{"id":"https://openalex.org/W2987421469","doi":"https://doi.org/10.18653/v1/d19-6409","title":"Seeded self-play for language learning","display_name":"Seeded self-play for language learning","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2987421469","doi":"https://doi.org/10.18653/v1/d19-6409","mag":"2987421469"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d19-6409","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-6409","pdf_url":"https://www.aclweb.org/anthology/D19-6409.pdf","source":null,"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 Beyond Vision and LANguage: inTEgrating Real-world kNowledge (LANTERN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D19-6409.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101761266","display_name":"Abhinav Gupta","orcid":"https://orcid.org/0000-0002-3646-2421"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Abhinav Gupta","raw_affiliation_strings":["Facebook AI Research","Facebook AI Research MILA"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook AI Research MILA","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004295653","display_name":"Ryan Lowe","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ryan Lowe","raw_affiliation_strings":["Facebook AI Research MILA","Facebook AI Research"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research MILA","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059094093","display_name":"Jakob Foerster","orcid":"https://orcid.org/0000-0001-9688-2498"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Jakob Foerster","raw_affiliation_strings":["Facebook AI Research MILA","Facebook AI Research"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research MILA","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016956470","display_name":"Douwe Kiela","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Douwe Kiela","raw_affiliation_strings":["Facebook AI Research","Facebook AI Research MILA"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook AI Research MILA","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080591144","display_name":"Jo\u00eblle Pineau","orcid":"https://orcid.org/0000-0003-0747-7250"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Joelle Pineau","raw_affiliation_strings":["Facebook AI Research","Facebook AI Research MILA"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook AI Research MILA","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101761266"],"corresponding_institution_ids":["https://openalex.org/I2252078561"],"apc_list":null,"apc_paid":null,"fwci":1.2601,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.85487563,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"62","last_page":"66"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9966999888420105,"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/T12031","display_name":"Speech and dialogue systems","score":0.9951000213623047,"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":0.7919057607650757},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6548705697059631},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5868704319000244},{"id":"https://openalex.org/keywords/language-acquisition","display_name":"Language acquisition","score":0.5863777995109558},{"id":"https://openalex.org/keywords/human-language","display_name":"Human language","score":0.5460262298583984},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.5240804553031921},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.47525736689567566},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.405746728181839},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09987038373947144},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08116933703422546}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7919057607650757},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6548705697059631},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5868704319000244},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.5863777995109558},{"id":"https://openalex.org/C2993724205","wikidata":"https://www.wikidata.org/wiki/Q315","display_name":"Human language","level":2,"score":0.5460262298583984},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5240804553031921},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.47525736689567566},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.405746728181839},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09987038373947144},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08116933703422546},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","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/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d19-6409","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-6409","pdf_url":"https://www.aclweb.org/anthology/D19-6409.pdf","source":null,"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 Beyond Vision and LANguage: inTEgrating Real-world kNowledge (LANTERN)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d19-6409","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-6409","pdf_url":"https://www.aclweb.org/anthology/D19-6409.pdf","source":null,"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 Beyond Vision and LANguage: inTEgrating Real-world kNowledge (LANTERN)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2987421469.pdf","grobid_xml":"https://content.openalex.org/works/W2987421469.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2142947219","https://openalex.org/W2164287115","https://openalex.org/W2395575420","https://openalex.org/W2531240212","https://openalex.org/W2547875792","https://openalex.org/W2548228487","https://openalex.org/W2602275733","https://openalex.org/W2623431351","https://openalex.org/W2766184602","https://openalex.org/W2805465728","https://openalex.org/W2835434549","https://openalex.org/W2897513296","https://openalex.org/W2912699886","https://openalex.org/W2914000177","https://openalex.org/W2950472486","https://openalex.org/W2952165242","https://openalex.org/W2963000099","https://openalex.org/W2963155490","https://openalex.org/W2963407617","https://openalex.org/W2963455109","https://openalex.org/W2963881016","https://openalex.org/W2964121744","https://openalex.org/W2964289358","https://openalex.org/W2969219365","https://openalex.org/W3100385063","https://openalex.org/W4251395411","https://openalex.org/W4295846245","https://openalex.org/W4297795114","https://openalex.org/W4299802797","https://openalex.org/W6631190155","https://openalex.org/W6759273029","https://openalex.org/W7070443497"],"related_works":["https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2556294339","https://openalex.org/W1513148995","https://openalex.org/W2051425333"],"abstract_inverted_index":{"How":[0],"can":[1,154,172],"we":[2,95,107,118],"teach":[3],"artificial":[4],"agents":[5,179,205],"to":[6,11,29,33,58,80,97,110,112,125,145,148,215],"use":[7,30],"human":[8,25,31,82,90,163,189],"language":[9,32,60,190,219],"flexibly":[10],"solve":[12,34],"problems":[13],"in":[14,23,61,102,116,123,157,220],"real-world":[15],"environments?":[16],"We":[17,192],"have":[18],"an":[19,41,69,105],"example":[20],"of":[21,88,129,151,187],"this":[22,62,93,194],"nature:":[24],"babies":[26],"eventually":[27],"learn":[28,59,81,98,216],"problems,":[35],"and":[36,209],"they":[37],"are":[38,54],"taught":[39],"with":[40,71,127,133,180,207],"adult":[42],"humanin-the-loop.":[43],"Unfortunately,":[44],"current":[45],"machine":[46],"learning":[47,75,182],"methods":[48],"(e.g.":[49],"from":[50],"deep":[51],"reinforcement":[52],"learning)":[53],"too":[55],"data":[56],"inefficient":[57],"way.":[63],"An":[64],"outstanding":[65],"goal":[66],"is":[67,143,168],"finding":[68],"algorithm":[70],"a":[72,100,120,184,217,221],"suitable":[73],"'language":[74],"prior'":[76],"that":[77,169,204],"allows":[78],"it":[79,153],"language,":[83],"while":[84],"minimizing":[85],"the":[86,140],"number":[87],"on-policy":[89,213],"interactions.":[91],"In":[92],"paper,":[94],"propose":[96],"such":[99,170],"prior":[101],"simulation":[103,124],"using":[104],"approach":[106],"call,":[108],"Learning":[109],"Learn":[111],"Communicate":[113],"(L2C).":[114],"Specifically,":[115],"L2C":[117,208],"train":[119],"meta-learning":[121,141],"agent":[122,142],"interact":[126],"populations":[128,161,171],"pre-trained":[130],"agents,":[131,152],"each":[132,149],"their":[134],"own":[135],"distinct":[136],"communication":[137],"protocol.":[138],"Once":[139],"able":[144],"quickly":[146],"adapt":[147],"population":[150],"be":[155,173],"deployed":[156],"new":[158],"populations,":[159],"including":[160],"speaking":[162],"language.":[164],"Our":[165,200],"key":[166],"insight":[167],"obtained":[174],"via":[175],"self-play,":[176],"after":[177],"pre-training":[178],"imitation":[181],"on":[183],"small":[185],"amount":[186],"off-policy":[188],"data.":[191],"call":[193],"latter":[195],"technique":[196],"Seeded":[197],"Self-Play":[198],"(S2P).":[199],"preliminary":[201],"experiments":[202],"show":[203],"trained":[206],"S2P":[210],"need":[211],"fewer":[212],"samples":[214],"compositional":[218],"Lewis":[222],"signaling":[223],"game.":[224]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}