{"id":"https://openalex.org/W4384024810","doi":"https://doi.org/10.1145/3583131.3590503","title":"MAP-Elites with Descriptor-Conditioned Gradients and Archive Distillation into a Single Policy","display_name":"MAP-Elites with Descriptor-Conditioned Gradients and Archive Distillation into a Single Policy","publication_year":2023,"publication_date":"2023-07-12","ids":{"openalex":"https://openalex.org/W4384024810","doi":"https://doi.org/10.1145/3583131.3590503"},"language":"en","primary_location":{"id":"doi:10.1145/3583131.3590503","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583131.3590503","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583131.3590503","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3583131.3590503","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082433472","display_name":"Maxence Faldor","orcid":"https://orcid.org/0000-0003-4743-9494"},"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":"Maxence Faldor","raw_affiliation_strings":["Adaptive and Intelligent Robotics Lab, Imperial College London, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-4743-9494","affiliations":[{"raw_affiliation_string":"Adaptive and Intelligent Robotics Lab, Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057428630","display_name":"F\u00e9lix Chalumeau","orcid":"https://orcid.org/0000-0001-9476-2900"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"F\u00e9lix Chalumeau","raw_affiliation_strings":["InstaDeep, Paris, France"],"raw_orcid":"https://orcid.org/0000-0001-9476-2900","affiliations":[{"raw_affiliation_string":"InstaDeep, Paris, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060282741","display_name":"Manon Flageat","orcid":"https://orcid.org/0000-0002-4601-2176"},"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":"Manon Flageat","raw_affiliation_strings":["Adaptive and Intelligent Robotics Lab, Imperial College London, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-4601-2176","affiliations":[{"raw_affiliation_string":"Adaptive and Intelligent Robotics Lab, 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":["Adaptive and Intelligent Robotics Lab, Imperial College London, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-3190-7073","affiliations":[{"raw_affiliation_string":"Adaptive and Intelligent Robotics Lab, Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9357,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.74665294,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"138","last_page":"146"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9993000030517578,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9973999857902527,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6925568580627441},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6640262603759766},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6500488519668579},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.5989652276039124},{"id":"https://openalex.org/keywords/evolutionary-robotics","display_name":"Evolutionary robotics","score":0.5892490148544312},{"id":"https://openalex.org/keywords/evolutionary-algorithm","display_name":"Evolutionary algorithm","score":0.582561731338501},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5464327931404114},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.53233802318573},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5209940075874329},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5045293569564819},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.4644332826137543},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45754170417785645},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4512540102005005},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.44205427169799805},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.43658122420310974},{"id":"https://openalex.org/keywords/evolutionary-computation","display_name":"Evolutionary computation","score":0.42940229177474976},{"id":"https://openalex.org/keywords/genetic-programming","display_name":"Genetic programming","score":0.42484933137893677},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4204520285129547},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3911220133304596},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.262727826833725},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2008044719696045}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6925568580627441},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6640262603759766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6500488519668579},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.5989652276039124},{"id":"https://openalex.org/C199505168","wikidata":"https://www.wikidata.org/wiki/Q3267529","display_name":"Evolutionary robotics","level":3,"score":0.5892490148544312},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.582561731338501},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5464327931404114},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.53233802318573},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5209940075874329},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5045293569564819},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.4644332826137543},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45754170417785645},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4512540102005005},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.44205427169799805},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.43658122420310974},{"id":"https://openalex.org/C105902424","wikidata":"https://www.wikidata.org/wiki/Q1197129","display_name":"Evolutionary computation","level":2,"score":0.42940229177474976},{"id":"https://openalex.org/C110332635","wikidata":"https://www.wikidata.org/wiki/Q629498","display_name":"Genetic programming","level":2,"score":0.42484933137893677},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4204520285129547},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3911220133304596},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.262727826833725},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2008044719696045},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3583131.3590503","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583131.3590503","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583131.3590503","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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:spiral.imperial.ac.uk:10044/1/104024","is_oa":true,"landing_page_url":"http://hdl.handle.net/10044/1/104024","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"The Genetic and Evolutionary Computation Conference","raw_type":"Conference Paper"}],"best_oa_location":{"id":"doi:10.1145/3583131.3590503","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583131.3590503","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583131.3590503","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4384024810.pdf","grobid_xml":"https://content.openalex.org/works/W4384024810.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1738827650","https://openalex.org/W2137983211","https://openalex.org/W2145339207","https://openalex.org/W2257979135","https://openalex.org/W2606327391","https://openalex.org/W2924740141","https://openalex.org/W2982316857","https://openalex.org/W3175917212","https://openalex.org/W4221140786","https://openalex.org/W4281480632","https://openalex.org/W4287123807","https://openalex.org/W4287757595","https://openalex.org/W4304194242","https://openalex.org/W4313889501","https://openalex.org/W4320167187","https://openalex.org/W4394662461"],"related_works":["https://openalex.org/W2186275702","https://openalex.org/W2176531811","https://openalex.org/W2546939201","https://openalex.org/W2542354426","https://openalex.org/W2547848286","https://openalex.org/W2543649460","https://openalex.org/W2544632397","https://openalex.org/W4879471","https://openalex.org/W2587876269","https://openalex.org/W2545494728"],"abstract_inverted_index":{"Quality-Diversity":[0],"algorithms,":[1],"such":[2],"as":[3],"MAP-Elites,":[4],"are":[5],"a":[6,24,36,63,120,140,184],"branch":[7],"of":[8,13,26,54,76,93,150,164,186],"Evolutionary":[9],"Computation":[10],"generating":[11],"collections":[12],"diverse":[14],"and":[15,28,47],"high-performing":[16],"solutions,":[17],"that":[18,123,158],"have":[19],"been":[20],"successfully":[21],"applied":[22],"to":[23,51,138],"variety":[25],"domains":[27],"particularly":[29],"in":[30,167],"evolutionary":[31],"robotics.":[32],"However,":[33],"MAP-Elites":[34],"performs":[35],"divergent":[37],"search":[38,92],"based":[39],"on":[40,86,181,183],"random":[41],"mutations":[42,100],"originating":[43],"from":[44],"Genetic":[45],"Algorithms,":[46],"thus,":[48],"is":[49],"limited":[50],"evolving":[52],"populations":[53],"low-dimensional":[55],"solutions.":[56,103],"PGA-MAP-Elites":[57,84,178],"overcomes":[58],"this":[59,105],"limitation":[60],"by":[61,68,179],"integrating":[62],"gradient-based":[64,95],"variation":[65,117],"operator":[66,96,118],"inspired":[67],"Deep":[69],"Reinforcement":[70],"Learning":[71],"which":[72],"enables":[73],"the":[74,90,94,114,125,128,135,148,151,161,168,174],"evolution":[75],"large":[77],"neural":[78],"networks.":[79],"Although":[80],"high-performingin":[81],"many":[82],"environments,":[83],"fails":[85],"several":[87],"tasks":[88],"where":[89],"convergent":[91],"does":[97],"not":[98],"direct":[99],"towards":[101],"archive-improving":[102],"In":[104],"work,":[106],"we":[107,112,133],"present":[108],"two":[109],"contributions:":[110],"(1)":[111],"enhance":[113],"Policy":[115],"Gradient":[116],"with":[119],"descriptor-conditioned":[121,141],"critic":[122],"improves":[124,173],"archive":[126,152],"across":[127],"entire":[129,162],"descriptor":[130],"space,":[131],"(2)":[132],"exploit":[134],"actor-critic":[136],"training":[137],"learn":[139],"policy":[142,157],"at":[143],"no":[144],"additional":[145],"cost,":[146],"distilling":[147],"knowledge":[149],"into":[153],"one":[154],"single":[155],"versatile":[156],"can":[159],"execute":[160],"range":[163],"behaviors":[165],"contained":[166],"archive.":[169],"Our":[170],"algorithm,":[171],"DCG-MAP-Elites":[172],"QD":[175],"score":[176],"over":[177],"82%":[180],"average,":[182],"set":[185],"challenging":[187],"locomotion":[188],"tasks.":[189]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}