{"id":"https://openalex.org/W2965394063","doi":"https://doi.org/10.24963/ijcai.2019/176","title":"DeltaDou: Expert-level Doudizhu AI through Self-play","display_name":"DeltaDou: Expert-level Doudizhu AI through Self-play","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2965394063","doi":"https://doi.org/10.24963/ijcai.2019/176","mag":"2965394063"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/176","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/176","pdf_url":"https://www.ijcai.org/proceedings/2019/0176.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0176.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102010526","display_name":"Qiqi Jiang","orcid":"https://orcid.org/0000-0002-1876-715X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Qiqi Jiang","raw_affiliation_strings":["SweetCode Inc, Beijing"],"affiliations":[{"raw_affiliation_string":"SweetCode Inc, Beijing","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036939387","display_name":"Kuangzheng Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kuangzheng Li","raw_affiliation_strings":["SweetCode Inc, Beijing"],"affiliations":[{"raw_affiliation_string":"SweetCode Inc, Beijing","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030857451","display_name":"Boyao Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boyao Du","raw_affiliation_strings":["SweetCode Inc, Beijing"],"affiliations":[{"raw_affiliation_string":"SweetCode Inc, Beijing","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353545","display_name":"Hao Chen","orcid":"https://orcid.org/0000-0002-3958-3456"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Chen","raw_affiliation_strings":["SweetCode Inc, Beijing"],"affiliations":[{"raw_affiliation_string":"SweetCode Inc, Beijing","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012430615","display_name":"Hai Fang","orcid":"https://orcid.org/0000-0003-1409-3917"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hai Fang","raw_affiliation_strings":["SweetCode Inc, Beijing"],"affiliations":[{"raw_affiliation_string":"SweetCode Inc, Beijing","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102010526"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.9404,"has_fulltext":true,"cited_by_count":46,"citation_normalized_percentile":{"value":0.93074885,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1265","last_page":"1271"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","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/T11574","display_name":"Artificial Intelligence in Games","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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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/T11197","display_name":"Digital Games and Media","score":0.9781000018119812,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/perfect-information","display_name":"Perfect information","score":0.7883950471878052},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7868355512619019},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.736025333404541},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.6111295223236084},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5939372777938843},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5529569983482361},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5150070190429688},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4636707305908203},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38447105884552},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.11946097016334534},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09674277901649475}],"concepts":[{"id":"https://openalex.org/C123676819","wikidata":"https://www.wikidata.org/wiki/Q1074338","display_name":"Perfect information","level":2,"score":0.7883950471878052},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7868355512619019},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.736025333404541},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.6111295223236084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5939372777938843},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5529569983482361},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5150070190429688},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4636707305908203},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38447105884552},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.11946097016334534},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09674277901649475},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2019/176","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/176","pdf_url":"https://www.ijcai.org/proceedings/2019/0176.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/176","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/176","pdf_url":"https://www.ijcai.org/proceedings/2019/0176.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2965394063.pdf","grobid_xml":"https://content.openalex.org/works/W2965394063.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W16011919","https://openalex.org/W1532584713","https://openalex.org/W1540121360","https://openalex.org/W1646839507","https://openalex.org/W1995987707","https://openalex.org/W2003861737","https://openalex.org/W2113228754","https://openalex.org/W2144274908","https://openalex.org/W2257979135","https://openalex.org/W2291772168","https://openalex.org/W2407621529","https://openalex.org/W2574978968","https://openalex.org/W2773381986","https://openalex.org/W2902907165","https://openalex.org/W2964164283","https://openalex.org/W6651007940","https://openalex.org/W6697063336","https://openalex.org/W6746060310"],"related_works":["https://openalex.org/W2360321812","https://openalex.org/W2395295193","https://openalex.org/W3122057932","https://openalex.org/W2113798763","https://openalex.org/W3088364074","https://openalex.org/W2004230228","https://openalex.org/W2610227658","https://openalex.org/W2145796981","https://openalex.org/W2900431508","https://openalex.org/W2050340470"],"abstract_inverted_index":{"Artificial":[0],"Intelligence":[1],"has":[2],"seen":[3],"several":[4],"breakthroughs":[5],"in":[6,90],"two-player":[7],"perfect":[8],"information":[9,16,48,94],"game.":[10,95],"Nevertheless,":[11],"Doudizhu,":[12],"a":[13,27,53,99],"three-player":[14],"imperfect":[15,93],"game,":[17],"is":[18],"still":[19],"quite":[20],"challenging.":[21],"In":[22],"this":[23,91],"paper,":[24],"we":[25],"present":[26],"Doudizhu":[28],"AI":[29],"by":[30,74],"applying":[31],"deep":[32],"reinforcement":[33],"learning":[34],"from":[35],"games":[36],"of":[37,47,50,71,87,111],"self-play.":[38],"The":[39],"algorithm":[40],"combines":[41],"an":[42],"asymmetric":[43],"MCTS":[44],"on":[45,62,68],"nodes":[46],"set":[49],"each":[51,63],"player,":[52],"policy-value":[54],"network":[55],"that":[56,80],"approximates":[57],"the":[58,85],"policy":[59],"and":[60,66,113],"value":[61],"decision":[64],"node,":[65],"inference":[67],"unobserved":[69],"hands":[70],"other":[72],"players":[73],"given":[75],"policy.":[76],"Our":[77],"results":[78],"show":[79],"self-play":[81,112],"can":[82,104],"significantly":[83],"improve":[84],"performance":[86],"our":[88,102],"agent":[89,103],"multi-agent":[92],"Even":[96],"starting":[97],"with":[98],"weak":[100],"AI,":[101],"achieve":[105],"human":[106],"expert":[107],"level":[108],"after":[109],"days":[110],"training.":[114]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}