{"id":"https://openalex.org/W4404710747","doi":"https://doi.org/10.1155/int/9482323","title":"Combining Counterfactual Regret Minimization With Information Gain to Solve Extensive Games With Unknown Environments","display_name":"Combining Counterfactual Regret Minimization With Information Gain to Solve Extensive Games With Unknown Environments","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404710747","doi":"https://doi.org/10.1155/int/9482323"},"language":"en","primary_location":{"id":"doi:10.1155/int/9482323","is_oa":true,"landing_page_url":"https://doi.org/10.1155/int/9482323","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1155/int/9482323","source":{"id":"https://openalex.org/S57950554","display_name":"International Journal of Intelligent Systems","issn_l":"0884-8173","issn":["0884-8173","1098-111X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Intelligent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1155/int/9482323","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103182416","display_name":"Chen Qiu","orcid":"https://orcid.org/0000-0002-1501-1584"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Qiu","raw_affiliation_strings":["School of Computer Science and Technology ,  Harbin Institute of Technology Shenzhen ,  Shenzhen ,  China ,  hitsz.edu.cn"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology ,  Harbin Institute of Technology Shenzhen ,  Shenzhen ,  China ,  hitsz.edu.cn","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328995","display_name":"Xuan Wang","orcid":"https://orcid.org/0000-0002-3512-0649"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210114441","display_name":"Zhejiang Provincial Public Security Department","ror":"https://ror.org/01z3tch16","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210114441"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xuan Wang","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies ,  Shenzhen ,  China","School of Computer Science and Technology ,  Harbin Institute of Technology Shenzhen ,  Shenzhen ,  China ,  hitsz.edu.cn"],"raw_orcid":"https://orcid.org/0000-0002-3512-0649","affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies ,  Shenzhen ,  China","institution_ids":["https://openalex.org/I4210114441"]},{"raw_affiliation_string":"School of Computer Science and Technology ,  Harbin Institute of Technology Shenzhen ,  Shenzhen ,  China ,  hitsz.edu.cn","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063886144","display_name":"Tenghao Ma","orcid":"https://orcid.org/0000-0002-1613-3284"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianzi Ma","raw_affiliation_strings":["School of Computer Science and Technology ,  Harbin Institute of Technology Shenzhen ,  Shenzhen ,  China ,  hitsz.edu.cn"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology ,  Harbin Institute of Technology Shenzhen ,  Shenzhen ,  China ,  hitsz.edu.cn","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yaojun Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaojun Wen","raw_affiliation_strings":["School of Computer Science and Technology ,  Harbin Institute of Technology Shenzhen ,  Shenzhen ,  China ,  hitsz.edu.cn"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology ,  Harbin Institute of Technology Shenzhen ,  Shenzhen ,  China ,  hitsz.edu.cn","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100417632","display_name":"Jiajia Zhang","orcid":"https://orcid.org/0000-0001-6611-2046"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210114441","display_name":"Zhejiang Provincial Public Security Department","ror":"https://ror.org/01z3tch16","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210114441"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajia Zhang","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies ,  Shenzhen ,  China","School of Computer Science and Technology ,  Harbin Institute of Technology Shenzhen ,  Shenzhen ,  China ,  hitsz.edu.cn"],"raw_orcid":"https://orcid.org/0000-0001-6611-2046","affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies ,  Shenzhen ,  China","institution_ids":["https://openalex.org/I4210114441"]},{"raw_affiliation_string":"School of Computer Science and Technology ,  Harbin Institute of Technology Shenzhen ,  Shenzhen ,  China ,  hitsz.edu.cn","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100328995"],"corresponding_institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213","https://openalex.org/I4210114441"],"apc_list":{"value":2500,"currency":"USD","value_usd":2500},"apc_paid":{"value":2500,"currency":"USD","value_usd":2500},"fwci":0.3147,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.67224566,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"2024","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9926000237464905,"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":0.9783999919891357,"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/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.9432417750358582},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.89255291223526},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.67237389087677},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6157647371292114},{"id":"https://openalex.org/keywords/information-gain","display_name":"Information gain","score":0.5913386344909668},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.48784327507019043},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37556421756744385},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.31455105543136597},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2748521566390991},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07280111312866211}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.9432417750358582},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.89255291223526},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.67237389087677},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6157647371292114},{"id":"https://openalex.org/C2983203078","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Information gain","level":2,"score":0.5913386344909668},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.48784327507019043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37556421756744385},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31455105543136597},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2748521566390991},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07280111312866211},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1155/int/9482323","is_oa":true,"landing_page_url":"https://doi.org/10.1155/int/9482323","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1155/int/9482323","source":{"id":"https://openalex.org/S57950554","display_name":"International Journal of Intelligent Systems","issn_l":"0884-8173","issn":["0884-8173","1098-111X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Intelligent Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1155/int/9482323","is_oa":true,"landing_page_url":"https://doi.org/10.1155/int/9482323","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1155/int/9482323","source":{"id":"https://openalex.org/S57950554","display_name":"International Journal of Intelligent Systems","issn_l":"0884-8173","issn":["0884-8173","1098-111X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1880084553","display_name":null,"funder_award_id":"62376073","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7349572720","display_name":null,"funder_award_id":"2022B1212010005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404710747.pdf","grobid_xml":"https://content.openalex.org/works/W4404710747.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1909320841","https://openalex.org/W2020920737","https://openalex.org/W2067050450","https://openalex.org/W2093825590","https://openalex.org/W2095705004","https://openalex.org/W2102665362","https://openalex.org/W2103315867","https://openalex.org/W2103437045","https://openalex.org/W2126776273","https://openalex.org/W2145339207","https://openalex.org/W2494793979","https://openalex.org/W2767449908","https://openalex.org/W2773381986","https://openalex.org/W2775142175","https://openalex.org/W2966397236","https://openalex.org/W3037694644","https://openalex.org/W4214717370","https://openalex.org/W4285364563","https://openalex.org/W4294576339","https://openalex.org/W4322773517","https://openalex.org/W4382135120","https://openalex.org/W6676468133"],"related_works":["https://openalex.org/W2971351794","https://openalex.org/W4376155396","https://openalex.org/W1983202944","https://openalex.org/W2132624896","https://openalex.org/W2802467175","https://openalex.org/W2022564137","https://openalex.org/W2035984254","https://openalex.org/W4291127980","https://openalex.org/W2118206667","https://openalex.org/W633344313"],"abstract_inverted_index":{"Counterfactual":[0],"regret":[1],"minimization":[2],"(CFR)":[3],"is":[4,18,57,66],"an":[5],"effective":[6],"algorithm":[7],"for":[8],"solving":[9],"extensive\u2010form":[10],"games":[11],"with":[12,86,100,114,125,168,202],"imperfect":[13],"information":[14,115,150],"(IIEGs).":[15],"However,":[16],"CFR":[17,56,62,113,159],"only":[19],"allowed":[20],"to":[21,96,117,133,206],"be":[22,161],"applied":[23],"in":[24,43,63,76,179],"known":[25],"environments,":[26],"where":[27],"the":[28,32,36,40,77,87,98,101,119,139,152,154,165,169,173,198,203,207,218],"transition":[29],"function":[30,38],"of":[31,39,123,176,200,221],"chance":[33],"player":[34],"and":[35,89,137,143,191,210],"reward":[37],"terminal":[41],"node":[42],"IIEGs":[44,124],"are":[45,90],"known.":[46],"In":[47,104,146],"uncertain":[48,142,180],"situations,":[49],"such":[50,187],"as":[51,164,188],"reinforcement":[52],"learning":[53],"(RL)":[54],"problems,":[55],"not":[58],"applicable.":[59],"Thus,":[60],"applying":[61],"unknown":[64,126,135],"environments":[65,136],"a":[67,109,130,212],"significant":[68],"challenge":[69],"that":[70,111],"can":[71,160],"also":[72],"address":[73],"some":[74],"difficulties":[75],"real":[78,102,144],"world.":[79],"Currently,":[80],"advanced":[81],"solutions":[82],"require":[83],"more":[84,213],"interactions":[85,201],"environment":[88,204],"limited":[91],"by":[92,148,158],"large":[93],"single\u2010sampling":[94],"variances":[95],"narrow":[97],"gap":[99],"environment.":[103],"this":[105],"paper,":[106],"we":[107],"propose":[108],"method":[110,178,195],"combines":[112],"gain":[116],"compute":[118],"Nash":[120],"equilibrium":[121],"(NE)":[122],"environments.":[127,145,181],"We":[128],"use":[129],"curiosity\u2010driven":[131],"approach":[132],"explore":[134],"minimize":[138],"discrepancy":[140],"between":[141],"addition,":[147],"incorporating":[149],"into":[151],"reward,":[153],"average":[155],"strategy":[156],"calculated":[157],"directly":[162],"implemented":[163],"interaction":[166,222],"policy":[167],"environment,":[170],"thereby":[171],"improving":[172],"exploration":[174],"efficiency":[175],"our":[177,194],"Through":[182],"experiments":[183],"on":[184],"standard":[185],"testbeds":[186],"Kuhn":[189],"poker":[190],"Leduc":[192],"poker,":[193],"significantly":[196],"reduces":[197],"number":[199,220],"compared":[205],"different":[208],"baselines":[209],"computes":[211],"accurate":[214],"approximate":[215],"NE":[216],"within":[217],"same":[219],"rounds.":[223]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}