{"id":"https://openalex.org/W4297838124","doi":"https://doi.org/10.14428/esann/2022.es2022-53","title":"Size Scaling in Self-Play Reinforcement Learning","display_name":"Size Scaling in Self-Play Reinforcement Learning","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4297838124","doi":"https://doi.org/10.14428/esann/2022.es2022-53"},"language":"en","primary_location":{"id":"doi:10.14428/esann/2022.es2022-53","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2022.es2022-53","pdf_url":"https://doi.org/10.14428/esann/2022.es2022-53","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2022 proceedings","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.14428/esann/2022.es2022-53","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008822433","display_name":"Oren Neumann","orcid":null},"institutions":[{"id":"https://openalex.org/I114090438","display_name":"Goethe University Frankfurt","ror":"https://ror.org/04cvxnb49","country_code":"DE","type":"education","lineage":["https://openalex.org/I114090438"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Oren Neumann","raw_affiliation_strings":["Institute for Theoretical Physics Goethe University Frankfurt Frankfurt am Main, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Theoretical Physics Goethe University Frankfurt Frankfurt am Main, Germany","institution_ids":["https://openalex.org/I114090438"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041243848","display_name":"Claudius Gros","orcid":"https://orcid.org/0000-0002-2126-0843"},"institutions":[{"id":"https://openalex.org/I114090438","display_name":"Goethe University Frankfurt","ror":"https://ror.org/04cvxnb49","country_code":"DE","type":"education","lineage":["https://openalex.org/I114090438"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Claudius Gros","raw_affiliation_strings":["Institute for Theoretical Physics Goethe University Frankfurt Frankfurt am Main, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Theoretical Physics Goethe University Frankfurt Frankfurt am Main, Germany","institution_ids":["https://openalex.org/I114090438"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114090438"],"apc_list":null,"apc_paid":null,"fwci":0.3796,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55044042,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"521","last_page":"526"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12659","display_name":"Innovation Diffusion and Forecasting","score":0.42239999771118164,"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"}},"topics":[{"id":"https://openalex.org/T12659","display_name":"Innovation Diffusion and Forecasting","score":0.42239999771118164,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7841261625289917},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6813693046569824},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.6387423872947693},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.47967052459716797},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3377259373664856},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14849799871444702},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09831079840660095},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.07115527987480164}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7841261625289917},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6813693046569824},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.6387423872947693},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.47967052459716797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3377259373664856},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14849799871444702},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09831079840660095},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.07115527987480164},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14428/esann/2022.es2022-53","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2022.es2022-53","pdf_url":"https://doi.org/10.14428/esann/2022.es2022-53","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2022 proceedings","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.14428/esann/2022.es2022-53","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2022.es2022-53","pdf_url":"https://doi.org/10.14428/esann/2022.es2022-53","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2022 proceedings","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4297838124.pdf","grobid_xml":"https://content.openalex.org/works/W4297838124.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W1500868819","https://openalex.org/W2902907165","https://openalex.org/W2914704832","https://openalex.org/W2921487450","https://openalex.org/W2969287672","https://openalex.org/W3001279689","https://openalex.org/W3125418453","https://openalex.org/W3138994021","https://openalex.org/W4225591000","https://openalex.org/W4300963239"],"related_works":["https://openalex.org/W1562959674","https://openalex.org/W2923653485","https://openalex.org/W2957776456","https://openalex.org/W4361026739","https://openalex.org/W2952472710","https://openalex.org/W4255994452","https://openalex.org/W4372194388","https://openalex.org/W4206669594","https://openalex.org/W3005560120","https://openalex.org/W3037422413"],"abstract_inverted_index":{"Performance":[0],"scaling":[1,21],"laws":[2],"with":[3,28,57],"resources":[4],"are":[5],"heavily":[6],"studied":[7],"in":[8,15,48],"supervised":[9],"deep":[10],"learning":[11],"models":[12],"but":[13],"not":[14],"reinforcement":[16],"learning.":[17],"We":[18,44],"examine":[19],"the":[20,23,49,52,58,83,91],"of":[22,51,60,93],"AlphaZero":[24],"[1]":[25],"algorithm's":[26],"performance":[27],"model":[29],"size":[30],"by":[31,100],"training":[32],"agents":[33],"on":[34,90],"three":[35],"competitive":[36],"two-player":[37],"games,":[38],"Connect":[39],"Four,":[40],"Oware":[41],"and":[42,70],"Pentago.":[43],"find":[45],"that":[46],"performance,":[47],"form":[50],"Elo":[53],"rating,":[54],"scales":[55],"logarithmically":[56],"number":[59],"free":[61],"neural":[62,74],"network":[63],"parameters,":[64],"a":[65,79],"trend":[66],"consistent":[67],"across":[68],"games":[69],"when":[71],"using":[72],"deeper":[73],"networks.":[75],"This":[76],"leads":[77],"to":[78],"universal":[80],"expression":[81],"for":[82],"average":[84],"match":[85],"outcome":[86],"which":[87,97],"depends":[88],"only":[89],"ratio":[92],"sizes":[94],"between":[95],"opponents,":[96],"is":[98],"supported":[99],"an":[101],"agnostic":[102],"rating":[103],"method.":[104]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}