{"id":"https://openalex.org/W3040907965","doi":"https://doi.org/10.1109/tcds.2020.3008574","title":"Behavioral Repertoire via Generative Adversarial Policy Networks","display_name":"Behavioral Repertoire via Generative Adversarial Policy Networks","publication_year":2020,"publication_date":"2020-07-10","ids":{"openalex":"https://openalex.org/W3040907965","doi":"https://doi.org/10.1109/tcds.2020.3008574","mag":"3040907965"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2020.3008574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2020.3008574","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cognitive and Developmental Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/34f83e43-1eff-4d3f-ad77-0844203728fb","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":true,"raw_author_name":"Marija Jegorova","raw_affiliation_strings":["School of Informatics, University of Edinburgh, Edinburgh, U.K"],"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, Edinburgh, U.K","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 Université, CNRS, ISIR, Paris, France"],"affiliations":[{"raw_affiliation_string":"Sorbonne Université, 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, Edinburgh, U.K"],"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5083432303"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":0.6628,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.75657979,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"14","issue":"4","first_page":"1344","last_page":"1355"},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.992900013923645,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9891999959945679,"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":0.6687610745429993},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6230120658874512},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5999899506568909},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.5968359112739563},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5657263994216919},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5587217807769775},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5108644366264343},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4730745255947113},{"id":"https://openalex.org/keywords/repertoire","display_name":"Repertoire","score":0.462956964969635},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4168376922607422},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3914357125759125},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3631112277507782}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6687610745429993},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6230120658874512},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5999899506568909},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.5968359112739563},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5657263994216919},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5587217807769775},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5108644366264343},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4730745255947113},{"id":"https://openalex.org/C2778473898","wikidata":"https://www.wikidata.org/wiki/Q2145110","display_name":"Repertoire","level":2,"score":0.462956964969635},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4168376922607422},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3914357125759125},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3631112277507782},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tcds.2020.3008574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2020.3008574","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cognitive and Developmental Systems","raw_type":"journal-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/34f83e43-1eff-4d3f-ad77-0844203728fb","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Jegorova, M, Doncieux, S & Hospedales, T M 2022, 'Behavioral Repertoire via Generative Adversarial Policy Networks', IEEE Transactions on Cognitive and Developmental Systems, vol. 14, no. 4, pp. 1344-1355. https://doi.org/10.1109/TCDS.2020.3008574","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:HAL:hal-03992639v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03992639","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":"IEEE Transactions on Cognitive and Developmental Systems, 2022, 14 (4), pp.1344-1355. ⟨10.1109/TCDS.2020.3008574⟩","raw_type":"Journal articles"},{"id":"pmh:oai:pure.ed.ac.uk:publications/34f83e43-1eff-4d3f-ad77-0844203728fb","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/34f83e43-1eff-4d3f-ad77-0844203728fb","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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 M 2022, 'Behavioral Repertoire via Generative Adversarial Policy Networks', IEEE Transactions on Cognitive and Developmental Systems, vol. 14, no. 4, pp. 1344-1355. https://doi.org/10.1109/TCDS.2020.3008574","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/34f83e43-1eff-4d3f-ad77-0844203728fb","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Jegorova, M, Doncieux, S & Hospedales, T M 2022, 'Behavioral Repertoire via Generative Adversarial Policy Networks', IEEE Transactions on Cognitive and Developmental Systems, vol. 14, no. 4, pp. 1344-1355. https://doi.org/10.1109/TCDS.2020.3008574","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2838024195","display_name":"UK Robotics and Artificial Intelligence Hub for Offshore Energy Asset Integrity Management","funder_award_id":"EP/R026173/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"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":49,"referenced_works":["https://openalex.org/W1510052597","https://openalex.org/W1738827650","https://openalex.org/W1929309940","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/W2741134157","https://openalex.org/W2772778096","https://openalex.org/W2778749116","https://openalex.org/W2907904605","https://openalex.org/W2962687375","https://openalex.org/W2962837436","https://openalex.org/W2963169977","https://openalex.org/W2963226019","https://openalex.org/W2963277051","https://openalex.org/W2963373786","https://openalex.org/W2963438456","https://openalex.org/W2963684088","https://openalex.org/W2963864421","https://openalex.org/W2964157221","https://openalex.org/W2978280891","https://openalex.org/W4240805545","https://openalex.org/W4295521014","https://openalex.org/W4298289240","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/W6718140377","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/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4288282832","https://openalex.org/W2956331735","https://openalex.org/W4380551139","https://openalex.org/W2963244934","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W4238433571"],"abstract_inverted_index":{"Learning":[0],"algorithms":[1],"are":[2],"enabling":[3],"robots":[4],"to":[5,36,43,60,134,206],"solve":[6],"increasingly":[7],"challenging":[8],"real-world":[9],"tasks.":[10],"These":[11],"approaches":[12],"often":[13,210],"rely":[14],"on":[15],"demonstrations":[16],"and":[17,45,129],"reproduce":[18],"the":[19,25,38,78,170,215],"behavior":[20],"shown.":[21],"Unexpected":[22],"changes":[23],"in":[24,28,49,169,214],"environment":[26],"or":[27,112,220],"robot":[29,75,143,205],"morphology":[30],"may":[31],"require":[32],"using":[33],"different":[34],"behaviors":[35,67,147,189],"achieve":[37],"same":[39],"effect,":[40],"for":[41,68,120,154],"instance,":[42],"reach":[44],"grasp":[46],"an":[47,124,163,191],"object":[48],"changing":[50],"clutter.":[51],"An":[52],"emerging":[53],"paradigm":[54],"addressing":[55],"this":[56,89,97,160,182],"robustness":[57],"issue":[58],"is":[59],"learn":[61],"a":[62,69,74,85,93,101,109,113,142,155,185,203],"diverse":[63],"set":[64],"of":[65,96,127,165,172,188,199,217],"successful":[66],"given":[70],"task,":[71],"from":[72],"which":[73],"can":[76,144],"select":[77],"most":[79],"suitable":[80],"policy":[81,140],"when":[82,211],"faced":[83],"with":[84,162],"new":[86,156],"environment.":[87],"In":[88],"article,":[90],"we":[91],"explore":[92],"novel":[94,131,146],"realization":[95],"vision":[98],"by":[99],"learning":[100,108],"generative":[102,118,139],"model":[103,119],"over":[104],"policies.":[105],"Rather":[106],"than":[107,190],"single":[110],"policy,":[111],"small":[114],"fixed":[115],"repertoire,":[116],"our":[117,138],"policies":[121,128],"compactly":[122],"encodes":[123],"unbounded":[125],"number":[126],"allows":[130],"controller":[132],"variants":[133],"be":[135],"sampled.":[136],"Leveraging":[137],"network,":[141],"sample":[145],"until":[148],"it":[149],"finds":[150],"one":[151],"that":[152,181],"works":[153],"scenario.":[157],"We":[158,179],"demonstrate":[159],"idea":[161],"application":[164],"robust":[166],"ball":[167,212],"throwing":[168,213],"presence":[171,216],"obstacles,":[173],"as":[174,176],"well":[175],"joint-damage-robust":[177],"throwing.":[178],"show":[180],"approach":[183],"achieves":[184],"greater":[186],"diversity":[187],"existing":[192],"evolutionary":[193],"approach,":[194],"while":[195],"maintaining":[196],"good":[197],"efficacy":[198],"sampled":[200],"behaviors,":[201],"allowing":[202],"Baxter":[204],"hit":[207],"targets":[208],"more":[209],"varying":[218],"obstacles":[219],"joint":[221],"impediments.":[222]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}