{"id":"https://openalex.org/W3085832734","doi":"https://doi.org/10.1007/s10489-020-01849-3","title":"Fast and slow curiosity for high-level exploration in reinforcement learning","display_name":"Fast and slow curiosity for high-level exploration in reinforcement learning","publication_year":2020,"publication_date":"2020-09-16","ids":{"openalex":"https://openalex.org/W3085832734","doi":"https://doi.org/10.1007/s10489-020-01849-3","mag":"3085832734"},"language":"en","primary_location":{"id":"doi:10.1007/s10489-020-01849-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10489-020-01849-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10489-020-01849-3.pdf","source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10489-020-01849-3.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069965217","display_name":"Nicolas Bougie","orcid":"https://orcid.org/0000-0001-9856-0038"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Nicolas Bougie","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan","The Graduate University for Advanced Studies, Sokendai, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0001-9856-0038","affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"The Graduate University for Advanced Studies, Sokendai, Tokyo, Japan","institution_ids":["https://openalex.org/I200475212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081854769","display_name":"Ryutaro Ichise","orcid":"https://orcid.org/0000-0001-8474-0150"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryutaro Ichise","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan","The Graduate University for Advanced Studies, Sokendai, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"The Graduate University for Advanced Studies, Sokendai, Tokyo, Japan","institution_ids":["https://openalex.org/I200475212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5069965217"],"corresponding_institution_ids":["https://openalex.org/I184597095","https://openalex.org/I200475212"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":2.6813,"has_fulltext":true,"cited_by_count":30,"citation_normalized_percentile":{"value":0.9198848,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"51","issue":"2","first_page":"1086","last_page":"1107"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9926999807357788,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9787999987602234,"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/curiosity","display_name":"Curiosity","score":0.9145488142967224},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8281497955322266},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8106070160865784},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7576069831848145},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6272446513175964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5333025455474854},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.4355959892272949},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4218318462371826},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0781107246875763}],"concepts":[{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.9145488142967224},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8281497955322266},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8106070160865784},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7576069831848145},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6272446513175964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5333025455474854},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.4355959892272949},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4218318462371826},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0781107246875763},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10489-020-01849-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10489-020-01849-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10489-020-01849-3.pdf","source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10489-020-01849-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10489-020-01849-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10489-020-01849-3.pdf","source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3085832734.pdf","grobid_xml":"https://content.openalex.org/works/W3085832734.grobid-xml"},"referenced_works_count":62,"referenced_works":["https://openalex.org/W567721252","https://openalex.org/W779494576","https://openalex.org/W1522301498","https://openalex.org/W1527702126","https://openalex.org/W1580389772","https://openalex.org/W1591713425","https://openalex.org/W1594201624","https://openalex.org/W1959608418","https://openalex.org/W1988526405","https://openalex.org/W2004303440","https://openalex.org/W2062577170","https://openalex.org/W2100677568","https://openalex.org/W2121863487","https://openalex.org/W2133665775","https://openalex.org/W2135184018","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2151083897","https://openalex.org/W2153663612","https://openalex.org/W2158782408","https://openalex.org/W2173564293","https://openalex.org/W2181347294","https://openalex.org/W2257979135","https://openalex.org/W2299638491","https://openalex.org/W2439880944","https://openalex.org/W2471801048","https://openalex.org/W2561776174","https://openalex.org/W2593766708","https://openalex.org/W2596982695","https://openalex.org/W2614839826","https://openalex.org/W2736601468","https://openalex.org/W2738724892","https://openalex.org/W2744921630","https://openalex.org/W2781726626","https://openalex.org/W2786917922","https://openalex.org/W2787800669","https://openalex.org/W2789008106","https://openalex.org/W2796704765","https://openalex.org/W2807192342","https://openalex.org/W2883433335","https://openalex.org/W2885550588","https://openalex.org/W2886012730","https://openalex.org/W2895453875","https://openalex.org/W2899205164","https://openalex.org/W2918355317","https://openalex.org/W2922007426","https://openalex.org/W2938321354","https://openalex.org/W2945012403","https://openalex.org/W2949267040","https://openalex.org/W2950040888","https://openalex.org/W2950765052","https://openalex.org/W2963293881","https://openalex.org/W2963359646","https://openalex.org/W2963523627","https://openalex.org/W2963639957","https://openalex.org/W2963713691","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2964342357","https://openalex.org/W2980225636","https://openalex.org/W3103780890","https://openalex.org/W4214717370"],"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/W2613740288","https://openalex.org/W4383268304","https://openalex.org/W3163092301"],"abstract_inverted_index":{"Abstract":[0],"Deep":[1],"reinforcement":[2],"learning":[3],"(DRL)":[4],"algorithms":[5],"rely":[6],"on":[7,157],"carefully":[8],"designed":[9],"environment":[10],"rewards":[11,23],"that":[12,48,61,91,108,117,174],"are":[13,24],"extrinsic":[14],"to":[15,62,72,93,132,142],"the":[16,29,84,101,126,134],"agent.":[17],"However,":[18],"in":[19,128,180,183],"many":[20],"real-world":[21],"scenarios":[22],"sparse":[25],"or":[26],"delayed,":[27],"motivating":[28],"need":[30],"for":[31],"discovering":[32],"efficient":[33],"exploration":[34,77,112,186],"strategies.":[35],"While":[36],"intrinsically":[37],"motivated":[38],"agents":[39],"hold":[40],"promise":[41],"of":[42,86,160,185],"better":[43],"local":[44,74,111,145],"exploration,":[45],"solving":[46],"problems":[47],"require":[49],"coordinated":[50],"decisions":[51],"over":[52],"long-time":[53,95],"horizons":[54],"remains":[55],"an":[56,129],"open":[57],"problem.":[58],"We":[59,121,139,153],"postulate":[60],"discover":[63],"such":[64],"strategies,":[65],"a":[66,105,114,158],"DRL":[67],"agent":[68,176],"should":[69],"be":[70],"able":[71],"combine":[73],"and":[75,88,113,146,168,188],"high-level":[76,147],"behaviors.":[78],"To":[79],"this":[80,123],"end,":[81],"we":[82],"introduce":[83],"concept":[85],"fast":[87,106],"slow":[89,115],"curiosity":[90,102],"aims":[92],"incentivize":[94],"horizon":[96],"exploration.":[97,120],"Our":[98],"method":[99,156],"decomposes":[100],"bonus":[103,124],"into":[104],"reward":[107,116],"deals":[109],"with":[110],"encourages":[118],"global":[119],"formulate":[122],"as":[125],"error":[127],"agent\u2019s":[130],"ability":[131],"reconstruct":[133],"observations":[135],"given":[136],"their":[137],"contexts.":[138],"further":[140],"propose":[141],"dynamically":[143],"weight":[144],"strategies":[148],"by":[149],"measuring":[150],"state":[151],"diversity.":[152],"evaluate":[154],"our":[155,175],"variety":[159],"benchmark":[161],"environments,":[162],"including":[163],"Minigrid,":[164],"Super":[165],"Mario":[166],"Bros,":[167],"Atari":[169],"games.":[170],"Experimental":[171],"results":[172],"show":[173],"outperforms":[177],"prior":[178],"approaches":[179],"most":[181],"tasks":[182],"terms":[184],"efficiency":[187],"mean":[189],"scores.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}