}