{"id":"https://openalex.org/W4401978632","doi":"https://doi.org/10.48550/arxiv.2408.01072","title":"A Survey on Self-play Methods in Reinforcement Learning","display_name":"A Survey on Self-play Methods in Reinforcement Learning","publication_year":2024,"publication_date":"2024-08-02","ids":{"openalex":"https://openalex.org/W4401978632","doi":"https://doi.org/10.48550/arxiv.2408.01072"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2408.01072","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.01072","pdf_url":"https://arxiv.org/pdf/2408.01072","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2408.01072","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034919789","display_name":"Ruize Zhang","orcid":"https://orcid.org/0009-0007-6666-3906","observed_orcids":["https://orcid.org/0009-0007-6666-3906"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Ruize","raw_affiliation_strings":["ZELAI XU ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZELAI XU ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xu, Zelai","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Zelai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102811261","display_name":"Chengdong Ma","orcid":"https://orcid.org/0000-0002-7963-3024","observed_orcids":["https://orcid.org/0000-0002-7963-3024"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Chengdong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011646653","display_name":"Chao Yu","orcid":"https://orcid.org/0000-0001-6975-0158","observed_orcids":["https://orcid.org/0000-0001-6975-0158"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Chao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032604295","display_name":"Wei-Wei Tu","orcid":"https://orcid.org/0000-0002-2407-0252","observed_orcids":["https://orcid.org/0000-0002-2407-0252"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tu, Wei-Wei","raw_affiliation_strings":["Chengdong Ma , Peking University , China,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chengdong Ma , Peking University , China,","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tang, Wenhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726818","display_name":"4Thparadigm (China)","ror":"https://ror.org/00x4k9h67","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tang, Wenhao","raw_affiliation_strings":["WEI-WEI TU , 4Paradigm , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WEI-WEI TU , 4Paradigm , China","institution_ids":["https://openalex.org/I4401726818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101984824","display_name":"Shiyu Huang","orcid":"https://orcid.org/0000-0003-0500-0141","observed_orcids":["https://orcid.org/0000-0003-0500-0141"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Shiyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073681676","display_name":"Deheng Ye","orcid":"https://orcid.org/0000-0002-1754-1837","observed_orcids":["https://orcid.org/0000-0002-1754-1837"]},"institutions":[{"id":"https://openalex.org/I4401726818","display_name":"4Thparadigm (China)","ror":"https://ror.org/00x4k9h67","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye, Deheng","raw_affiliation_strings":["WEI-WEI TU , 4Paradigm , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WEI-WEI TU , 4Paradigm , China","institution_ids":["https://openalex.org/I4401726818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084510549","display_name":"Wenbo Ding","orcid":"https://orcid.org/0000-0002-0597-4512","observed_orcids":["https://orcid.org/0000-0002-0597-4512"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ding, Wenbo","raw_affiliation_strings":["Tencent , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent , China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090073634","display_name":"Yaodong Yang","orcid":"https://orcid.org/0000-0001-8132-5613","observed_orcids":["https://orcid.org/0000-0001-8132-5613","https://orcid.org/0000-0001-8660-2376"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Yaodong","raw_affiliation_strings":["Chengdong Ma , Peking University , China,","Peking University , China,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chengdong Ma , Peking University , China,","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University , China,","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100445198","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0002-3526-9494","observed_orcids":["https://orcid.org/0000-0002-3526-9494"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":45,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9940999746322632,"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":0.9940999746322632,"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":0.005100000184029341,"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":9.999999747378752e-05,"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/self-play","display_name":"self-play","score":0.9919999837875366},{"id":"https://openalex.org/keywords/multi-agent-reinforcement-learning","display_name":"multi-agent reinforcement learning","score":0.9909999966621399},{"id":"https://openalex.org/keywords/noncooperative-games","display_name":"non-cooperative game","score":0.8870000243186951},{"id":"https://openalex.org/keywords/game-theory","display_name":"game theory","score":0.640999972820282},{"id":"https://openalex.org/keywords/game-agents","display_name":"game-playing agents","score":0.3959999978542328},{"id":"https://openalex.org/keywords/go","display_name":"Go","score":0.5239999890327454},{"id":"https://openalex.org/keywords/poker","display_name":"poker","score":0.9139999747276306},{"id":"https://openalex.org/keywords/video-games","display_name":"video games","score":0.9369999766349792}],"concepts":[{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6647810935974121},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5839551687240601},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.46270397305488586},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3742257356643677},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2357858121395111},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.18039441108703613}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2408.01072","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.01072","pdf_url":"https://arxiv.org/pdf/2408.01072","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2408.01072","doi":"https://doi.org/10.48550/arxiv.2408.01072","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2408.01072","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2408.01072","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.01072","pdf_url":"https://arxiv.org/pdf/2408.01072","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2045798616","display_name":null,"funder_award_id":"62325405","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5811851265","display_name":null,"funder_award_id":"62406159","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401978632.pdf","grobid_xml":"https://content.openalex.org/works/W4401978632.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1525285119","https://openalex.org/W1757796397","https://openalex.org/W2098111478","https://openalex.org/W2291986326","https://openalex.org/W2623431351","https://openalex.org/W2912660065","https://openalex.org/W2948263504","https://openalex.org/W2979533262","https://openalex.org/W2996037775","https://openalex.org/W3013828496","https://openalex.org/W3036927735","https://openalex.org/W3080474688","https://openalex.org/W3110282614","https://openalex.org/W3179152922","https://openalex.org/W3207318282","https://openalex.org/W4223908421","https://openalex.org/W4225481856","https://openalex.org/W4226303304","https://openalex.org/W4285597410","https://openalex.org/W4327810158","https://openalex.org/W4391047180","https://openalex.org/W4407185095","https://openalex.org/W4407309357","https://openalex.org/W4415020576","https://openalex.org/W4416013170","https://openalex.org/W7078689789"],"related_works":["https://openalex.org/W3179152922","https://openalex.org/W2977093897","https://openalex.org/W3033564068","https://openalex.org/W3107615218","https://openalex.org/W4205909924","https://openalex.org/W4416361403","https://openalex.org/W3085581910","https://openalex.org/W3000818637","https://openalex.org/W7130389591","https://openalex.org/W2991046523"],"abstract_inverted_index":{"Self-play,":[0],"a":[1,49,65,94],"learning":[2,40],"paradigm":[3],"where":[4],"agents":[5],"iteratively":[6],"refine":[7],"their":[8,115],"policies":[9],"by":[10,63,77,118],"interacting":[11],"with":[12],"historical":[13],"or":[14,19],"concurrent":[15],"versions":[16],"of":[17,54,72,122],"themselves":[18],"other":[20],"evolving":[21],"agents,":[22],"has":[23],"shown":[24],"remarkable":[25],"success":[26],"in":[27,37,124,138],"solving":[28],"complex":[29],"non-cooperative":[30,126],"multi-agent":[31,38],"tasks.":[32],"Despite":[33],"its":[34],"growing":[35],"prominence":[36],"reinforcement":[39],"(MARL),":[41],"such":[42],"as":[43],"Go,":[44],"poker,":[45],"and":[46,51,86,97,114,134],"video":[47],"games,":[48],"comprehensive":[50,66],"structured":[52],"understanding":[53],"self-play":[55,73,100,123],"remains":[56],"lacking.":[57],"This":[58],"survey":[59,130],"fills":[60],"this":[61,103],"gap":[62,110],"offering":[64],"roadmap":[67],"to":[68],"the":[69,79,83,106,109,112,120,129],"diverse":[70],"landscape":[71],"methods.":[74],"We":[75],"begin":[76],"introducing":[78],"necessary":[80],"preliminaries,":[81],"including":[82],"MARL":[84],"framework":[85,96],"basic":[87],"game":[88],"theory":[89],"concepts.":[90],"Then,":[91],"it":[92],"provides":[93],"unified":[95],"classifies":[98],"existing":[99],"algorithms":[101,113],"within":[102],"framework.":[104],"Moreover,":[105],"paper":[107],"bridges":[108],"between":[111],"practical":[116],"implications":[117],"illustrating":[119],"role":[121],"different":[125],"scenarios.":[127],"Finally,":[128],"highlights":[131],"open":[132],"challenges":[133],"future":[135],"research":[136],"directions":[137],"self-play.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":17},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":6},{"year":2020,"cited_by_count":1}],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2024-08-29T00:00:00"}