{"id":"https://openalex.org/W2904170485","doi":"https://doi.org/10.1609/aaai.v33i01.33016104","title":"Large Scale Learning of Agent Rationality in Two-Player Zero-Sum Games","display_name":"Large Scale Learning of Agent Rationality in Two-Player Zero-Sum Games","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2904170485","doi":"https://doi.org/10.1609/aaai.v33i01.33016104","mag":"2904170485"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33016104","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33016104","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4567/4445","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4567/4445","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030456881","display_name":"Chun Kai Ling","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chun Kai Ling","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061127138","display_name":"Fei Fang","orcid":"https://orcid.org/0000-0003-2256-8329"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fei Fang","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075035644","display_name":"J. Zico Kolter","orcid":"https://orcid.org/0000-0002-8106-5759"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. Zico Kolter","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":21.4729,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.99239905,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"33","issue":"01","first_page":"6104","last_page":"6111"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11674","display_name":"Sports Analytics and Performance","score":0.974399983882904,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11674","display_name":"Sports Analytics and Performance","score":0.974399983882904,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9596999883651733,"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":0.7214188575744629},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.6899357438087463},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5249003171920776},{"id":"https://openalex.org/keywords/rationality","display_name":"Rationality","score":0.5034927725791931},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.48253318667411804},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4642539620399475},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4258568286895752},{"id":"https://openalex.org/keywords/sequential-game","display_name":"Sequential game","score":0.4206181764602661},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.39310333132743835},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3781585395336151},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32271814346313477},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.2060212790966034},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19693779945373535}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7214188575744629},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.6899357438087463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5249003171920776},{"id":"https://openalex.org/C201717286","wikidata":"https://www.wikidata.org/wiki/Q938185","display_name":"Rationality","level":2,"score":0.5034927725791931},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.48253318667411804},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4642539620399475},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4258568286895752},{"id":"https://openalex.org/C73795354","wikidata":"https://www.wikidata.org/wiki/Q287618","display_name":"Sequential game","level":3,"score":0.4206181764602661},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.39310333132743835},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3781585395336151},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32271814346313477},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.2060212790966034},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19693779945373535},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v33i01.33016104","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33016104","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4567/4445","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/4567","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33016104","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33016104","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4567/4445","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","score":0.7099999785423279,"display_name":"No poverty"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2904170485.pdf","grobid_xml":"https://content.openalex.org/works/W2904170485.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1980392196","https://openalex.org/W2014089538","https://openalex.org/W2108111486","https://openalex.org/W2132339352","https://openalex.org/W2136427775","https://openalex.org/W2149086825","https://openalex.org/W2241435520","https://openalex.org/W2254533881","https://openalex.org/W2264897026","https://openalex.org/W2341638976","https://openalex.org/W2505728881","https://openalex.org/W2599008924","https://openalex.org/W2899771611","https://openalex.org/W2951328700","https://openalex.org/W2962756936","https://openalex.org/W3122059187","https://openalex.org/W4212898980","https://openalex.org/W4294091620","https://openalex.org/W4301496368","https://openalex.org/W6605006787","https://openalex.org/W6653623256","https://openalex.org/W6673974147","https://openalex.org/W6676357390","https://openalex.org/W6681884964","https://openalex.org/W6735270558","https://openalex.org/W6756040250"],"related_works":["https://openalex.org/W4229052146","https://openalex.org/W2071306797","https://openalex.org/W2405803446","https://openalex.org/W2374666693","https://openalex.org/W2149560990","https://openalex.org/W2911145752","https://openalex.org/W2372443802","https://openalex.org/W1993365706","https://openalex.org/W2363987469","https://openalex.org/W1517532457"],"abstract_inverted_index":{"With":[0],"the":[1,17,102,154,189],"recent":[2,33],"advances":[3],"in":[4,16,107,117],"solving":[5,166],"large,":[6,142],"zero-sum":[7,110],"extensive":[8],"form":[9],"games,":[10,111,158,175],"there":[11],"is":[12,92],"a":[13,32,36,44,48,89,122],"growing":[14],"interest":[15],"inverse":[18],"problem":[19],"of":[20,104,156,179,181,191],"inferring":[21],"underlying":[22],"game":[23,45,53,165],"parameters":[24,54],"given":[25],"only":[26],"access":[27],"to":[28,55,67,77,100,120,138,141],"agent":[29,126],"actions.":[30],"Although":[31],"work":[34],"provides":[35],"powerful":[37],"differentiable":[38],"end-to-end":[39,135],"learning":[40],"frameworks":[41],"which":[42,152],"embed":[43],"solver":[46],"within":[47],"deep-learning":[49],"framework,":[50],"allowing":[51],"unknown":[52],"be":[56],"learned":[57],"via":[58],"backpropagation,":[59],"this":[60,81],"framework":[61,90],"faces":[62],"significant":[63],"limitations":[64,86],"when":[65],"applied":[66],"boundedly":[68],"rational":[69],"human":[70,105],"agents":[71,106],"and":[72,87,124,129,132,167,199],"large":[73],"scale":[74,139],"problems,":[75],"leading":[76],"poor":[78],"practicality.":[79],"In":[80],"paper,":[82],"we":[83,112,145,176],"address":[84],"these":[85],"propose":[88,146],"that":[91],"applicable":[93],"for":[94,134,163],"more":[95],"practical":[96],"settings.":[97],"First,":[98],"seeking":[99],"learn":[101],"rationality":[103],"complex":[108],"two-player":[109],"draw":[113],"upon":[114],"well-known":[115],"ideas":[116],"decision":[118],"theory":[119],"obtain":[121],"concise":[123],"interpretable":[125],"behavior":[127],"model,":[128],"derive":[130],"solvers":[131],"gradients":[133],"learning.":[136],"Second,":[137],"up":[140],"real-world":[143,196],"scenarios,":[144],"an":[147],"efficient":[148],"first-order":[149],"primal-dual":[150],"method":[151],"exploits":[153],"structure":[155],"extensive-form":[157],"yielding":[159],"significantly":[160],"faster":[161],"computation":[162],"both":[164,195],"gradient":[168],"computation.":[169],"When":[170],"tested":[171],"on":[172,194],"randomly":[173],"generated":[174],"report":[177],"speedups":[178],"orders":[180],"magnitude":[182],"over":[183],"previous":[184],"approaches.":[185],"We":[186],"also":[187],"demonstrate":[188],"effectiveness":[190],"our":[192],"model":[193],"one-player":[197],"settings":[198],"synthetic":[200],"data.":[201]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}