{"id":"https://openalex.org/W2995036248","doi":"https://doi.org/10.1109/tsmc.2019.2957051","title":"Self-Attention-Based Temporary Curiosity in Reinforcement Learning Exploration","display_name":"Self-Attention-Based Temporary Curiosity in Reinforcement Learning Exploration","publication_year":2019,"publication_date":"2019-12-18","ids":{"openalex":"https://openalex.org/W2995036248","doi":"https://doi.org/10.1109/tsmc.2019.2957051","mag":"2995036248"},"language":"en","primary_location":{"id":"doi:10.1109/tsmc.2019.2957051","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2019.2957051","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":"https://openalex.org/A5026968126","display_name":"H. Hu","orcid":"https://orcid.org/0000-0002-9825-8186"},"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":true,"raw_author_name":"Hangkai Hu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068624597","display_name":"Shiji Song","orcid":"https://orcid.org/0000-0001-7361-9283"},"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":"Shiji Song","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013240918","display_name":"Gao Huang","orcid":"https://orcid.org/0000-0002-7251-0988"},"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":"Gao Huang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5026968126"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.0127,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.83351608,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"51","issue":"9","first_page":"5773","last_page":"5784"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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":0.9987999796867371,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9043999910354614,"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/curiosity","display_name":"Curiosity","score":0.9855297803878784},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.8742127418518066},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6348641514778137},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5847890377044678},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4521123468875885},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.4178810119628906},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2325999140739441},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.10131281614303589}],"concepts":[{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.9855297803878784},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.8742127418518066},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6348641514778137},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5847890377044678},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4521123468875885},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.4178810119628906},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2325999140739441},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.10131281614303589},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsmc.2019.2957051","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2019.2957051","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":[{"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W172298727","https://openalex.org/W779494576","https://openalex.org/W1757796397","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2160589914","https://openalex.org/W2257979135","https://openalex.org/W2267186426","https://openalex.org/W2413794162","https://openalex.org/W2417786368","https://openalex.org/W2561776174","https://openalex.org/W2596982695","https://openalex.org/W2604960773","https://openalex.org/W2724169821","https://openalex.org/W2804078698","https://openalex.org/W2885550588","https://openalex.org/W2897873640","https://openalex.org/W2903320160","https://openalex.org/W2913909435","https://openalex.org/W2914949296","https://openalex.org/W2949475445","https://openalex.org/W2951919148","https://openalex.org/W2952428002","https://openalex.org/W2962730405","https://openalex.org/W2963091558","https://openalex.org/W2963276097","https://openalex.org/W2963403868","https://openalex.org/W2963423916","https://openalex.org/W2963523627","https://openalex.org/W2963564796","https://openalex.org/W2963639957","https://openalex.org/W2963864421","https://openalex.org/W2963891416","https://openalex.org/W2963925437","https://openalex.org/W2964043796","https://openalex.org/W2964067469","https://openalex.org/W2964083594","https://openalex.org/W2964174623","https://openalex.org/W2974778612","https://openalex.org/W4289743246","https://openalex.org/W4295253143","https://openalex.org/W4298857966","https://openalex.org/W4298876402","https://openalex.org/W4385245566","https://openalex.org/W6607097208","https://openalex.org/W6622487243","https://openalex.org/W6637967152","https://openalex.org/W6683300800","https://openalex.org/W6683436435","https://openalex.org/W6684921986","https://openalex.org/W6685757253","https://openalex.org/W6692846177","https://openalex.org/W6716474083","https://openalex.org/W6717230150","https://openalex.org/W6730641667","https://openalex.org/W6735033012","https://openalex.org/W6735939104","https://openalex.org/W6739901393","https://openalex.org/W6740092555","https://openalex.org/W6745858788","https://openalex.org/W6751097180","https://openalex.org/W6752378368","https://openalex.org/W6753349536","https://openalex.org/W6753925943","https://openalex.org/W6756303580","https://openalex.org/W6759691523","https://openalex.org/W6763509872"],"related_works":["https://openalex.org/W4285676344","https://openalex.org/W3094054656","https://openalex.org/W2123270665","https://openalex.org/W2060310955","https://openalex.org/W4382584175","https://openalex.org/W2284924956","https://openalex.org/W3043413210","https://openalex.org/W3039898216","https://openalex.org/W2185422427","https://openalex.org/W2478680874"],"abstract_inverted_index":{"In":[0,50,116],"many":[1],"real-world":[2],"scenarios,":[3],"extrinsic":[4],"rewards":[5],"provided":[6],"by":[7],"the":[8,35,48,71,80,92,102,108,133,141,145,179,184,187,198],"environment":[9],"are":[10],"sparse.":[11],"An":[12],"agent":[13,109],"trained":[14],"with":[15,113,132,164],"classic":[16],"reinforcement":[17],"learning":[18],"algorithm":[19],"fails":[20],"to":[21,59,70,130],"explore":[22],"these":[23],"environments":[24],"in":[25,169],"a":[26,56,111,121,152,173],"sufficient":[27],"and":[28,79,106,126,150,182],"effective":[29],"way.":[30],"To":[31],"address":[32],"this":[33,117],"problem,":[34],"exploration":[36,54,89,105,167],"bonus":[37],"which":[38],"derives":[39],"from":[40,144],"environmental":[41,61,77],"novelty":[42,62,78],"serves":[43],"as":[44],"intrinsic":[45],"motivation":[46],"for":[47,156],"agent.":[49],"recent":[51],"years,":[52],"curiosity-driven":[53,88],"is":[55],"mainstream":[57],"approach":[58],"describe":[60],"through":[63],"prediction":[64],"errors":[65],"of":[66,75,82,94,104,123,135,147,175,178,186,190],"dynamics":[67],"models.":[68],"Due":[69],"expressive":[72],"ability":[73],"limitations":[74],"curiosity-based":[76],"difficulty":[81],"finding":[83],"appropriate":[84],"feature":[85],"space,":[86],"most":[87],"methods":[90,168],"have":[91],"problem":[93,99,134],"overprotection":[95,136],"against":[96,137],"repetition.":[97,138],"This":[98],"can":[100],"reduce":[101],"efficiency":[103],"lead":[107],"into":[110],"trap":[112],"local":[114],"optimality.":[115],"article,":[118],"we":[119],"propose":[120,151],"combination":[122],"persisting":[124],"curiosity":[125,128,158],"temporary":[127,157],"framework":[129,163,181,200],"deal":[131],"We":[139,160],"introduce":[140],"self-attention":[142,154],"mechanism":[143,155],"field":[146],"computer":[148],"vision":[149],"sequence-based":[153],"generation.":[159],"compare":[161],"our":[162,191],"some":[165],"previous":[166],"hard-exploration":[170],"environments,":[171],"provide":[172],"series":[174],"comprehensive":[176],"analysis":[177],"proposed":[180,199],"investigate":[183],"effect":[185],"individual":[188],"components":[189],"method.":[192],"The":[193],"experimental":[194],"results":[195],"indicate":[196],"that":[197],"delivers":[201],"superior":[202],"performance":[203],"than":[204],"existing":[205],"methods.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4}],"updated_date":"2026-03-24T08:02:53.985720","created_date":"2025-10-10T00:00:00"}