{"id":"https://openalex.org/W4382680334","doi":"https://doi.org/10.1145/3605782","title":"Curiosity Creates Diversity in Policy Search","display_name":"Curiosity Creates Diversity in Policy Search","publication_year":2023,"publication_date":"2023-06-30","ids":{"openalex":"https://openalex.org/W4382680334","doi":"https://doi.org/10.1145/3605782"},"language":"en","primary_location":{"id":"doi:10.1145/3605782","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3605782","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3605782","source":{"id":"https://openalex.org/S4210221532","display_name":"ACM Transactions on Evolutionary Learning and Optimization","issn_l":"2688-299X","issn":["2688-299X","2688-3007"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Evolutionary Learning and Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3605782","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016383055","display_name":"Paul-Antoine Le Tolguenec","orcid":"https://orcid.org/0000-0003-4555-6718"},"institutions":[{"id":"https://openalex.org/I112991645","display_name":"Airbus (France)","ror":"https://ror.org/023qdcg29","country_code":"FR","type":"company","lineage":["https://openalex.org/I112991645","https://openalex.org/I4210121748"]},{"id":"https://openalex.org/I17866349","display_name":"Universit\u00e9 F\u00e9d\u00e9rale de Toulouse Midi-Pyr\u00e9n\u00e9es","ror":"https://ror.org/004raaa70","country_code":"FR","type":"education","lineage":["https://openalex.org/I17866349"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Paul-Antoine Le Tolguenec","raw_affiliation_strings":["ISAE-Supaero, Universit\u00e9 de Toulouse, Airbus, France"],"raw_orcid":"https://orcid.org/0000-0003-4555-6718","affiliations":[{"raw_affiliation_string":"ISAE-Supaero, Universit\u00e9 de Toulouse, Airbus, France","institution_ids":["https://openalex.org/I112991645","https://openalex.org/I17866349"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049708660","display_name":"Emmanuel Rachelson","orcid":"https://orcid.org/0000-0002-8559-1617"},"institutions":[{"id":"https://openalex.org/I17866349","display_name":"Universit\u00e9 F\u00e9d\u00e9rale de Toulouse Midi-Pyr\u00e9n\u00e9es","ror":"https://ror.org/004raaa70","country_code":"FR","type":"education","lineage":["https://openalex.org/I17866349"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Emmanuel Rachelson","raw_affiliation_strings":["ISAE-Supaero, Universit\u00e9 de Toulouse, France"],"raw_orcid":"https://orcid.org/0000-0002-8559-1617","affiliations":[{"raw_affiliation_string":"ISAE-Supaero, Universit\u00e9 de Toulouse, France","institution_ids":["https://openalex.org/I17866349"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050701848","display_name":"Yann Besse","orcid":"https://orcid.org/0009-0008-3639-6090"},"institutions":[{"id":"https://openalex.org/I112991645","display_name":"Airbus (France)","ror":"https://ror.org/023qdcg29","country_code":"FR","type":"company","lineage":["https://openalex.org/I112991645","https://openalex.org/I4210121748"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Yann Besse","raw_affiliation_strings":["Airbus, France"],"raw_orcid":"https://orcid.org/0009-0008-3639-6090","affiliations":[{"raw_affiliation_string":"Airbus, France","institution_ids":["https://openalex.org/I112991645"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001743328","display_name":"Dennis G. Wilson","orcid":"https://orcid.org/0000-0003-2414-0051"},"institutions":[{"id":"https://openalex.org/I17866349","display_name":"Universit\u00e9 F\u00e9d\u00e9rale de Toulouse Midi-Pyr\u00e9n\u00e9es","ror":"https://ror.org/004raaa70","country_code":"FR","type":"education","lineage":["https://openalex.org/I17866349"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Dennis G. Wilson","raw_affiliation_strings":["ISAE-Supaero, Universit\u00e9 de Toulouse, France"],"raw_orcid":"https://orcid.org/0000-0003-2414-0051","affiliations":[{"raw_affiliation_string":"ISAE-Supaero, Universit\u00e9 de Toulouse, France","institution_ids":["https://openalex.org/I17866349"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2615,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6294704,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"3","issue":"3","first_page":"1","last_page":"20"},"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"}},{"id":"https://openalex.org/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10646","display_name":"Experimental Behavioral Economics Studies","score":0.9717000126838684,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/curiosity","display_name":"Curiosity","score":0.9879815578460693},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.6939924955368042},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.520774781703949},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48339715600013733},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.46162229776382446},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.45553115010261536},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.3310268223285675},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.321169912815094},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.13354694843292236},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0906628966331482}],"concepts":[{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.9879815578460693},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.6939924955368042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.520774781703949},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48339715600013733},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.46162229776382446},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.45553115010261536},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.3310268223285675},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.321169912815094},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.13354694843292236},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0906628966331482},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3605782","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3605782","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3605782","source":{"id":"https://openalex.org/S4210221532","display_name":"ACM Transactions on Evolutionary Learning and Optimization","issn_l":"2688-299X","issn":["2688-299X","2688-3007"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Evolutionary Learning and Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3605782","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3605782","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3605782","source":{"id":"https://openalex.org/S4210221532","display_name":"ACM Transactions on Evolutionary Learning and Optimization","issn_l":"2688-299X","issn":["2688-299X","2688-3007"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Evolutionary Learning and Optimization","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4382680334.pdf","grobid_xml":"https://content.openalex.org/works/W4382680334.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W120361141","https://openalex.org/W1738827650","https://openalex.org/W2020451939","https://openalex.org/W2099746672","https://openalex.org/W2112036188","https://openalex.org/W2145339207","https://openalex.org/W2151083897","https://openalex.org/W2161966552","https://openalex.org/W2556477470","https://openalex.org/W2596367596","https://openalex.org/W2604373826","https://openalex.org/W2779977383","https://openalex.org/W2781585732","https://openalex.org/W2914261249","https://openalex.org/W2947246097","https://openalex.org/W2950794298","https://openalex.org/W2964025389","https://openalex.org/W2969456553","https://openalex.org/W2992977009","https://openalex.org/W2994369270","https://openalex.org/W2995298643","https://openalex.org/W3018036994","https://openalex.org/W3043524450","https://openalex.org/W3090861407","https://openalex.org/W3098960920","https://openalex.org/W3103183699","https://openalex.org/W3112009288","https://openalex.org/W3126171498","https://openalex.org/W3129322645","https://openalex.org/W3155633270","https://openalex.org/W3167445240","https://openalex.org/W3167538233","https://openalex.org/W3180151790","https://openalex.org/W3206305573","https://openalex.org/W4221143659","https://openalex.org/W4225892134","https://openalex.org/W4250503569","https://openalex.org/W4293154685","https://openalex.org/W4300091631","https://openalex.org/W4300799055","https://openalex.org/W6730153900","https://openalex.org/W6740801417","https://openalex.org/W6747387971","https://openalex.org/W6826873949"],"related_works":["https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"When":[0],"searching":[1],"for":[2,30,109,129],"policies,":[3],"reward-sparse":[4],"environments":[5],"often":[6],"lack":[7],"sufficient":[8],"information":[9],"about":[10],"which":[11,139],"behaviors":[12],"to":[13,27,48,52,58,94,136],"improve":[14],"upon":[15],"or":[16,44],"avoid.":[17],"In":[18,67],"such":[19],"environments,":[20],"the":[21,127],"policy":[22,83],"search":[23,29,40,84],"process":[24],"is":[25,51,65],"bound":[26],"blindly":[28],"reward-yielding":[31],"transitions":[32,61],"and":[33,118,134],"no":[34],"early":[35],"reward":[36,64],"can":[37,122],"bias":[38],"this":[39,50,68],"in":[41,56,80],"one":[42],"direction":[43],"another.":[45],"A":[46],"way":[47],"overcome":[49],"use":[53,71,95],"intrinsic":[54,77],"motivation":[55],"order":[57],"explore":[59],"new":[60],"until":[62],"a":[63,72,98],"found.":[66],"work,":[69],"we":[70],"recently":[73],"proposed":[74],"definition":[75],"of":[76],"motivation,":[78],"Curiosity,":[79],"an":[81,90,130],"evolutionary":[82,91,106],"method.":[85],"We":[86,101],"propose":[87],"Curiosity-ES,":[88],"1":[89],"strategy":[92],"adapted":[93],"Curiosity":[96],"as":[97,111,113],"fitness":[99],"metric.":[100],"compare":[102],"Curiosity-ES":[103,121],"with":[104,114],"other":[105],"algorithms":[107],"intended":[108],"exploration,":[110],"well":[112],"Curiosity-based":[115],"reinforcement":[116],"learning,":[117],"find":[119,140],"that":[120],"generate":[123],"higher":[124],"diversity":[125,132],"without":[126],"need":[128],"explicit":[131],"criterion":[133],"leads":[135],"more":[137],"policies":[138],"reward.":[141]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2023-07-01T00:00:00"}
