{"id":"https://openalex.org/W4414360545","doi":"https://doi.org/10.24963/ijcai.2025/19","title":"Combining Deep Reinforcement Learning and Search with Generative Models for Game-Theoretic Opponent Modeling","display_name":"Combining Deep Reinforcement Learning and Search with Generative Models for Game-Theoretic Opponent Modeling","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360545","doi":"https://doi.org/10.24963/ijcai.2025/19"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/19","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/19","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101674351","display_name":"Zun Li","orcid":"https://orcid.org/0000-0003-1748-0883"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Zun Li","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049659586","display_name":"Marc Lanctot","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Marc Lanctot","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013841168","display_name":"Kevin R. McKee","orcid":"https://orcid.org/0000-0002-4412-1686"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Kevin R. McKee","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051039278","display_name":"Luke Marris","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Luke Marris","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112947561","display_name":"Ian Gemp","orcid":"https://orcid.org/0000-0002-7774-3246"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Ian Gemp","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043984392","display_name":"Daniel Hennes","orcid":"https://orcid.org/0000-0002-3646-5286"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Daniel Hennes","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058922471","display_name":"Paul M\u00fcller","orcid":"https://orcid.org/0000-0002-5734-3130"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Paul Muller","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105978897","display_name":"Kate Larson","orcid":"https://orcid.org/0000-0002-5455-9657"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["CA","GB","US"],"is_corresponding":false,"raw_author_name":"Kate Larson","raw_affiliation_strings":["Google DeepMind","University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]},{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062949033","display_name":"Yoram Bachrach","orcid":"https://orcid.org/0000-0002-4382-7636"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Yoram Bachrach","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002102744","display_name":"Michael P. Wellman","orcid":"https://orcid.org/0000-0002-1691-6844"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael P. Wellman","raw_affiliation_strings":["University of Michigan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"161","last_page":"169"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8070999979972839,"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":0.8070999979972839,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6751000285148621},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4740999937057495},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.47049999237060547},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.45739999413490295},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4410000145435333},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4169999957084656},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4092000126838684},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.38940000534057617},{"id":"https://openalex.org/keywords/best-response","display_name":"Best response","score":0.36649999022483826}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7117999792098999},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6751000285148621},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.644599974155426},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.538100004196167},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4740999937057495},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.47049999237060547},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.45739999413490295},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4410000145435333},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4169999957084656},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4092000126838684},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.38940000534057617},{"id":"https://openalex.org/C32407928","wikidata":"https://www.wikidata.org/wiki/Q2733833","display_name":"Best response","level":3,"score":0.36649999022483826},{"id":"https://openalex.org/C199776023","wikidata":"https://www.wikidata.org/wiki/Q202875","display_name":"Negotiation","level":2,"score":0.3617999851703644},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.359499990940094},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.3564999997615814},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.34700000286102295},{"id":"https://openalex.org/C123676819","wikidata":"https://www.wikidata.org/wiki/Q1074338","display_name":"Perfect information","level":2,"score":0.33250001072883606},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C145071142","wikidata":"https://www.wikidata.org/wiki/Q1411116","display_name":"Fictitious play","level":3,"score":0.27900001406669617},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.2711000144481659}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/19","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/19","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Opponent":[0],"modeling":[1,68,216],"methods":[2],"typically":[3,28],"involve":[4],"two":[5],"crucial":[6],"steps:":[7],"building":[8],"a":[9,22,37,59,81,92,119,207],"belief":[10],"distribution":[11],"over":[12],"opponents'":[13],"strategies,":[14],"and":[15,39,61,112,116,151,188,224,232,241],"exploiting":[16],"this":[17,55,126],"opponent":[18,67,145,167,186],"model":[19,96,146,187],"by":[20],"playing":[21],"best":[23,43,82],"response.":[24],"However,":[25],"existing":[26],"approaches":[27],"require":[29],"domain-specific":[30],"heurstics":[31],"to":[32,47,107,138,163],"come":[33],"up":[34,165],"with":[35,91,202,214,246],"such":[36],"model,":[38],"algorithms":[40],"for":[41,66],"approximating":[42],"responses":[44],"are":[45,175],"hard":[46],"scale":[48],"in":[49,118,205],"large,":[50],"imperfect":[51,109],"information":[52,110],"domains.":[53],"In":[54],"work,":[56],"we":[57,170],"introduce":[58],"scalable":[60],"generic":[62],"multiagent":[63,122],"training":[64,222],"regime":[65],"using":[69,156],"deep":[70,94],"game-theoretic":[71,149],"reinforcement":[72],"learning.":[73],"We":[74,124,154,194],"first":[75],"propose":[76,155],"Generative":[77],"Best":[78],"Respoonse":[79],"(GenBR),":[80],"response":[83],"algorithm":[84],"based":[85,159],"on":[86,160],"Monte-Carlo":[87],"Tree":[88],"Search":[89,213],"(MCTS)":[90],"learned":[93],"generative":[95,215],"that":[97,174,236],"samples":[98],"world":[99],"states":[100],"during":[101,192,220],"planning.":[102],"This":[103],"new":[104,127],"method":[105,128],"scales":[106],"large":[108],"domains":[111],"can":[113,233],"be":[114],"plug":[115],"play":[117],"variety":[120],"of":[121,132,142,209],"algorithms.":[123],"use":[125],"under":[129],"the":[130,140,177],"framework":[131],"Policy":[133],"Space":[134],"Response":[135],"Oracles":[136],"(PSRO),":[137],"automate":[139],"generation":[141],"an":[143,166,184],"offline":[144],"via":[147],"iterative":[148],"reasoning":[150],"population-based":[152],"training.":[153],"solution":[157],"concepts":[158],"bargaining":[161,211,243],"theory":[162],"build":[164],"mixture,":[168],"which":[169],"find":[171],"identifying":[172],"profiles":[173],"near":[176],"Pareto":[178],"frontier.":[179],"Then":[180],"GenBR":[181],"keeps":[182],"updating":[183],"online":[185,228],"reacts":[189],"against":[190],"it":[191],"gameplay.":[193],"conduct":[195],"behavioral":[196],"studies":[197],"where":[198],"human":[199],"participants":[200],"negotiate":[201],"our":[203],"agents":[204,235],"Deal-or-No-Deal,":[206],"class":[208],"bilateral":[210],"games.":[212],"finds":[217],"stronger":[218],"policies":[219],"both":[221],"time":[223],"test":[225],"time,":[226],"enables":[227],"Bayesian":[229],"co-player":[230],"prediction,":[231],"produce":[234],"achieve":[237],"comparable":[238],"social":[239],"welfare":[240],"Nash":[242],"score":[244],"negotiating":[245],"humans":[247,249],"as":[248],"trading":[250],"among":[251],"themselves.":[252]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}