{"id":"https://openalex.org/W2962596559","doi":"https://doi.org/10.18653/v1/w19-5912","title":"Collaborative Multi-Agent Dialogue Model Training Via Reinforcement Learning","display_name":"Collaborative Multi-Agent Dialogue Model Training Via Reinforcement Learning","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2962596559","doi":"https://doi.org/10.18653/v1/w19-5912","mag":"2962596559"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-5912","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5912","pdf_url":"https://www.aclweb.org/anthology/W19-5912.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 20th Annual SIGdial Meeting on Discourse and Dialogue","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W19-5912.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014990977","display_name":"Alexandros Papangelis","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156496","display_name":"Uber AI (United States)","ror":null,"country_code":"US","type":null,"lineage":["https://openalex.org/I4210156496"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexandros Papangelis","raw_affiliation_strings":["Francisco, California","Uber AI (United States), San Francisco, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Francisco, California","institution_ids":[]},{"raw_affiliation_string":"Uber AI (United States), San Francisco, United States","institution_ids":["https://openalex.org/I4210156496"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029052900","display_name":"Yi\u2010Chia Wang","orcid":"https://orcid.org/0000-0001-8021-5180"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi-Chia Wang","raw_affiliation_strings":["Francisco, California","University of Illinois at Chicago, Chicago, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Francisco, California","institution_ids":[]},{"raw_affiliation_string":"University of Illinois at Chicago, Chicago, United States","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028406899","display_name":"Piero Molino","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156496","display_name":"Uber AI (United States)","ror":null,"country_code":"US","type":null,"lineage":["https://openalex.org/I4210156496"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Piero Molino","raw_affiliation_strings":["Francisco, California","Uber AI (United States), San Francisco, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Francisco, California","institution_ids":[]},{"raw_affiliation_string":"Uber AI (United States), San Francisco, United States","institution_ids":["https://openalex.org/I4210156496"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087941479","display_name":"G\u00f6khan T\u00fcr","orcid":"https://orcid.org/0009-0008-7740-2557"},"institutions":[{"id":"https://openalex.org/I4210156496","display_name":"Uber AI (United States)","ror":null,"country_code":"US","type":null,"lineage":["https://openalex.org/I4210156496"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gokhan Tur","raw_affiliation_strings":["Uber AI (United States), San Francisco, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Uber AI (United States), San Francisco, United States","institution_ids":["https://openalex.org/I4210156496"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"92","last_page":"102"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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":0.7756609916687012},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5938183665275574},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.5908015370368958},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.5352473855018616},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.516537606716156},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3765479326248169},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32563090324401855}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7756609916687012},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5938183665275574},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.5908015370368958},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.5352473855018616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.516537606716156},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3765479326248169},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32563090324401855}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/w19-5912","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5912","pdf_url":"https://www.aclweb.org/anthology/W19-5912.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 20th Annual SIGdial Meeting on Discourse and Dialogue","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1907.05507","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.05507","pdf_url":"https://arxiv.org/pdf/1907.05507","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"},{"id":"mag:2962596559","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1907.05507.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1907.05507","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1907.05507","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/w19-5912","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5912","pdf_url":"https://www.aclweb.org/anthology/W19-5912.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 20th Annual SIGdial Meeting on Discourse and Dialogue","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4300000071525574,"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/W2962596559.pdf","grobid_xml":"https://content.openalex.org/works/W2962596559.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W361876","https://openalex.org/W311892248","https://openalex.org/W648947103","https://openalex.org/W1552182777","https://openalex.org/W1645937837","https://openalex.org/W1763968285","https://openalex.org/W1835254890","https://openalex.org/W1940872118","https://openalex.org/W1948566616","https://openalex.org/W1975244201","https://openalex.org/W1980340273","https://openalex.org/W1987326241","https://openalex.org/W2001050921","https://openalex.org/W2004637830","https://openalex.org/W2050523636","https://openalex.org/W2062175565","https://openalex.org/W2094472029","https://openalex.org/W2101105183","https://openalex.org/W2106347453","https://openalex.org/W2108239140","https://openalex.org/W2130942839","https://openalex.org/W2137871902","https://openalex.org/W2152342063","https://openalex.org/W2163068732","https://openalex.org/W2251058040","https://openalex.org/W2467173223","https://openalex.org/W2473329891","https://openalex.org/W2534381863","https://openalex.org/W2592808142","https://openalex.org/W2594726847","https://openalex.org/W2806600904","https://openalex.org/W2810840719","https://openalex.org/W2889193023","https://openalex.org/W2954579883","https://openalex.org/W2962682659","https://openalex.org/W2962775474","https://openalex.org/W2962852262","https://openalex.org/W2962883855","https://openalex.org/W2962938168","https://openalex.org/W2963043030","https://openalex.org/W2963433587","https://openalex.org/W2963546833","https://openalex.org/W2963797754","https://openalex.org/W2963963856","https://openalex.org/W2963974889","https://openalex.org/W2964044380","https://openalex.org/W2964308564","https://openalex.org/W2964331270"],"related_works":["https://openalex.org/W2979372603","https://openalex.org/W2943556788","https://openalex.org/W2237185708","https://openalex.org/W1973111422","https://openalex.org/W3013348603","https://openalex.org/W2976650111","https://openalex.org/W2988505930","https://openalex.org/W3098297242","https://openalex.org/W3034977961","https://openalex.org/W3037124050","https://openalex.org/W3190156919","https://openalex.org/W3037793033","https://openalex.org/W3125861392","https://openalex.org/W2963677857","https://openalex.org/W2988210831","https://openalex.org/W2949181853","https://openalex.org/W2894179095","https://openalex.org/W2134281179","https://openalex.org/W2980784261","https://openalex.org/W2006303459"],"abstract_inverted_index":{"We":[0,41],"present":[1],"the":[2,37,43,96,109],"first":[3],"complete":[4],"attempt":[5],"at":[6],"concurrently":[7],"training":[8],"conversational":[9],"agents":[10,38,111],"that":[11,108],"communicate":[12],"only":[13,67],"via":[14,69],"self-generated":[15],"language.":[16],"Using":[17],"DSTC2":[18],"as":[19,45],"seed":[20],"data,":[21],"we":[22,106],"trained":[23],"natural":[24,70],"language":[25,71],"understanding":[26],"(NLU)":[27],"and":[28,35,61,65,94,101],"generation":[29],"(NLG)":[30],"networks":[31],"for":[32],"each":[33,51],"agent":[34,52],"let":[36],"interact":[39,68],"online.":[40],"model":[42],"interaction":[44],"a":[46,55],"stochastic":[47],"collaborative":[48],"game":[49],"where":[50],"(player)":[53],"has":[54],"role":[56],"(\"assistant\",":[57],"\"tourist\",":[58],"\"eater\",":[59],"etc.)":[60],"their":[62],"own":[63,92],"objectives,":[64],"can":[66],"they":[72],"generate.":[73],"Each":[74],"agent,":[75],"therefore,":[76],"needs":[77],"to":[78,80],"learn":[79],"operate":[81],"optimally":[82],"in":[83],"an":[84],"environment":[85],"with":[86],"multiple":[87],"sources":[88],"of":[89],"uncertainty":[90],"(its":[91],"NLU":[93],"NLG,":[95],"other":[97],"agent's":[98],"NLU,":[99],"Policy,":[100],"NLG).":[102],"In":[103],"our":[104],"evaluation,":[105],"show":[107],"stochastic-game":[110],"outperform":[112],"deep":[113],"learning":[114],"based":[115],"supervised":[116],"baselines.":[117]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}