{"id":"https://openalex.org/W4324118564","doi":"https://doi.org/10.1109/cac57257.2022.10054957","title":"Offline PSRO with Max-Min Entropy for Multi-Player Imperfect Information Games","display_name":"Offline PSRO with Max-Min Entropy for Multi-Player Imperfect Information Games","publication_year":2022,"publication_date":"2022-11-25","ids":{"openalex":"https://openalex.org/W4324118564","doi":"https://doi.org/10.1109/cac57257.2022.10054957"},"language":"en","primary_location":{"id":"doi:10.1109/cac57257.2022.10054957","doi":"https://doi.org/10.1109/cac57257.2022.10054957","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cac57257.2022.10054957","pdf_url":null,"source":{"id":"https://openalex.org/S4363604230","display_name":"China Automation Congress (CAC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2022 China Automation Congress (CAC)","raw_type":"proceedings-article"},"volume":null,"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/A5000620358","display_name":"Junren Luo","orcid":"https://orcid.org/0000-0003-2126-0365","observed_orcids":["https://orcid.org/0000-0003-2126-0365"]},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junren Luo","raw_affiliation_strings":["National University of Defense Technology,College of Intelligence and Technology,Changsha,China","College of Intelligence and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Intelligence and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Intelligence and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072408261","display_name":"Wanpeng Zhang","orcid":"https://orcid.org/0000-0001-5351-3449","observed_orcids":["https://orcid.org/0000-0001-5351-3449"]},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanpeng Zhang","raw_affiliation_strings":["National University of Defense Technology,College of Intelligence and Technology,Changsha,China","College of Intelligence and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Intelligence and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Intelligence and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025342481","display_name":"Mingwo Zou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingwo Zou","raw_affiliation_strings":["National University of Defense Technology,College of Intelligence and Technology,Changsha,China","College of Intelligence and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Intelligence and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Intelligence and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108313535","display_name":"Jiongming Su","orcid":"https://orcid.org/0009-0007-2965-8825","observed_orcids":["https://orcid.org/0009-0007-2965-8825"]},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiongming Su","raw_affiliation_strings":["National University of Defense Technology,College of Intelligence and Technology,Changsha,China","College of Intelligence and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Intelligence and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Intelligence and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100394982","display_name":"Jing Chen","orcid":"https://orcid.org/0000-0003-3409-8651","observed_orcids":["https://orcid.org/0000-0003-3409-8651"]},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Chen","raw_affiliation_strings":["National University of Defense Technology,College of Intelligence and Technology,Changsha,China","College of Intelligence and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Intelligence and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Intelligence and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18546949,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"5020","last_page":"5024"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9829000234603882,"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":0.9829000234603882,"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":0.009800000116229057,"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/T11031","display_name":"Game Theory and Applications","score":0.004399999976158142,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/entropy-regularization","display_name":"entropy regularization","score":0.6259999871253967},{"id":"https://openalex.org/keywords/multiplayer-games","display_name":"multiplayer games","score":0.6840000152587891},{"id":"https://openalex.org/keywords/imperfect-information-games","display_name":"imperfect information games","score":0.9869999885559082},{"id":"https://openalex.org/keywords/extensive-form-games","display_name":"extensive form games","score":0.9879999756813049},{"id":"https://openalex.org/keywords/best-response","display_name":"best response","score":0.7210000157356262},{"id":"https://openalex.org/keywords/game-theoretic-learning","display_name":"game-theoretic learning","score":0.6589999794960022}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8053493499755859},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6104026436805725},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.47937682271003723},{"id":"https://openalex.org/C155911762","wikidata":"https://www.wikidata.org/wiki/Q422321","display_name":"Blueprint","level":2,"score":0.4784376919269562},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.4545608162879944},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4299110174179077},{"id":"https://openalex.org/C123676819","wikidata":"https://www.wikidata.org/wiki/Q1074338","display_name":"Perfect information","level":2,"score":0.41148728132247925},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3926711082458496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39055824279785156},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0758117139339447},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cac57257.2022.10054957","doi":"https://doi.org/10.1109/cac57257.2022.10054957","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cac57257.2022.10054957","pdf_url":null,"source":{"id":"https://openalex.org/S4363604230","display_name":"China Automation Congress (CAC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2022 China Automation Congress (CAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2026177035","https://openalex.org/W2257979135","https://openalex.org/W2539402368","https://openalex.org/W2574978968","https://openalex.org/W2911495555","https://openalex.org/W2912083425","https://openalex.org/W2914304175","https://openalex.org/W2925418831","https://openalex.org/W4360584316","https://openalex.org/W4362590704"],"related_works":["https://openalex.org/W7133359914","https://openalex.org/W7096296915","https://openalex.org/W7095674924","https://openalex.org/W2202744812","https://openalex.org/W2889169285","https://openalex.org/W10452781","https://openalex.org/W4394649275","https://openalex.org/W7096249828","https://openalex.org/W4221155770","https://openalex.org/W7100666874"],"abstract_inverted_index":{"Game":[0],"theoretic":[1],"learning":[2,16,68],"for":[3,76],"the":[4,8,47,54,64,80,84],"blueprint":[5],"strategy":[6],"is":[7,17,57],"central":[9],"topic":[10],"of":[11,86],"offline":[12,31,48,55,77],"game":[13,78],"solving.":[14],"Offline":[15],"one":[18,30],"typical":[19],"data-driven":[20],"paradigm":[21],"that":[22,37],"learns":[23],"from":[24,63],"logged":[25],"dataset.":[26],"This":[27,70],"paper":[28],"provides":[29],"PSRO":[32,56],"algorithms":[33],"with":[34,42,50,59],"max-min":[35],"exploration":[36],"can":[38],"solve":[39],"extensive-form":[40],"games":[41],"imperfect":[43],"information.":[44],"After":[45],"constructing":[46],"dataset":[49],"expert":[51],"interaction":[52],"experience,":[53],"trained":[58],"best":[60],"response":[61],"generated":[62],"entropy":[65],"regularized":[66],"reinforcement":[67],"method.":[69],"work":[71],"will":[72],"provide":[73],"a":[74],"reference":[75],"solving,":[79],"experimental":[81],"results":[82],"demonstrated":[83],"effectiveness":[85],"our":[87],"framework.":[88]},"counts_by_year":[],"updated_date":"2026-10-05T09:50:58.205359","created_date":"2023-03-15T00:00:00"}
