{"id":"https://openalex.org/W4385764344","doi":"https://doi.org/10.24963/ijcai.2023/422","title":"BRExIt: On Opponent Modelling in Expert Iteration","display_name":"BRExIt: On Opponent Modelling in Expert Iteration","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385764344","doi":"https://doi.org/10.24963/ijcai.2023/422"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/422","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/422","pdf_url":"https://www.ijcai.org/proceedings/2023/0422.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0422.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015781911","display_name":"Daniel E. Hern\u00e1ndez","orcid":"https://orcid.org/0000-0003-2563-9129"},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]},{"id":"https://openalex.org/I52099693","display_name":"University of York","ror":"https://ror.org/04m01e293","country_code":"GB","type":"education","lineage":["https://openalex.org/I52099693"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Daniel Hernandez","raw_affiliation_strings":["Sony AI","University of York","University of York, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony AI","institution_ids":["https://openalex.org/I2800278093"]},{"raw_affiliation_string":"University of York","institution_ids":["https://openalex.org/I52099693"]},{"raw_affiliation_string":"University of York, UK","institution_ids":["https://openalex.org/I52099693"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065056119","display_name":"Hendrik Baier","orcid":"https://orcid.org/0000-0002-7211-8070"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Hendrik Baier","raw_affiliation_strings":["Eindhoven University of Technology","Eindhoven University of Technology, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology","institution_ids":["https://openalex.org/I83019370"]},{"raw_affiliation_string":"Eindhoven University of Technology, The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069752991","display_name":"Michael Kaisers","orcid":null},"institutions":[{"id":"https://openalex.org/I1341640284","display_name":"Centrum Wiskunde & Informatica","ror":"https://ror.org/00x7ekv49","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1341640284","https://openalex.org/I2800991832","https://openalex.org/I4405262988"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Michael Kaisers","raw_affiliation_strings":["Centrum Wiskunde & Informatica","Centrum Wiskunde & Informatica, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centrum Wiskunde & Informatica","institution_ids":["https://openalex.org/I1341640284"]},{"raw_affiliation_string":"Centrum Wiskunde & Informatica, The Netherlands","institution_ids":["https://openalex.org/I1341640284"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2092,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.42498236,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3795","last_page":"3802"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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/T10462","display_name":"Reinforcement Learning in Robotics","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/T11574","display_name":"Artificial Intelligence in Games","score":0.9983000159263611,"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/T11674","display_name":"Sports Analytics and Performance","score":0.9959999918937683,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7382125854492188},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7081189155578613},{"id":"https://openalex.org/keywords/brexit","display_name":"Brexit","score":0.6487893462181091},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.6203894019126892},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5699304938316345},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5181654691696167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5121195316314697},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47774308919906616},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46779829263687134},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42727115750312805},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.1497218906879425},{"id":"https://openalex.org/keywords/european-union","display_name":"European union","score":0.1178835928440094},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07631662487983704}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7382125854492188},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7081189155578613},{"id":"https://openalex.org/C2776469822","wikidata":"https://www.wikidata.org/wiki/Q7888194","display_name":"Brexit","level":3,"score":0.6487893462181091},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.6203894019126892},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5699304938316345},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5181654691696167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5121195316314697},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47774308919906616},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46779829263687134},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42727115750312805},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.1497218906879425},{"id":"https://openalex.org/C2910001868","wikidata":"https://www.wikidata.org/wiki/Q458","display_name":"European union","level":2,"score":0.1178835928440094},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07631662487983704},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C105639569","wikidata":"https://www.wikidata.org/wiki/Q582577","display_name":"Economic policy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/422","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/422","pdf_url":"https://www.ijcai.org/proceedings/2023/0422.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/422","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/422","pdf_url":"https://www.ijcai.org/proceedings/2023/0422.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second 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/W4385764344.pdf","grobid_xml":"https://content.openalex.org/works/W4385764344.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W2126316555","https://openalex.org/W2201581102","https://openalex.org/W2257979135","https://openalex.org/W2475089067","https://openalex.org/W2492104848","https://openalex.org/W2618097077","https://openalex.org/W2736601468","https://openalex.org/W2740377041","https://openalex.org/W2758442112","https://openalex.org/W2772709170","https://openalex.org/W2776777826","https://openalex.org/W2913409451","https://openalex.org/W2918318309","https://openalex.org/W2963065757","https://openalex.org/W2977093897","https://openalex.org/W2980061931","https://openalex.org/W2982316857","https://openalex.org/W2996037775","https://openalex.org/W3083310462","https://openalex.org/W3093519064","https://openalex.org/W3170943554","https://openalex.org/W3212314511","https://openalex.org/W4206439154","https://openalex.org/W4281553483","https://openalex.org/W4287018575","https://openalex.org/W4287813665","https://openalex.org/W4297789683","https://openalex.org/W4297797010","https://openalex.org/W4298857966"],"related_works":["https://openalex.org/W2979683410","https://openalex.org/W2914690430","https://openalex.org/W4240114703","https://openalex.org/W2921963337","https://openalex.org/W2560066009","https://openalex.org/W4319601116","https://openalex.org/W2559860852","https://openalex.org/W4383117548","https://openalex.org/W4386279425","https://openalex.org/W2757632492"],"abstract_inverted_index":{"Finding":[0],"a":[1,6,72,103,115],"best":[2,104],"response":[3],"policy":[4,73],"is":[5],"central":[7],"objective":[8],"in":[9,47,68,87],"game":[10],"theory":[11],"and":[12,82],"multi-agent":[13],"learning,":[14],"with":[15,71],"modern":[16],"population-based":[17],"training":[18],"approaches":[19],"employing":[20],"reinforcement":[21],"learning":[22,46,56],"algorithms":[23],"as":[24,78],"best-response":[25],"oracles":[26],"to":[27,63,96],"improve":[28,65],"play":[29],"against":[30,114],"candidate":[31],"opponents":[32],"(typically":[33],"previously":[34],"learnt":[35,93],"policies).":[36],"We":[37],"propose":[38],"Best":[39],"Response":[40],"Expert":[41,58],"Iteration":[42,59],"(BRExIt),":[43],"which":[44],"accelerates":[45],"games":[48],"by":[49],"incorporating":[50],"opponent":[51,76,85,94],"models":[52],"into":[53],"the":[54,69,90],"state-of-the-art":[55],"algorithm":[57],"(ExIt).":[60],"BRExIt":[61,126],"aims":[62],"(1)":[64],"feature":[66],"shaping":[67],"apprentice,":[70],"head":[74],"predicting":[75],"policies":[77,130],"an":[79,107],"auxiliary":[80],"task,":[81],"(2)":[83],"bias":[84],"moves":[86],"planning":[88],"towards":[89],"given":[91],"or":[92],"model,":[95],"generate":[97],"apprentice":[98],"targets":[99],"that":[100,125],"better":[101,128],"approximate":[102],"response.":[105],"In":[106],"empirical":[108],"ablation":[109],"on":[110],"BRExIt's":[111],"algorithmic":[112],"variants":[113],"set":[116],"of":[117],"fixed":[118],"test":[119],"agents,":[120],"we":[121],"provide":[122],"statistical":[123],"evidence":[124],"learns":[127],"performing":[129],"than":[131],"ExIt.":[132],"Code":[133],"available":[134,139],"at:":[135],"https://github.com/Danielhp95/on-opponent-modelling-in-expert-iteration-code.":[136],"Supplementary":[137],"material":[138],"at":[140],"https://arxiv.org/abs/2206.00113.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}