{"id":"https://openalex.org/W2980225636","doi":"https://doi.org/10.1007/s10994-019-05845-8","title":"Skill-based curiosity for intrinsically motivated reinforcement learning","display_name":"Skill-based curiosity for intrinsically motivated reinforcement learning","publication_year":2019,"publication_date":"2019-10-10","ids":{"openalex":"https://openalex.org/W2980225636","doi":"https://doi.org/10.1007/s10994-019-05845-8","mag":"2980225636"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-019-05845-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-019-05845-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-019-05845-8.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"Machine Learning","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/s10994-019-05845-8.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":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"]}]},{"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":2.2338,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":{"value":0.90557191,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"109","issue":"3","first_page":"493","last_page":"512"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9962000250816345,"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":0.9962000250816345,"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/T11135","display_name":"Virology and Viral Diseases","score":0.9508000016212463,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9498000144958496,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9666679501533508},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8116064667701721},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.701341450214386},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6305456161499023},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6210512518882751},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6050540804862976},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5587946772575378},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5528891086578369},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4967937767505646},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.470054030418396},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4187777042388916},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14757364988327026},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07912680506706238},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0782184898853302},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.06685042381286621}],"concepts":[{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.9666679501533508},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8116064667701721},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.701341450214386},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6305456161499023},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6210512518882751},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6050540804862976},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5587946772575378},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5528891086578369},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4967937767505646},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.470054030418396},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4187777042388916},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14757364988327026},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07912680506706238},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0782184898853302},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.06685042381286621},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10994-019-05845-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-019-05845-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-019-05845-8.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"Machine Learning","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10994-019-05845-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-019-05845-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-019-05845-8.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2980225636.pdf","grobid_xml":"https://content.openalex.org/works/W2980225636.grobid-xml"},"referenced_works_count":56,"referenced_works":["https://openalex.org/W172298727","https://openalex.org/W567721252","https://openalex.org/W1757796397","https://openalex.org/W1771410628","https://openalex.org/W1777239053","https://openalex.org/W1863227302","https://openalex.org/W1959608418","https://openalex.org/W2004303440","https://openalex.org/W2061562262","https://openalex.org/W2100677568","https://openalex.org/W2112220463","https://openalex.org/W2120889539","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2151083897","https://openalex.org/W2155027007","https://openalex.org/W2158782408","https://openalex.org/W2163605009","https://openalex.org/W2169209873","https://openalex.org/W2173564293","https://openalex.org/W2260756217","https://openalex.org/W2298457129","https://openalex.org/W2419612459","https://openalex.org/W2551887912","https://openalex.org/W2596982695","https://openalex.org/W2614839826","https://openalex.org/W2733961795","https://openalex.org/W2738669288","https://openalex.org/W2807192342","https://openalex.org/W2823112946","https://openalex.org/W2889599215","https://openalex.org/W2890253414","https://openalex.org/W2895453875","https://openalex.org/W2899205164","https://openalex.org/W2949247522","https://openalex.org/W2949608212","https://openalex.org/W2950872548","https://openalex.org/W2963523627","https://openalex.org/W2963634205","https://openalex.org/W2964043796","https://openalex.org/W2964121744","https://openalex.org/W2964161785","https://openalex.org/W2978938326","https://openalex.org/W3102768201","https://openalex.org/W4214717370","https://openalex.org/W6616173779","https://openalex.org/W6631190155","https://openalex.org/W6638018090","https://openalex.org/W6640963894","https://openalex.org/W6660504773","https://openalex.org/W6677916085","https://openalex.org/W6682849425","https://openalex.org/W6740801417","https://openalex.org/W6753060773","https://openalex.org/W6754957883","https://openalex.org/W6780394890"],"related_works":["https://openalex.org/W4285676344","https://openalex.org/W3094054656","https://openalex.org/W2123270665","https://openalex.org/W4382584175","https://openalex.org/W2060310955","https://openalex.org/W2284924956","https://openalex.org/W3043413210","https://openalex.org/W2613740288","https://openalex.org/W4383268304","https://openalex.org/W2501594388"],"abstract_inverted_index":{"Abstract":[0],"Reinforcement":[1],"learning":[2,64,123,195],"methods":[3],"rely":[4],"on":[5,118],"rewards":[6],"provided":[7],"by":[8,200],"the":[9,15,29,42,49,82,87,98,101,104,112,116,119,126,145,155,173],"environment":[10,47],"that":[11,66,179,197],"are":[12],"extrinsic":[13,202],"to":[14,40,44,70,78,106,124,149,184,193],"agent.":[16],"However,":[17],"many":[18],"real-world":[19],"scenarios":[20],"involve":[21],"sparse":[22,162],"or":[23],"delayed":[24],"rewards.":[25,203],"In":[26],"such":[27],"cases,":[28],"agent":[30,43,69,105,178],"can":[31,90],"develop":[32],"its":[33,46,108],"own":[34,109],"intrinsic":[35],"reward":[36,163,183],"function":[37],"called":[38],"curiosity":[39,59,99,182],"enable":[41],"explore":[45],"in":[48,92,165],"quest":[50],"of":[51,84,103,121,128,144,154,161,175],"new":[52,73,129],"skills.":[53,74,156],"We":[54,96,114,157,171],"propose":[55,148],"a":[56,151,159],"novel":[57],"end-to-end":[58],"mechanism":[60],"for":[61],"deep":[62],"reinforcement":[63,194],"methods,":[65],"allows":[67],"an":[68,176],"gradually":[71],"acquire":[72],"Our":[75],"method":[76],"scales":[77],"high-dimensional":[79],"problems,":[80],"avoids":[81],"need":[83],"directly":[85],"predicting":[86],"future,":[88],"and,":[89],"perform":[91],"sequential":[93],"decision":[94],"scenarios.":[95],"formulate":[97],"as":[100],"ability":[102],"predict":[107],"knowledge":[110],"about":[111],"task.":[113],"base":[115],"prediction":[117],"idea":[120],"skill":[122],"incentivize":[125],"discovery":[127],"skills,":[130],"and":[131,142,168],"guide":[132],"exploration":[133],"towards":[134],"promising":[135],"solutions.":[136],"To":[137],"further":[138],"improve":[139],"data":[140],"efficiency":[141],"generalization":[143],"agent,":[146],"we":[147],"learn":[150,199],"latent":[152],"representation":[153],"present":[158],"variety":[160],"tasks":[164],"MiniGrid,":[166],"MuJoCo,":[167],"Atari":[169],"games.":[170],"compare":[172],"performance":[174,191],"augmented":[177],"uses":[180],"our":[181],"state-of-the-art":[185],"learners.":[186],"Experimental":[187],"evaluation":[188],"exhibits":[189],"higher":[190],"compared":[192],"models":[196],"only":[198],"maximizing":[201]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}