{"id":"https://openalex.org/W4206145040","doi":"https://doi.org/10.1109/cog52621.2021.9619146","title":"Proximal Policy Optimization with Elo-based Opponent Selection and Combination with Enhanced Rolling Horizon Evolution Algorithm","display_name":"Proximal Policy Optimization with Elo-based Opponent Selection and Combination with Enhanced Rolling Horizon Evolution Algorithm","publication_year":2021,"publication_date":"2021-08-17","ids":{"openalex":"https://openalex.org/W4206145040","doi":"https://doi.org/10.1109/cog52621.2021.9619146"},"language":"en","primary_location":{"id":"doi:10.1109/cog52621.2021.9619146","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog52621.2021.9619146","pdf_url":null,"source":{"id":"https://openalex.org/S4363608335","display_name":"2021 IEEE Conference on Games (CoG)","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":"2021 IEEE Conference on Games (CoG)","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/A5064113913","display_name":"Rongqin Liang","orcid":"https://orcid.org/0000-0002-7313-6561"},"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"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rongqin Liang","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080193690","display_name":"Yuanheng Zhu","orcid":"https://orcid.org/0000-0001-5384-423X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanheng Zhu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences / University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences / University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029367575","display_name":"Zhentao Tang","orcid":"https://orcid.org/0000-0002-2481-4119"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhentao Tang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences / University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences / University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113960258","display_name":"Mu Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mu Yang","raw_affiliation_strings":["Department of Game AI Research, Parametrix.ai, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Department of Game AI Research, Parametrix.ai, Shenzhen, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101872636","display_name":"Xiaolong Zhu","orcid":"https://orcid.org/0000-0002-2169-8220"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaolong Zhu","raw_affiliation_strings":["Department of Game AI Research, Parametrix.ai, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Department of Game AI Research, Parametrix.ai, Shenzhen, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5064113913"],"corresponding_institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.8796,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.78051972,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9995999932289124,"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":0.9995999932289124,"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/T11197","display_name":"Digital Games and Media","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10731","display_name":"Educational Games and Gamification","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6675611138343811},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.6413760781288147},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4948887228965759},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.49273326992988586},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48623934388160706},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4841116666793823},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.4699096083641052},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.442335844039917},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.3511708974838257},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18081018328666687}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6675611138343811},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.6413760781288147},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4948887228965759},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.49273326992988586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48623934388160706},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4841116666793823},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.4699096083641052},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.442335844039917},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.3511708974838257},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18081018328666687},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cog52621.2021.9619146","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog52621.2021.9619146","pdf_url":null,"source":{"id":"https://openalex.org/S4363608335","display_name":"2021 IEEE Conference on Games (CoG)","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":"2021 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2968709009","display_name":null,"funder_award_id":"2018AAA0101005","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2069797667","https://openalex.org/W2145339207","https://openalex.org/W2475089067","https://openalex.org/W2569196563","https://openalex.org/W2604279009","https://openalex.org/W2736601468","https://openalex.org/W2749807327","https://openalex.org/W2766774971","https://openalex.org/W2963890729","https://openalex.org/W2989847975","https://openalex.org/W3084241738","https://openalex.org/W3118210634","https://openalex.org/W6721101288"],"related_works":["https://openalex.org/W2280422768","https://openalex.org/W3143197806","https://openalex.org/W4252555497","https://openalex.org/W4388150944","https://openalex.org/W3121175838","https://openalex.org/W3016293053","https://openalex.org/W1690653314","https://openalex.org/W2401723157","https://openalex.org/W2065055572","https://openalex.org/W2784269775"],"abstract_inverted_index":{"Two-player":[0],"zero-sum":[1],"video":[2],"game":[3,11],"is":[4],"a":[5],"basic":[6],"and":[7,30,73,93],"important":[8],"problem":[9],"in":[10,49],"artificial":[12],"intelligence.":[13],"In":[14,56],"2020,":[15],"enhanced":[16,74],"rolling":[17,75],"horizon":[18,76],"evolution":[19,77],"algorithm":[20,78],"with":[21,80,113],"policy":[22,70],"gradient":[23],"(ERHEAPI)":[24],"beat":[25],"heuristics,":[26],"Monte-Carlo":[27],"tree":[28],"search":[29],"other":[31],"methods":[32],"to":[33,84],"win":[34],"the":[35,45,50,90,96,102,107,110,119],"championship":[36],"of":[37,47,109,121],"Fighting":[38],"Game":[39],"Artificial":[40],"Intelligence":[41],"Competition":[42],"(FTGAIC).":[43],"However,":[44],"performance":[46,108],"ERHEAPI":[48],"first":[51],"round":[52],"was":[53],"not":[54],"good.":[55],"this":[57],"paper,":[58],"we":[59],"present":[60],"an":[61],"effective":[62],"method":[63],"noted":[64],"as":[65],"ERHEAPPO":[66,112],"that":[67,95],"combines":[68],"proximal":[69],"optimization":[71],"(PPO)":[72],"(ERHEA)":[79],"opponent":[81,98],"model":[82],"learning":[83],"further":[85],"improve":[86,101],"performance.":[87],"We":[88,105],"train":[89],"PPO":[91],"agent":[92],"find":[94],"Elo-based":[97],"selection":[99],"can":[100],"sample":[103],"efficiency.":[104],"compare":[106],"proposed":[111],"ERHEAPI.":[114],"The":[115],"experimental":[116],"results":[117],"demonstrate":[118],"effectiveness":[120],"ERHEAPPO.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}