{"id":"https://openalex.org/W4407255972","doi":"https://doi.org/10.3390/sym17020250","title":"Efficient Parallel Design for Self-Play in Two-Player Zero-Sum Games","display_name":"Efficient Parallel Design for Self-Play in Two-Player Zero-Sum Games","publication_year":2025,"publication_date":"2025-02-07","ids":{"openalex":"https://openalex.org/W4407255972","doi":"https://doi.org/10.3390/sym17020250"},"language":"en","primary_location":{"id":"doi:10.3390/sym17020250","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym17020250","pdf_url":"https://www.mdpi.com/2073-8994/17/2/250/pdf?version=1738921508","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2073-8994/17/2/250/pdf?version=1738921508","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077477958","display_name":"Hongsong Tang","orcid":"https://orcid.org/0000-0002-1366-3749"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongsong Tang","raw_affiliation_strings":["School of Science, Beijing University of Posts and Telecommunications, Beijing 100876, China"],"raw_orcid":"https://orcid.org/0000-0002-1366-3749","affiliations":[{"raw_affiliation_string":"School of Science, Beijing University of Posts and Telecommunications, Beijing 100876, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427253","display_name":"Bo Chen","orcid":"https://orcid.org/0000-0001-5151-9388"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Chen","raw_affiliation_strings":["School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing 100876, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing 100876, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111492686","display_name":"Yingzhuo Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingzhuo Liu","raw_affiliation_strings":["School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing 100876, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing 100876, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101042868","display_name":"Kuoye Han","orcid":null},"institutions":[{"id":"https://openalex.org/I2800372957","display_name":"China Electronics Technology Group Corporation","ror":"https://ror.org/0098hst83","country_code":"CN","type":"company","lineage":["https://openalex.org/I2800372957"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kuoye Han","raw_affiliation_strings":["Information Science Academy (ISA), China Electronics Technology Group Corporation (CETC), Beijing 100043, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Science Academy (ISA), China Electronics Technology Group Corporation (CETC), Beijing 100043, China","institution_ids":["https://openalex.org/I2800372957"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053440918","display_name":"Jingqian Liu","orcid":"https://orcid.org/0009-0008-8949-9691"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingqian Liu","raw_affiliation_strings":["Chinatelecom Group Corporation, Beijing 100032, China"],"raw_orcid":"https://orcid.org/0009-0008-8949-9691","affiliations":[{"raw_affiliation_string":"Chinatelecom Group Corporation, Beijing 100032, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045970695","display_name":"Zhaowei Qu","orcid":"https://orcid.org/0000-0002-8819-6778"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhaowei Qu","raw_affiliation_strings":["School of Science, Beijing University of Posts and Telecommunications, Beijing 100876, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Science, Beijing University of Posts and Telecommunications, Beijing 100876, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5045970695"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":{"value":2000,"currency":"CHF","value_usd":2227},"apc_paid":{"value":2000,"currency":"CHF","value_usd":2227},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00770836,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":"2","first_page":"250","last_page":"250"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.998199999332428,"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":0.998199999332428,"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":0.9886000156402588,"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/T12158","display_name":"Guidance and Control Systems","score":0.9473000168800354,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8597678542137146},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.8188594579696655},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5449357032775879},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.47080835700035095},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44267648458480835},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.41843464970588684},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3287487030029297},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.13051676750183105},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11353006958961487}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8597678542137146},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.8188594579696655},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5449357032775879},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.47080835700035095},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44267648458480835},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.41843464970588684},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3287487030029297},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.13051676750183105},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11353006958961487},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3390/sym17020250","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym17020250","pdf_url":"https://www.mdpi.com/2073-8994/17/2/250/pdf?version=1738921508","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3390/sym17020250","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym17020250","pdf_url":"https://www.mdpi.com/2073-8994/17/2/250/pdf?version=1738921508","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4407255972.pdf"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W2113351146","https://openalex.org/W2257979135","https://openalex.org/W2574978968","https://openalex.org/W2750605955","https://openalex.org/W2766447205","https://openalex.org/W2786036274","https://openalex.org/W2963762747","https://openalex.org/W2977093897","https://openalex.org/W2982316857","https://openalex.org/W2989847975","https://openalex.org/W2997502221","https://openalex.org/W3096726323","https://openalex.org/W3107951310","https://openalex.org/W3118210634","https://openalex.org/W3196792970","https://openalex.org/W3198350258","https://openalex.org/W4287757305","https://openalex.org/W4287813665","https://openalex.org/W4296546847","https://openalex.org/W4311723471","https://openalex.org/W4366731969","https://openalex.org/W4401023795","https://openalex.org/W6604092932","https://openalex.org/W6677916085","https://openalex.org/W6681187623","https://openalex.org/W6758729514","https://openalex.org/W6766805167","https://openalex.org/W6767327128","https://openalex.org/W6775695405","https://openalex.org/W6780812528","https://openalex.org/W6785535465","https://openalex.org/W6800877681","https://openalex.org/W6843268680","https://openalex.org/W6851389620"],"related_works":["https://openalex.org/W2073713056","https://openalex.org/W3110702597","https://openalex.org/W2078761926","https://openalex.org/W2110441383","https://openalex.org/W2125620709","https://openalex.org/W1498872724","https://openalex.org/W4233149903","https://openalex.org/W4293864700","https://openalex.org/W2524540579","https://openalex.org/W2326878701"],"abstract_inverted_index":{"Self-play":[0],"methods":[1],"have":[2],"achieved":[3],"remarkable":[4],"success":[5],"in":[6,13,41,60,130,153,175],"two-player":[7,62],"zero-sum":[8,63],"games,":[9],"attaining":[10],"superhuman":[11],"performance":[12,59,109,174],"many":[14],"complex":[15,26,61],"game":[16,142],"domains.":[17],"Parallelizing":[18],"learners":[19,30],"is":[20,52,114,135],"a":[21],"feasible":[22],"approach":[23],"to":[24,33,54,84,93,127,167],"handle":[25],"games.":[27,64],"However,":[28],"parallelizing":[29],"often":[31],"leads":[32],"the":[34,46,74,107,139,155,162,165],"suboptimal":[35],"exploitation":[36],"of":[37,110,164],"computational":[38,87],"resources,":[39],"resulting":[40],"inefficiencies.":[42],"This":[43,159],"paper":[44],"introduces":[45],"Mixed":[47],"Hierarchical":[48,90],"Oracle":[49,76],"(MHO),":[50],"which":[51],"designed":[53,100],"enhance":[55],"training":[56,108],"efficiency":[57],"and":[58,89,96,143,146,172],"MHO":[65,134,166],"efficiently":[66],"leverages":[67],"interaction":[68],"data":[69],"among":[70],"parallelized":[71,103],"solvers":[72],"during":[73],"Parallelized":[75],"(PO)":[77],"process,":[78],"while":[79],"employing":[80],"Model":[81],"Soups":[82],"(MS)":[83],"consolidate":[85],"fragmented":[86],"resources":[88],"Exploration":[91],"(HE)":[92],"balance":[94],"exploration":[95],"exploitation.":[97],"These":[98],"carefully":[99],"enhancements":[101],"for":[102],"systems":[104],"significantly":[105],"improve":[106,173],"self-play.":[111],"Additionally,":[112],"MiniStar":[113,144],"introduced":[115],"as":[116],"an":[117],"open":[118],"source":[119],"environment":[120],"focused":[121],"on":[122,137],"small-scale":[123],"combat":[124],"scenarios,":[125],"developed":[126],"facilitate":[128],"research":[129],"self-play":[131,176],"algorithms.":[132],"The":[133],"evaluated":[136],"both":[138],"AlphaStar888":[140],"matrix":[141],"environment,":[145],"ablation":[147],"studies":[148],"further":[149],"demonstrates":[150],"its":[151],"effectiveness":[152],"improving":[154],"agent\u2019s":[156],"decision-making":[157],"capabilities.":[158],"work":[160],"highlight":[161],"potential":[163],"optimize":[168],"compute":[169],"resource":[170],"utilization":[171],"methods.":[177]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
