{"id":"https://openalex.org/W3175917212","doi":"https://doi.org/10.1145/3449639.3459304","title":"Policy gradient assisted MAP-Elites","display_name":"Policy gradient assisted MAP-Elites","publication_year":2021,"publication_date":"2021-06-21","ids":{"openalex":"https://openalex.org/W3175917212","doi":"https://doi.org/10.1145/3449639.3459304","mag":"3175917212"},"language":"en","primary_location":{"id":"doi:10.1145/3449639.3459304","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3449639.3459304","pdf_url":null,"source":{"id":"https://openalex.org/S4363608932","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.archives-ouvertes.fr/hal-03135723","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103685930","display_name":"Olle Nilsson","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Olle Nilsson","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011747084","display_name":"Antoine Cully","orcid":"https://orcid.org/0000-0002-3190-7073"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Antoine Cully","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.0879,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.97319778,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"866","last_page":"875"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9975000023841858,"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"}},{"id":"https://openalex.org/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9894999861717224,"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/robotics","display_name":"Robotics","score":0.7018799185752869},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6932839751243591},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6350058317184448},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5904704332351685},{"id":"https://openalex.org/keywords/evolutionary-robotics","display_name":"Evolutionary robotics","score":0.5890638828277588},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5821607112884521},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.5580941438674927},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5502451062202454},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.5065847635269165},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4946870505809784},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4632291793823242},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.46014460921287537},{"id":"https://openalex.org/keywords/evolutionary-algorithm","display_name":"Evolutionary algorithm","score":0.45388561487197876},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4139925241470337},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36333996057510376}],"concepts":[{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.7018799185752869},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6932839751243591},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6350058317184448},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5904704332351685},{"id":"https://openalex.org/C199505168","wikidata":"https://www.wikidata.org/wiki/Q3267529","display_name":"Evolutionary robotics","level":3,"score":0.5890638828277588},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5821607112884521},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.5580941438674927},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5502451062202454},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.5065847635269165},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4946870505809784},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4632291793823242},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.46014460921287537},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.45388561487197876},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4139925241470337},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36333996057510376},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3449639.3459304","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3449639.3459304","pdf_url":null,"source":{"id":"https://openalex.org/S4363608932","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-03135723v1","is_oa":true,"landing_page_url":"https://hal.archives-ouvertes.fr/hal-03135723","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://hal.archives-ouvertes.fr/hal-03135723","raw_type":"info:eu-repo/semantics/preprint"},{"id":"pmh:oai:HAL:hal-03135723v2","is_oa":true,"landing_page_url":"https://hal.science/hal-03135723","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"The Genetic and Evolutionary Computation Conference, Jul 2021, Lille, France. ⟨10.1145/3449639.3459304⟩","raw_type":"Conference papers"},{"id":"pmh:oai:oskar-bordeaux.fr:20.500.12278/37054","is_oa":false,"landing_page_url":"https://oskar-bordeaux.fr/handle/20.500.12278/37054","pdf_url":null,"source":{"id":"https://openalex.org/S4306402569","display_name":"Oskar-Bordeaux (Universite de Bordeaux)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Communication dans un congr\u00e8s avec actes"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-03135723v1","is_oa":true,"landing_page_url":"https://hal.archives-ouvertes.fr/hal-03135723","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://hal.archives-ouvertes.fr/hal-03135723","raw_type":"info:eu-repo/semantics/preprint"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.5,"id":"https://metadata.un.org/sdg/11"}],"awards":[{"id":"https://openalex.org/G8338956521","display_name":null,"funder_award_id":"EP/V006673/1 project REcoVER","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G866405208","display_name":"REcoVER: Learning algorithms for REsilient and VErsatile Robots","funder_award_id":"EP/V006673/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8782551874","display_name":null,"funder_award_id":"EP/V006673/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320283","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W758372786","https://openalex.org/W1738827650","https://openalex.org/W1757796397","https://openalex.org/W1965675101","https://openalex.org/W1974150877","https://openalex.org/W1980516134","https://openalex.org/W2018435387","https://openalex.org/W2099746672","https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2151083897","https://openalex.org/W2165150801","https://openalex.org/W2173248099","https://openalex.org/W2342068300","https://openalex.org/W2462548332","https://openalex.org/W2566523535","https://openalex.org/W2592285292","https://openalex.org/W2596367596","https://openalex.org/W2612690371","https://openalex.org/W2620641794","https://openalex.org/W2623491082","https://openalex.org/W2739858255","https://openalex.org/W2744921630","https://openalex.org/W2765397130","https://openalex.org/W2785542505","https://openalex.org/W2787387965","https://openalex.org/W2787938642","https://openalex.org/W2788904251","https://openalex.org/W2797210984","https://openalex.org/W2797471289","https://openalex.org/W2809762329","https://openalex.org/W2809844857","https://openalex.org/W2894662639","https://openalex.org/W2898585845","https://openalex.org/W2947246097","https://openalex.org/W2962687375","https://openalex.org/W2963438456","https://openalex.org/W2963790038","https://openalex.org/W2964001908","https://openalex.org/W2964043796","https://openalex.org/W2976102139","https://openalex.org/W2994369270","https://openalex.org/W3009830825","https://openalex.org/W3009840839","https://openalex.org/W3035026685","https://openalex.org/W3041043431","https://openalex.org/W3042891072","https://openalex.org/W3095471059","https://openalex.org/W3098960920","https://openalex.org/W3099344189","https://openalex.org/W3101747404","https://openalex.org/W3103183699","https://openalex.org/W3103202942","https://openalex.org/W3104601631","https://openalex.org/W4212774754"],"related_works":["https://openalex.org/W4244439390","https://openalex.org/W2380659006","https://openalex.org/W4251432983","https://openalex.org/W2096206748","https://openalex.org/W4381586542","https://openalex.org/W2076767946","https://openalex.org/W2095960527","https://openalex.org/W2011837598","https://openalex.org/W1976294505","https://openalex.org/W4212806423"],"abstract_inverted_index":{"Quality-Diversity":[0],"optimization":[1,18],"algorithms":[2],"such":[3],"as":[4],"MAP-Elites,":[5],"aim":[6],"to":[7,16,56,77,106,119,175],"generate":[8],"collections":[9],"of":[10,28,39,46,127,170],"both":[11],"diverse":[12,139],"and":[13,111,140],"high-performing":[14,141],"solutions":[15,110],"an":[17,132],"problem.":[19],"MAP-Elites":[20,53,69,76],"has":[21],"shown":[22],"promising":[23],"results":[24,162],"in":[25,32],"a":[26,71,86,102,115,121],"variety":[27],"applications.":[29],"In":[30],"particular":[31],"evolutionary":[33],"robotics":[34,51],"tasks":[35,150],"targeting":[36],"the":[37,44,168,171],"generation":[38],"behavioral":[40,153],"repertoires":[41,154,173],"that":[42,74,155,164],"highlight":[43],"versatility":[45],"robots.":[47],"However,":[48],"for":[49,137,151],"most":[50],"applications":[52],"is":[54,112],"limited":[55],"using":[57],"simple":[58],"open-loop":[59],"or":[60],"low-dimensional":[61],"controllers.":[62,160],"Here":[63],"we":[64],"present":[65],"Policy":[66],"Gradient":[67],"Assisted":[68],"(PGA-MAP-Elites),":[70],"novel":[72],"algorithm":[73,136],"enables":[75],"efficiently":[78],"evolve":[79],"large":[80],"neural":[81,104,158],"network":[82,105,159],"controllers":[83],"by":[84,91],"introducing":[85],"gradient-based":[87],"variation":[88,118],"operator":[89,96],"inspired":[90],"Deep":[92],"Reinforcement":[93],"Learning.":[94],"This":[95],"leverages":[97],"gradient":[98],"estimates":[99],"obtained":[100],"from":[101],"critic":[103],"rapidly":[107],"find":[108],"higher-performing":[109],"paired":[113],"with":[114],"traditional":[116],"genetic":[117],"maintain":[120],"divergent":[122],"search":[123],"behavior.":[124],"The":[125,161],"synergy":[126],"these":[128],"operators":[129],"makes":[130],"PGA-MAP-Elites":[131,165],"efficient":[133],"yet":[134],"powerful":[135],"finding":[138],"behaviors.":[142],"We":[143],"evaluate":[144],"our":[145],"method":[146],"on":[147],"four":[148],"different":[149],"building":[152],"use":[156],"deep":[157],"show":[163],"significantly":[166],"improves":[167],"quality":[169],"generated":[172],"compared":[174],"existing":[176],"methods.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}