{"id":"https://openalex.org/W4416252125","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227369","title":"Diversity-Driven Offline-to-Online Multi-Player Policy Learning for Football Matches","display_name":"Diversity-Driven Offline-to-Online Multi-Player Policy Learning for Football Matches","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416252125","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227369"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227369","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227369","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","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/A5090380831","display_name":"Shijie Wang","orcid":"https://orcid.org/0000-0001-8429-9449"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shijie Wang","raw_affiliation_strings":["School of Artificial Intelligence, UCAS Institute of Automation, CAS,Beijing,China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, UCAS Institute of Automation, CAS,Beijing,China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060319097","display_name":"Zhiqiang Pu","orcid":"https://orcid.org/0000-0002-4841-4048"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiang Pu","raw_affiliation_strings":["School of Artificial Intelligence, UCAS Institute of Automation, CAS,Beijing,China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, UCAS Institute of Automation, CAS,Beijing,China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008262752","display_name":"Tianyi Hu","orcid":"https://orcid.org/0000-0002-2231-8170"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyi Hu","raw_affiliation_strings":["School of Artificial Intelligence, UCAS Institute of Automation, CAS,Beijing,China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, UCAS Institute of Automation, CAS,Beijing,China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103364650","display_name":"Hao Ma","orcid":"https://orcid.org/0000-0001-9563-2518"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Ma","raw_affiliation_strings":["School of Artificial Intelligence, UCAS Institute of Automation, CAS,Beijing,China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, UCAS Institute of Automation, CAS,Beijing,China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075244395","display_name":"Huimu Wang","orcid":"https://orcid.org/0000-0001-7115-8831"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huimu Wang","raw_affiliation_strings":["JD.COM,Beijing,China"],"affiliations":[{"raw_affiliation_string":"JD.COM,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019541846","display_name":"Jianqiang Yi","orcid":"https://orcid.org/0000-0003-3268-9482"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianqiang Yi","raw_affiliation_strings":["School of Artificial Intelligence, UCAS Institute of Automation, CAS,Beijing,China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, UCAS Institute of Automation, CAS,Beijing,China","institution_ids":["https://openalex.org/I4210100255"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5090380831"],"corresponding_institution_ids":["https://openalex.org/I4210100255"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1832183,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.555899977684021,"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":0.555899977684021,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.14339999854564667,"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":0.04179999977350235,"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/football","display_name":"Football","score":0.683899998664856},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6751999855041504},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5374000072479248},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5263000130653381},{"id":"https://openalex.org/keywords/online-and-offline","display_name":"Online and offline","score":0.4781999886035919},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.4587000012397766},{"id":"https://openalex.org/keywords/offline-learning","display_name":"Offline learning","score":0.35510000586509705},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.35120001435279846}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7261999845504761},{"id":"https://openalex.org/C2778444522","wikidata":"https://www.wikidata.org/wiki/Q1081491","display_name":"Football","level":2,"score":0.683899998664856},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6751999855041504},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5374000072479248},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5263000130653381},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5151000022888184},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.4781999886035919},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.4587000012397766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4505999982357025},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.35510000586509705},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.35120001435279846},{"id":"https://openalex.org/C3020114046","wikidata":"https://www.wikidata.org/wiki/Q41323","display_name":"American football","level":3,"score":0.34860000014305115},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.33970001339912415},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.33079999685287476},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C125014702","wikidata":"https://www.wikidata.org/wiki/Q4680749","display_name":"Adaptive learning","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.26429998874664307},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.2556000053882599}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227369","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227369","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320326444","display_name":"Nova","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1512681781","https://openalex.org/W1973270683","https://openalex.org/W1987111416","https://openalex.org/W1992149319","https://openalex.org/W1998155433","https://openalex.org/W2127338106","https://openalex.org/W2135746467","https://openalex.org/W2142360629","https://openalex.org/W2152617511","https://openalex.org/W2158581396","https://openalex.org/W2158782408","https://openalex.org/W2176410557","https://openalex.org/W2209913494","https://openalex.org/W2514295870","https://openalex.org/W2786572318","https://openalex.org/W2951360122","https://openalex.org/W2997502221","https://openalex.org/W4211248338","https://openalex.org/W4297838928","https://openalex.org/W4319993446","https://openalex.org/W4385245566","https://openalex.org/W4385626984"],"related_works":[],"abstract_inverted_index":{"Due":[0],"to":[1,31,71,119,124,129,139,178],"the":[2,36,91,131,150,157,186],"complexity":[3],"of":[4,38,113,134,153,160],"football":[5,19,59],"matches,":[6],"high-quality":[7],"player":[8],"policies":[9,42],"must":[10],"exhibit":[11],"diverse":[12],"behaviors":[13],"for":[14,58,85,93],"effective":[15],"collaboration.":[16],"However,":[17],"in":[18,165,185],"tasks":[20],"where":[21],"online":[22,75,94,103,144,161],"interactions":[23],"are":[24],"time-consuming":[25],"and":[26,35,74,102,115],"costly,":[27],"it":[28],"is":[29,68],"difficult":[30],"balance":[32],"training":[33],"efficiency":[34],"emergence":[37],"diversity":[39],"when":[40],"learning":[41,56,155],"from":[43,137],"scratch.":[44],"Therefore,":[45],"this":[46],"paper":[47],"proposes":[48],"a":[49,64],"novel":[50],"diversity-driven":[51],"offline-to-online":[52],"(DOTO)":[53],"multi-player":[54],"policy":[55,126,196],"method":[57],"matches.":[60],"Specifically,":[61],"we":[62,97,141],"design":[63],"transformer-actor-critic":[65],"module":[66,81],"that":[67,171],"universally":[69],"applicable":[70],"both":[72],"offline":[73,86,101,138,154],"stages,":[76],"enabling":[77],"seamless":[78],"adaptation.":[79],"This":[80],"utilizes":[82],"expert":[83],"data":[84],"pre-training,":[87],"which":[88,109,180],"serves":[89],"as":[90],"initialization":[92,147],"fine-tuning.":[95],"Subsequently,":[96],"introduce":[98],"an":[99,143],"across":[100],"adaptive":[104,121],"intention":[105,111],"clustering":[106,118],"guidance":[107],"module,":[108],"learns":[110],"representations":[112],"agents":[114],"performs":[116],"intention-based":[117],"construct":[120],"loss":[122],"functions":[123],"guide":[125],"diversity.":[127,197],"Besides,":[128],"mitigate":[130],"bootstrapping":[132],"errors":[133],"distribution":[135],"shift":[136],"online,":[140],"implement":[142],"partial":[145],"random":[146],"mechanism,":[148],"balancing":[149],"inherent":[151],"conservativeness":[152],"with":[156],"flexible":[158],"exploration":[159],"learning.":[162],"Extensive":[163],"experiments":[164],"Google":[166],"Research":[167],"Football":[168],"environment":[169],"show":[170],"DOTO":[172],"not":[173],"only":[174],"increases":[175],"win":[176],"rate":[177],"50%":[179],"surpasses":[181],"all":[182],"state-of-the-art":[183],"methods":[184],"hardest":[187],"11":[188,190],"vs.":[189],"task,":[191],"but":[192],"also":[193],"generates":[194],"richer":[195]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-14T00:00:00"}