{"id":"https://openalex.org/W2978280891","doi":"https://doi.org/10.1109/devlrn.2019.8850727","title":"Behavioral Repertoire via Generative Adversarial Policy Networks","display_name":"Behavioral Repertoire via Generative Adversarial Policy Networks","publication_year":2019,"publication_date":"2019-08-01","ids":{"openalex":"https://openalex.org/W2978280891","doi":"https://doi.org/10.1109/devlrn.2019.8850727","mag":"2978280891"},"language":"en","primary_location":{"id":"doi:10.1109/devlrn.2019.8850727","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2019.8850727","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/3665ea01-b387-4a45-96d9-44327833c990","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083432303","display_name":"Marija Jegorova","orcid":"https://orcid.org/0000-0001-6319-9537"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Marija Jegorova","raw_affiliation_strings":["School of Informatics, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003629424","display_name":"St\u00e9phane Doncieux","orcid":"https://orcid.org/0000-0003-1541-054X"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210150358","display_name":"Institut Syst\u00e8mes Intelligents et de Robotique","ror":"https://ror.org/05neq8668","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210150358","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Stephane Doncieux","raw_affiliation_strings":["Sorbonne Universit\u00e9, CNRS, ISIR, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sorbonne Universit\u00e9, CNRS, ISIR, Paris, France","institution_ids":["https://openalex.org/I4210150358","https://openalex.org/I1294671590","https://openalex.org/I39804081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087823932","display_name":"Timothy M. Hospedales","orcid":"https://orcid.org/0000-0003-4867-7486"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Timothy M. Hospedales","raw_affiliation_strings":["School of Informatics, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7059,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78355551,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"320","last_page":"326"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9873999953269958,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9789999723434448,"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/computer-science","display_name":"Computer science","score":0.717534065246582},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6255989074707031},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5972663760185242},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.5860986113548279},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5817549228668213},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5727460980415344},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.49026134610176086},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.47431135177612305},{"id":"https://openalex.org/keywords/repertoire","display_name":"Repertoire","score":0.44308075308799744},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4409805238246918},{"id":"https://openalex.org/keywords/clutter","display_name":"Clutter","score":0.4263281226158142},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4140876531600952},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3888321816921234}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.717534065246582},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6255989074707031},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5972663760185242},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.5860986113548279},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5817549228668213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5727460980415344},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.49026134610176086},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.47431135177612305},{"id":"https://openalex.org/C2778473898","wikidata":"https://www.wikidata.org/wiki/Q2145110","display_name":"Repertoire","level":2,"score":0.44308075308799744},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4409805238246918},{"id":"https://openalex.org/C132094186","wikidata":"https://www.wikidata.org/wiki/Q641585","display_name":"Clutter","level":3,"score":0.4263281226158142},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4140876531600952},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3888321816921234},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"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/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/devlrn.2019.8850727","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2019.8850727","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/3665ea01-b387-4a45-96d9-44327833c990","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/3665ea01-b387-4a45-96d9-44327833c990","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Jegorova, M, Doncieux, S & Hospedales, T 2019, Behavioral Repertoire via Generative Adversarial Policy Networks. in 2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob). Institute of Electrical and Electronics Engineers, pp. 320-326, 9th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics, Oslo, Norway, 19/08/19. https://doi.org/10.1109/DEVLRN.2019.8850727","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/34f83e43-1eff-4d3f-ad77-0844203728fb","is_oa":false,"landing_page_url":"https://hdl.handle.net/20.500.11820/34f83e43-1eff-4d3f-ad77-0844203728fb","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":""},{"id":"pmh:oai:pure.ed.ac.uk:publications/3665ea01-b387-4a45-96d9-44327833c990","is_oa":false,"landing_page_url":"http://hdl.handle.net/20.500.11820/3665ea01-b387-4a45-96d9-44327833c990","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/3665ea01-b387-4a45-96d9-44327833c990","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/3665ea01-b387-4a45-96d9-44327833c990","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Jegorova, M, Doncieux, S & Hospedales, T 2019, Behavioral Repertoire via Generative Adversarial Policy Networks. in 2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob). Institute of Electrical and Electronics Engineers, pp. 320-326, 9th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics, Oslo, Norway, 19/08/19. https://doi.org/10.1109/DEVLRN.2019.8850727","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1510052597","https://openalex.org/W1710476689","https://openalex.org/W1738827650","https://openalex.org/W1929309940","https://openalex.org/W1972063518","https://openalex.org/W1984446294","https://openalex.org/W2011222378","https://openalex.org/W2014268383","https://openalex.org/W2015630562","https://openalex.org/W2032179398","https://openalex.org/W2099746672","https://openalex.org/W2108579430","https://openalex.org/W2119717200","https://openalex.org/W2125389028","https://openalex.org/W2130405068","https://openalex.org/W2151083897","https://openalex.org/W2405756170","https://openalex.org/W2419545936","https://openalex.org/W2462548332","https://openalex.org/W2591436094","https://openalex.org/W2727901370","https://openalex.org/W2735027910","https://openalex.org/W2741134157","https://openalex.org/W2772778096","https://openalex.org/W2778749116","https://openalex.org/W2962687375","https://openalex.org/W2962837436","https://openalex.org/W2962879692","https://openalex.org/W2963169977","https://openalex.org/W2963277051","https://openalex.org/W2963328631","https://openalex.org/W2963373786","https://openalex.org/W2963438456","https://openalex.org/W2963684088","https://openalex.org/W2963864421","https://openalex.org/W2964157221","https://openalex.org/W4210352771","https://openalex.org/W4240805545","https://openalex.org/W4295521014","https://openalex.org/W4300982816","https://openalex.org/W6637568146","https://openalex.org/W6684921986","https://openalex.org/W6685352114","https://openalex.org/W6713645886","https://openalex.org/W6718092244","https://openalex.org/W6718379498","https://openalex.org/W6735913928","https://openalex.org/W6740758455","https://openalex.org/W6748603076","https://openalex.org/W6779669310"],"related_works":["https://openalex.org/W2163296013","https://openalex.org/W2743859443","https://openalex.org/W4255048859","https://openalex.org/W2326995835","https://openalex.org/W3120300186","https://openalex.org/W2084831119","https://openalex.org/W165915117","https://openalex.org/W4288282832","https://openalex.org/W2956331735","https://openalex.org/W2963244934"],"abstract_inverted_index":{"Learning":[0],"algorithms":[1],"are":[2],"enabling":[3],"robots":[4],"to":[5,32,39,56,130,196],"solve":[6],"increasingly":[7],"challenging":[8],"real-world":[9],"tasks.":[10],"These":[11],"approaches":[12],"often":[13,200],"rely":[14],"on":[15],"demonstrations":[16],"and":[17,41,125],"reproduce":[18],"the":[19,25,34,74,165,205],"behavior":[20],"shown.":[21],"Unexpected":[22],"changes":[23],"in":[24,45,164,204],"environment":[26],"may":[27],"require":[28],"using":[29],"different":[30],"behaviors":[31,63,143,179],"achieve":[33],"same":[35],"effect,":[36],"for":[37,64,116,150],"instance":[38],"reach":[40],"grasp":[42],"an":[43,120,159,181],"object":[44],"changing":[46],"clutter.":[47],"An":[48],"emerging":[49],"paradigm":[50],"addressing":[51],"this":[52,85,93,156,172],"robustness":[53],"issue":[54],"is":[55],"learn":[57],"a":[58,65,70,81,89,97,105,109,138,151,175,193],"diverse":[59],"set":[60],"of":[61,92,123,161,167,178,189,207],"successful":[62],"given":[66],"task,":[67],"from":[68],"which":[69],"robot":[71,139,195],"can":[72,140],"select":[73],"most":[75],"suitable":[76],"policy":[77,136],"when":[78,201],"faced":[79],"with":[80,158],"new":[82,152],"environment.":[83,153],"In":[84],"paper,":[86],"we":[87],"explore":[88],"novel":[90,127,142],"realization":[91],"vision":[94],"by":[95],"learning":[96,104],"generative":[98,114,135],"model":[99,115],"over":[100],"policies.":[101],"Rather":[102],"than":[103,180],"single":[106],"policy,":[107],"or":[108],"small":[110],"fixed":[111],"repertoire,":[112],"our":[113,134],"policies":[117,124],"compactly":[118],"encodes":[119],"unbounded":[121],"number":[122],"allows":[126],"controller":[128],"variants":[129],"be":[131],"sampled.":[132],"Leveraging":[133],"network,":[137],"sample":[141],"until":[144],"it":[145],"finds":[146],"one":[147],"that":[148,171],"works":[149],"We":[154,169],"demonstrate":[155],"idea":[157],"application":[160],"robust":[162],"ball-throwing":[163],"presence":[166,206],"obstacles.":[168,208],"show":[170],"approach":[173],"achieves":[174],"greater":[176],"diversity":[177],"existing":[182],"evolutionary":[183],"approach,":[184],"while":[185],"maintaining":[186],"good":[187],"efficacy":[188],"sampled":[190],"behaviors,":[191],"allowing":[192],"Baxter":[194],"hit":[197],"targets":[198],"more":[199],"ball":[202],"throwing":[203]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}