{"id":"https://openalex.org/W4385488796","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191424","title":"Mnemonic Dictionary Learning for Intrinsic Motivation in Reinforcement Learning","display_name":"Mnemonic Dictionary Learning for Intrinsic Motivation in Reinforcement Learning","publication_year":2023,"publication_date":"2023-06-18","ids":{"openalex":"https://openalex.org/W4385488796","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191424"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn54540.2023.10191424","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn54540.2023.10191424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5089763177","display_name":"Renye Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Renye Yan","raw_affiliation_strings":["School of Software & Microelectronics, Peking University,Beijing,China","School of the Integrated Circuits, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software & Microelectronics, Peking University,Beijing,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of the Integrated Circuits, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101421907","display_name":"Zhe Wu","orcid":"https://orcid.org/0000-0001-9009-1089"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhe Wu","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100926694","display_name":"Yuan Zhan","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Zhan","raw_affiliation_strings":["Institute of Automation,Chinese Academy of Sciences,Beijing,China","Chinese Academy of Sciences, Institute of Automation, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation,Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Automation, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090751520","display_name":"Pin Tao","orcid":"https://orcid.org/0000-0003-2687-7997"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pin Tao","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology,Beijing,China","Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089981020","display_name":"Zongwei Wang","orcid":"https://orcid.org/0000-0001-6297-2700"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongwei Wang","raw_affiliation_strings":["School of the Integrated Circuits, Peking University,Beijing,China","Beijing Advanced Innovation Center for Integrated Circuits, Beijing, China","School of the Integrated Circuits, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of the Integrated Circuits, Peking University,Beijing,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Beijing Advanced Innovation Center for Integrated Circuits, Beijing, China","institution_ids":["https://openalex.org/I4210165198"]},{"raw_affiliation_string":"School of the Integrated Circuits, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060554231","display_name":"Yimao Cai","orcid":"https://orcid.org/0000-0002-6854-8211"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yimao Cai","raw_affiliation_strings":["School of the Integrated Circuits, Peking University,Beijing,China","Beijing Advanced Innovation Center for Integrated Circuits, Beijing, China","School of the Integrated Circuits, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of the Integrated Circuits, Peking University,Beijing,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Beijing Advanced Innovation Center for Integrated Circuits, Beijing, China","institution_ids":["https://openalex.org/I4210165198"]},{"raw_affiliation_string":"School of the Integrated Circuits, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076090670","display_name":"Junliang Xing","orcid":"https://orcid.org/0000-0001-6801-0510"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junliang Xing","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology,Beijing,China","Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"529","issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T10581","display_name":"Neural dynamics and brain function","score":0.9855999946594238,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9835000038146973,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/mnemonic","display_name":"Mnemonic","score":0.9148579835891724},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8046985268592834},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7519729137420654},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5778066515922546},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.487915962934494},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4742490351200104},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4330008625984192},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4328117072582245},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41192173957824707},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.17720812559127808},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1011260449886322}],"concepts":[{"id":"https://openalex.org/C197792726","wikidata":"https://www.wikidata.org/wiki/Q191062","display_name":"Mnemonic","level":2,"score":0.9148579835891724},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8046985268592834},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7519729137420654},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5778066515922546},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.487915962934494},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4742490351200104},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4330008625984192},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4328117072582245},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41192173957824707},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.17720812559127808},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1011260449886322},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn54540.2023.10191424","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn54540.2023.10191424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7454805152","display_name":null,"funder_award_id":"62076238,62222606,61834001,62025401","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7595801955","display_name":null,"funder_award_id":"2022ZD0116401,2019YFB2205401","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"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":65,"referenced_works":["https://openalex.org/W1988526405","https://openalex.org/W2005876975","https://openalex.org/W2034806191","https://openalex.org/W2112447569","https://openalex.org/W2113606819","https://openalex.org/W2135046866","https://openalex.org/W2145339207","https://openalex.org/W2188721763","https://openalex.org/W2257979135","https://openalex.org/W2559655401","https://openalex.org/W2596982695","https://openalex.org/W2601322194","https://openalex.org/W2626429629","https://openalex.org/W2788862220","https://openalex.org/W2803616302","https://openalex.org/W2804380964","https://openalex.org/W2885550588","https://openalex.org/W2895453875","https://openalex.org/W2949475445","https://openalex.org/W2953100042","https://openalex.org/W2963276097","https://openalex.org/W2963277051","https://openalex.org/W2963321092","https://openalex.org/W2963359646","https://openalex.org/W2963523627","https://openalex.org/W2964067469","https://openalex.org/W2970948392","https://openalex.org/W2982316857","https://openalex.org/W2997289589","https://openalex.org/W2998470023","https://openalex.org/W3018036994","https://openalex.org/W3034962946","https://openalex.org/W3041394538","https://openalex.org/W3092161856","https://openalex.org/W3129322645","https://openalex.org/W3175870124","https://openalex.org/W4221164780","https://openalex.org/W4225963367","https://openalex.org/W4287867830","https://openalex.org/W4295837424","https://openalex.org/W4300799055","https://openalex.org/W4306176261","https://openalex.org/W4319165238","https://openalex.org/W6676727762","https://openalex.org/W6676903177","https://openalex.org/W6717230150","https://openalex.org/W6718092244","https://openalex.org/W6730641667","https://openalex.org/W6735033012","https://openalex.org/W6735944222","https://openalex.org/W6740801417","https://openalex.org/W6748972340","https://openalex.org/W6751285671","https://openalex.org/W6751540476","https://openalex.org/W6753925943","https://openalex.org/W6754957883","https://openalex.org/W6756293349","https://openalex.org/W6756303580","https://openalex.org/W6758641611","https://openalex.org/W6763356705","https://openalex.org/W6771807793","https://openalex.org/W6783582377","https://openalex.org/W6809531794","https://openalex.org/W6810671056","https://openalex.org/W6846255677"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W4238433571","https://openalex.org/W2967848559","https://openalex.org/W4299831724","https://openalex.org/W4283803360"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,60,75],"for":[2,63,147],"hard-exploration":[3],"tasks":[4,157],"remains":[5],"challenging":[6,20],"due":[7],"to":[8,29,33,76,102,120,176],"the":[9,31,35,51,79,100,107,111,118,122,128,170],"long-term":[10],"dependence":[11],"and":[12,125,134,161,173],"sparse-and-delay":[13],"rewards":[14],"in":[15,66,106,180],"complex":[16],"environments.":[17],"In":[18,44],"these":[19],"tasks,":[21],"intrinsic":[22,64,90],"motivation":[23,65,91],"has":[24],"become":[25],"a":[26,57,83,144],"dominant":[27],"paradigm":[28],"enable":[30],"agent":[32,101,119],"explore":[34,103],"environment":[36],"when":[37],"no":[38],"external":[39],"reward":[40],"feedback":[41],"is":[42],"available.":[43],"this":[45,181],"work,":[46],"inspired":[47],"by":[48,110],"studies":[49,179],"from":[50],"human":[52],"memory":[53,112],"mechanism,":[54],"we":[55],"present":[56],"mnemonic":[58,94],"dictionary":[59,74,95],"(MDL)":[61],"model":[62,71,96,140],"reinforcement":[67],"learning.":[68],"The":[69,137],"MDL":[70,139],"leverages":[72],"sparse":[73],"incremental":[77],"abstract":[78],"exploration":[80,149],"histories":[81],"into":[82],"compact":[84],"memory-like":[85],"dictionary,":[86],"providing":[87],"an":[88],"excellent":[89],"model.":[92],"This":[93],"not":[97],"only":[98],"drives":[99],"novel":[104],"stats":[105],"environments":[108,129],"indicated":[109],"reconstruction":[113,135],"error":[114],"but":[115],"also":[116],"helps":[117],"remember":[121],"key":[123],"states":[124],"structure":[126],"of":[127],"using":[130],"its":[131,159],"learned":[132],"bases":[133],"coefficients.":[136],"proposed":[138],"can":[141],"serve":[142],"as":[143],"generative":[145],"module":[146],"existing":[148],"methods.":[150],"Extensive":[151],"experimental":[152],"results":[153],"on":[154],"typical":[155],"sparse-reward":[156],"demonstrate":[158],"effectiveness":[160],"applicability":[162],"over":[163],"several":[164],"competing":[165],"algorithms.":[166],"We":[167],"will":[168],"release":[169],"source":[171],"code":[172],"trained":[174],"models":[175],"facilitate":[177],"further":[178],"research":[182],"direction.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}