{"id":"https://openalex.org/W3035026685","doi":"https://doi.org/10.1145/3512290.3528845","title":"Diversity Policy Gradient for Sample Efficient Quality-Diversity Optimization","display_name":"Diversity Policy Gradient for Sample Efficient Quality-Diversity Optimization","publication_year":2020,"publication_date":"2020-06-15","ids":{"openalex":"https://openalex.org/W3035026685","doi":"https://doi.org/10.1145/3512290.3528845","mag":"3035026685"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2006.08505","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.08505","pdf_url":"https://arxiv.org/pdf/2006.08505","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2006.08505","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015141560","display_name":"Thomas Pierrot","orcid":"https://orcid.org/0000-0002-5227-6194"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pierrot, Thomas","raw_affiliation_strings":["InstaDeep"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"InstaDeep","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mac\\'e, Valentin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mac\\'e, Valentin","raw_affiliation_strings":["InstaDeep"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"InstaDeep","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chalumeau, F\\'elix","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chalumeau, F\\'elix","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Flajolet, Arthur","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Flajolet, Arthur","raw_affiliation_strings":["InstaDeep"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"InstaDeep","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028486593","display_name":"Geoffrey Cideron","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cideron, Geoffrey","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067029999","display_name":"Karim Beguir","orcid":"https://orcid.org/0000-0002-2789-6527"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Beguir, Karim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Cully, Antoine","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cully, Antoine","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042850624","display_name":"Olivier Sigaud","orcid":"https://orcid.org/0000-0002-8544-0229"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sigaud, Olivier","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Perrin-Gilbert, Nicolas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Perrin-Gilbert, Nicolas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T11182","display_name":"Auction Theory and Applications","score":0.9753000140190125,"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"}},{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.963100016117096,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/mixing","display_name":"Mixing (physics)","score":0.7766633033752441},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.7485023736953735},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7131591439247131},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6343778371810913},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5759057402610779},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4293510913848877},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4029493033885956},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.19602236151695251},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1558251678943634},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.12342387437820435},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.12308099865913391},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.06467527151107788}],"concepts":[{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.7766633033752441},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.7485023736953735},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7131591439247131},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6343778371810913},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5759057402610779},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4293510913848877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4029493033885956},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.19602236151695251},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1558251678943634},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.12342387437820435},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.12308099865913391},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.06467527151107788},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:arXiv.org:2006.08505","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.08505","pdf_url":"https://arxiv.org/pdf/2006.08505","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2006.08505","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.08505","pdf_url":"https://arxiv.org/pdf/2006.08505","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4666169063","display_name":"Virtual humanoids learning motion skills","funder_award_id":"ANR-18-CE33-0005","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W567721252","https://openalex.org/W758372786","https://openalex.org/W2132083787","https://openalex.org/W2151083897","https://openalex.org/W2173248099","https://openalex.org/W2462548332","https://openalex.org/W2596367596","https://openalex.org/W2623491082","https://openalex.org/W2724169821","https://openalex.org/W2733961795","https://openalex.org/W2744921630","https://openalex.org/W2765602917","https://openalex.org/W2766447205","https://openalex.org/W2770298516","https://openalex.org/W2778749116","https://openalex.org/W2785542505","https://openalex.org/W2786917922","https://openalex.org/W2787938642","https://openalex.org/W2810602713","https://openalex.org/W2894662639","https://openalex.org/W2904246096","https://openalex.org/W2914261249","https://openalex.org/W2922007426","https://openalex.org/W2949475445","https://openalex.org/W2953326529","https://openalex.org/W2954644321","https://openalex.org/W2963438456","https://openalex.org/W2963790038","https://openalex.org/W2964214518","https://openalex.org/W2974639061","https://openalex.org/W2981030070","https://openalex.org/W2996001434","https://openalex.org/W3000146453","https://openalex.org/W3004082694","https://openalex.org/W3013618273","https://openalex.org/W3020367954","https://openalex.org/W3101747404"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2089013912","https://openalex.org/W2076061571","https://openalex.org/W1987513656","https://openalex.org/W2145821588"],"abstract_inverted_index":{"A":[0],"fascinating":[1],"aspect":[2],"of":[3,16,113,125,138,144],"nature":[4],"lies":[5],"in":[6,22,44,63,131,163],"its":[7,198],"ability":[8],"to":[9,37,46,52,79,121,157,182],"produce":[10,122],"a":[11,33,38,49,60,105,123,145,164,173],"large":[12],"and":[13,117,127,176,186],"diverse":[14,126],"collection":[15,74,124],"organisms":[17],"that":[18,58,150,191],"are":[19,95],"all":[20],"high-performing":[21,128],"their":[23],"niche.":[24],"By":[25],"contrast,":[26],"most":[27],"AI":[28],"algorithms":[29,97,116],"focus":[30],"on":[31],"finding":[32],"single":[34],"efficient":[35],"solution":[36],"given":[39],"problem.":[40],"Aiming":[41],"for":[42,68,86,99],"diversity":[43,162],"addition":[45],"performance":[47],"is":[48,141,193],"convenient":[50],"way":[51],"deal":[53],"with":[54],"the":[55,72,80,111,142,154],"exploration-exploitation":[56],"trade-off":[57],"plays":[59],"central":[61],"role":[62],"learning.":[64],"It":[65],"also":[66],"allows":[67],"increased":[69],"robustness":[70],"when":[71],"returned":[73],"contains":[75],"several":[76],"working":[77],"solutions":[78],"considered":[81],"problem,":[82],"making":[83],"it":[84],"well-suited":[85],"real":[87],"applications":[88],"such":[89],"as":[90],"robotics.":[91],"Quality-Diversity":[92],"(QD)":[93],"methods":[94],"evolutionary":[96,199],"designed":[98],"this":[100,139],"purpose.":[101],"This":[102],"paper":[103],"proposes":[104],"novel":[106],"algorithm,":[107],"QDPG,":[108],"which":[109],"combines":[110],"strength":[112],"Policy":[114,147],"Gradient":[115,148],"Quality":[118],"Diversity":[119,146],"approaches":[120],"neural":[129,170],"policies":[130,159],"continuous":[132],"control":[133],"environments.":[134],"The":[135],"main":[136],"contribution":[137],"work":[140],"introduction":[143],"(DPG)":[149],"exploits":[151],"information":[152],"at":[153],"time-step":[155],"level":[156],"drive":[158],"towards":[160],"more":[161,195],"sample-efficient":[165,196],"manner.":[166],"Specifically,":[167],"QDPG":[168,192],"selects":[169],"controllers":[171],"from":[172],"MAP-Elites":[174],"grid":[175],"uses":[177],"two":[178],"gradient-based":[179],"mutation":[180],"operators":[181],"improve":[183],"both":[184],"quality":[185],"diversity.":[187],"Our":[188],"results":[189],"demonstrate":[190],"significantly":[194],"than":[197],"competitors.":[200]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}