{"id":"https://openalex.org/W4281553483","doi":"https://doi.org/10.24963/ijcai.2022/484","title":"Approximate Exploitability: Learning a Best Response","display_name":"Approximate Exploitability: Learning a Best Response","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4281553483","doi":"https://doi.org/10.24963/ijcai.2022/484"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/484","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/484","pdf_url":"https://www.ijcai.org/proceedings/2022/0484.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2022/0484.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090501025","display_name":"Finbarr Timbers","orcid":"https://orcid.org/0000-0001-9047-9542"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA","GB"],"is_corresponding":true,"raw_author_name":"Finbarr Timbers","raw_affiliation_strings":["DeepMind","University of Alberta"],"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032717855","display_name":"Nolan Bard","orcid":"https://orcid.org/0009-0007-0048-6636"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]},{"id":"https://openalex.org/I4210090411","display_name":"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"],"is_corresponding":false,"raw_author_name":"Nolan Bard","raw_affiliation_strings":["DeepMind","University of Alberta"],"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081026564","display_name":"Edward Lockhart","orcid":"https://orcid.org/0000-0001-8753-0765"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]},{"id":"https://openalex.org/I4210090411","display_name":"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"],"is_corresponding":false,"raw_author_name":"Edward Lockhart","raw_affiliation_strings":["DeepMind","University of Alberta"],"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049659586","display_name":"Marc Lanctot","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]},{"id":"https://openalex.org/I4210090411","display_name":"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"],"is_corresponding":false,"raw_author_name":"Marc Lanctot","raw_affiliation_strings":["Deepmind","University of Alberta"],"affiliations":[{"raw_affiliation_string":"Deepmind","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000836428","display_name":"Martin Schmid","orcid":"https://orcid.org/0000-0002-0440-9802"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA","GB"],"is_corresponding":false,"raw_author_name":"Martin Schmid","raw_affiliation_strings":["DeepMind","University of Alberta"],"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018555885","display_name":"Neil Burch","orcid":"https://orcid.org/0000-0002-4596-3690"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA","GB"],"is_corresponding":false,"raw_author_name":"Neil Burch","raw_affiliation_strings":["DeepMind","University of Alberta"],"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080518618","display_name":"Julian Schrittwieser","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA","GB"],"is_corresponding":false,"raw_author_name":"Julian Schrittwieser","raw_affiliation_strings":["DeepMind","University of Alberta"],"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083969139","display_name":"Thomas Hubert","orcid":"https://orcid.org/0000-0003-2209-3933"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]},{"id":"https://openalex.org/I4210090411","display_name":"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"],"is_corresponding":false,"raw_author_name":"Thomas Hubert","raw_affiliation_strings":["DeepMind","University of Alberta"],"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081163135","display_name":"Michael Bowling","orcid":"https://orcid.org/0000-0003-2960-8418"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA","GB"],"is_corresponding":false,"raw_author_name":"Michael Bowling","raw_affiliation_strings":["DeepMind","University of Alberta"],"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"University of Alberta","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5090501025"],"corresponding_institution_ids":["https://openalex.org/I154425047","https://openalex.org/I4210090411"],"apc_list":null,"apc_paid":null,"fwci":1.1434,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.79551821,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3487","last_page":"3493"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9955999851226807,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9950000047683716,"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/adversarial-system","display_name":"Adversarial system","score":0.8272908926010132},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.818101167678833},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7833564877510071},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7130030393600464},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7116047143936157},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6084777116775513},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5783565640449524},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5683895945549011},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5655616521835327},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.45781436562538147},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4336732029914856},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32827135920524597},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12225326895713806}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8272908926010132},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.818101167678833},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7833564877510071},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7130030393600464},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7116047143936157},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6084777116775513},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5783565640449524},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5683895945549011},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5655616521835327},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.45781436562538147},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4336732029914856},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32827135920524597},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12225326895713806},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2022/484","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/484","pdf_url":"https://www.ijcai.org/proceedings/2022/0484.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/484","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/484","pdf_url":"https://www.ijcai.org/proceedings/2022/0484.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4281553483.pdf","grobid_xml":"https://content.openalex.org/works/W4281553483.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W193176855","https://openalex.org/W969015820","https://openalex.org/W1512315140","https://openalex.org/W1636614024","https://openalex.org/W2103315867","https://openalex.org/W2113228754","https://openalex.org/W2145339207","https://openalex.org/W2162651021","https://openalex.org/W2187559597","https://openalex.org/W2462906003","https://openalex.org/W2574978968","https://openalex.org/W2594844947","https://openalex.org/W2736899637","https://openalex.org/W2773381986","https://openalex.org/W2804505179","https://openalex.org/W2806053164","https://openalex.org/W2896973754","https://openalex.org/W2902907165","https://openalex.org/W2904815624","https://openalex.org/W2951301202","https://openalex.org/W2964019952","https://openalex.org/W2969287672","https://openalex.org/W2996343955","https://openalex.org/W3080474688","https://openalex.org/W3103780890","https://openalex.org/W3172082158","https://openalex.org/W4301480774"],"related_works":["https://openalex.org/W2950183588","https://openalex.org/W3080754722","https://openalex.org/W4383221314","https://openalex.org/W3093978547","https://openalex.org/W2953536436","https://openalex.org/W3203790781","https://openalex.org/W4313346231","https://openalex.org/W2738001131","https://openalex.org/W4285785480","https://openalex.org/W2997056298"],"abstract_inverted_index":{"Researchers":[0],"have":[1],"shown":[2],"that":[3],"neural":[4],"networks":[5],"are":[6,74],"vulnerable":[7],"to":[8,22,46,49,58,91],"adversarial":[9],"examples":[10],"and":[11,71],"subtle":[12],"environment":[13],"changes.":[14],"The":[15],"resulting":[16],"errors":[17],"can":[18],"look":[19],"like":[20],"blunders":[21],"humans,":[23],"eroding":[24],"trust":[25],"in":[26,101],"these":[27],"agents.":[28,112],"In":[29],"prior":[30],"games":[31,103],"research,":[32],"agent":[33],"evaluation":[34,43],"often":[35],"focused":[36],"on":[37],"the":[38,99],"in-practice":[39],"game":[40],"outcomes.":[41,51],"Such":[42],"typically":[44],"fails":[45],"evaluate":[47],"robustness":[48],"worst-case":[50,61,95],"Computer":[52],"poker":[53],"research":[54],"has":[55],"examined":[56],"how":[57],"assess":[59],"such":[60],"performance.":[62,96],"Unfortunately,":[63],"exact":[64],"computation":[65],"is":[66,115],"infeasible":[67],"with":[68],"larger":[69],"domains,":[70],"existing":[72],"approximations":[73],"poker-specific.":[75],"We":[76,97],"introduce":[77],"ISMCTS-BR,":[78],"a":[79,88,105],"scalable":[80],"search-based":[81],"deep":[82],"reinforcement":[83],"learning":[84,87],"algorithm":[85],"for":[86],"best":[89],"response":[90],"an":[92],"agent,":[93],"approximating":[94],"demonstrate":[98],"technique":[100],"several":[102,110],"against":[104],"variety":[106],"of":[107],"agents,":[108],"including":[109],"AlphaZero-based":[111],"Supplementary":[113],"material":[114],"available":[116],"at":[117],"https://arxiv.org/abs/2004.09677.":[118]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}