{"id":"https://openalex.org/W2977093897","doi":"https://doi.org/10.1109/cig.2019.8848006","title":"A Generalized Framework for Self-Play Training","display_name":"A Generalized Framework for Self-Play Training","publication_year":2019,"publication_date":"2019-08-01","ids":{"openalex":"https://openalex.org/W2977093897","doi":"https://doi.org/10.1109/cig.2019.8848006","mag":"2977093897"},"language":"en","primary_location":{"id":"doi:10.1109/cig.2019.8848006","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cig.2019.8848006","pdf_url":null,"source":{"id":"https://openalex.org/S4306498491","display_name":"2019 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":"2019 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/A5102004210","display_name":"Daniel Hern\u00e1ndez","orcid":"https://orcid.org/0000-0002-1667-2579"},"institutions":[{"id":"https://openalex.org/I52099693","display_name":"University of York","ror":"https://ror.org/04m01e293","country_code":"GB","type":"education","lineage":["https://openalex.org/I52099693"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Daniel Hernandez","raw_affiliation_strings":["Department of Computer Science, University of York, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of York, UK","institution_ids":["https://openalex.org/I52099693"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068468650","display_name":"Kevin Denamgana\u00ef","orcid":"https://orcid.org/0000-0002-8776-4331"},"institutions":[{"id":"https://openalex.org/I52099693","display_name":"University of York","ror":"https://ror.org/04m01e293","country_code":"GB","type":"education","lineage":["https://openalex.org/I52099693"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kevin Denamganai","raw_affiliation_strings":["Department of Computer Science, University of York, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of York, UK","institution_ids":["https://openalex.org/I52099693"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055954787","display_name":"Yuan Gao","orcid":"https://orcid.org/0000-0002-3526-5856"},"institutions":[{"id":"https://openalex.org/I123387679","display_name":"Uppsala University","ror":"https://ror.org/048a87296","country_code":"SE","type":"education","lineage":["https://openalex.org/I123387679"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Yuan Gao","raw_affiliation_strings":["Department of Information and Technology, Uppsala University, Sweden"],"affiliations":[{"raw_affiliation_string":"Department of Information and Technology, Uppsala University, Sweden","institution_ids":["https://openalex.org/I123387679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011877026","display_name":"Peter York","orcid":"https://orcid.org/0000-0002-7329-9993"},"institutions":[{"id":"https://openalex.org/I52099693","display_name":"University of York","ror":"https://ror.org/04m01e293","country_code":"GB","type":"education","lineage":["https://openalex.org/I52099693"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peter York","raw_affiliation_strings":["Department of Computer Science, University of York, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of York, UK","institution_ids":["https://openalex.org/I52099693"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048451922","display_name":"Sam Devlin","orcid":"https://orcid.org/0000-0002-7769-3090"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sam Devlin","raw_affiliation_strings":["Microsoft Research, Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Cambridge, UK","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033216620","display_name":"Spyridon Samothrakis","orcid":"https://orcid.org/0000-0003-1902-9690"},"institutions":[{"id":"https://openalex.org/I110002522","display_name":"University of Essex","ror":"https://ror.org/02nkf1q06","country_code":"GB","type":"education","lineage":["https://openalex.org/I110002522"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Spyridon Samothrakis","raw_affiliation_strings":["University of Essex, Institute of Analytics & Data Science, UK"],"affiliations":[{"raw_affiliation_string":"University of Essex, Institute of Analytics & Data Science, UK","institution_ids":["https://openalex.org/I110002522"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017600718","display_name":"James Alfred Walker","orcid":"https://orcid.org/0000-0003-2174-7173"},"institutions":[{"id":"https://openalex.org/I52099693","display_name":"University of York","ror":"https://ror.org/04m01e293","country_code":"GB","type":"education","lineage":["https://openalex.org/I52099693"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"James Alfred Walker","raw_affiliation_strings":["Department of Computer Science, University of York, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of York, UK","institution_ids":["https://openalex.org/I52099693"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5102004210"],"corresponding_institution_ids":["https://openalex.org/I52099693"],"apc_list":null,"apc_paid":null,"fwci":1.7054,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.88260497,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"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":0.9987000226974487,"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":0.9987000226974487,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9940000176429749,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.991599977016449,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7003150582313538},{"id":"https://openalex.org/keywords/meaning","display_name":"Meaning (existential)","score":0.65565025806427},{"id":"https://openalex.org/keywords/replicate","display_name":"Replicate","score":0.606948971748352},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5291695594787598},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5258848071098328},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5157732963562012},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.48418310284614563},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.3560400903224945},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1624840795993805},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.07901829481124878}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7003150582313538},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.65565025806427},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.606948971748352},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5291695594787598},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5258848071098328},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5157732963562012},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.48418310284614563},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.3560400903224945},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1624840795993805},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.07901829481124878},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cig.2019.8848006","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cig.2019.8848006","pdf_url":null,"source":{"id":"https://openalex.org/S4306498491","display_name":"2019 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":"2019 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W111971617","https://openalex.org/W164946830","https://openalex.org/W1579184372","https://openalex.org/W1757796397","https://openalex.org/W2040249719","https://openalex.org/W2103626435","https://openalex.org/W2107649750","https://openalex.org/W2119717200","https://openalex.org/W2124191651","https://openalex.org/W2126316555","https://openalex.org/W2131600418","https://openalex.org/W2132994929","https://openalex.org/W2187089797","https://openalex.org/W2257979135","https://openalex.org/W2324671092","https://openalex.org/W2592076308","https://openalex.org/W2618097077","https://openalex.org/W2736601468","https://openalex.org/W2762117857","https://openalex.org/W2766447205","https://openalex.org/W2772709170","https://openalex.org/W2784570041","https://openalex.org/W2787259794","https://openalex.org/W2810602713","https://openalex.org/W2895865957","https://openalex.org/W2913409451","https://openalex.org/W2962715211","https://openalex.org/W2963477884","https://openalex.org/W2963642149","https://openalex.org/W2963937357","https://openalex.org/W3198350258","https://openalex.org/W4214717370","https://openalex.org/W4297789683","https://openalex.org/W4297802199","https://openalex.org/W4297810554","https://openalex.org/W4298857966","https://openalex.org/W4300198501","https://openalex.org/W4362203700","https://openalex.org/W6606729516","https://openalex.org/W6637967152","https://openalex.org/W6687681856","https://openalex.org/W6738855998","https://openalex.org/W6741002519","https://openalex.org/W6743367460","https://openalex.org/W6745190604","https://openalex.org/W6746177919","https://openalex.org/W6748636368","https://openalex.org/W6751955673","https://openalex.org/W6758729514","https://openalex.org/W6780225908","https://openalex.org/W6780559895","https://openalex.org/W6947956204"],"related_works":["https://openalex.org/W4254851101","https://openalex.org/W3171007296","https://openalex.org/W22115721","https://openalex.org/W2211931904","https://openalex.org/W2065444835","https://openalex.org/W2321234655","https://openalex.org/W2952773340","https://openalex.org/W2470062578","https://openalex.org/W2981861370","https://openalex.org/W2982204590"],"abstract_inverted_index":{"Throughout":[0],"scientific":[1],"history,":[2],"overarching":[3],"theoretical":[4,81],"frameworks":[5],"have":[6],"allowed":[7],"researchers":[8],"to":[9,20,27,79],"grow":[10],"beyond":[11],"personal":[12],"intuitions":[13],"and":[14,22,26],"culturally":[15],"biased":[16],"theories.":[17],"They":[18],"allow":[19],"verify":[21],"replicate":[23],"existing":[24,69],"findings,":[25],"link":[28],"disconnected":[29],"results.":[30],"The":[31,113],"notion":[32],"of":[33,63,98],"self-play,":[34],"albeit":[35],"often":[36],"cited":[37],"in":[38,46],"multiagent":[39,85],"Reinforcement":[40],"Learning,":[41],"has":[42],"never":[43],"been":[44],"grounded":[45],"a":[47,52,80,88,96],"formal":[48],"model.":[49],"We":[50],"present":[51],"formalized":[53],"framework,":[54],"with":[55,108],"clearly":[56],"defined":[57],"assumptions,":[58],"which":[59],"encapsulates":[60],"the":[61,99,109,119],"meaning":[62],"self-play":[64,70,101,127],"as":[65,76],"abstracted":[66],"from":[67],"various":[68],"algorithms.":[71],"This":[72],"framework":[73],"is":[74,129],"framed":[75],"an":[77,132],"approximation":[78],"solution":[82,105],"concept":[83],"for":[84],"training.":[86],"On":[87],"simple":[89],"environment,":[90],"we":[91],"qualitatively":[92],"measure":[93],"how":[94],"well":[95],"subset":[97],"captured":[100],"methods":[102],"approximate":[103],"this":[104],"when":[106],"paired":[107],"famous":[110],"PPO":[111],"algorithm.":[112],"results":[114],"indicate":[115],"that":[116,126],"throughout":[117],"training":[118],"trained":[120],"policies":[121],"exhibit":[122],"cyclic":[123],"evolutions,":[124],"showing":[125],"research":[128],"still":[130],"at":[131],"early":[133],"stage.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}