{"id":"https://openalex.org/W3006868496","doi":"https://doi.org/10.1109/ssci44817.2019.9002814","title":"Alternative Loss Functions in AlphaZero-like Self-play","display_name":"Alternative Loss Functions in AlphaZero-like Self-play","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3006868496","doi":"https://doi.org/10.1109/ssci44817.2019.9002814","mag":"3006868496"},"language":"en","primary_location":{"id":"doi:10.1109/ssci44817.2019.9002814","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci44817.2019.9002814","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Symposium Series on Computational Intelligence (SSCI)","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/A5018832096","display_name":"Hui Wang","orcid":"https://orcid.org/0000-0001-5074-900X"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Hui Wang","raw_affiliation_strings":["Leiden Institute of Advanced Computer Science, Leiden University, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leiden Institute of Advanced Computer Science, Leiden University, The Netherlands","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007378438","display_name":"Michael Emmerich","orcid":"https://orcid.org/0000-0002-7342-2090"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Michael Emmerich","raw_affiliation_strings":["Leiden Institute of Advanced Computer Science, Leiden University, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leiden Institute of Advanced Computer Science, Leiden University, The Netherlands","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062774048","display_name":"Mike Preu\u00df","orcid":"https://orcid.org/0000-0003-4681-1346"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Mike Preuss","raw_affiliation_strings":["Leiden Institute of Advanced Computer Science, Leiden University, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leiden Institute of Advanced Computer Science, Leiden University, The Netherlands","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085542421","display_name":"Aske Plaat","orcid":"https://orcid.org/0000-0001-7202-3322"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Aske Plaat","raw_affiliation_strings":["Leiden Institute of Advanced Computer Science, Leiden University, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leiden Institute of Advanced Computer Science, Leiden University, The Netherlands","institution_ids":["https://openalex.org/I121797337"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.771,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.9673296,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"518","issue":null,"first_page":"155","last_page":"162"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11674","display_name":"Sports Analytics and Performance","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11674","display_name":"Sports Analytics and Performance","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9991000294685364,"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/T10731","display_name":"Educational Games and Gamification","score":0.9922999739646912,"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":0.7609779834747314},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.6035766005516052},{"id":"https://openalex.org/keywords/tournament","display_name":"Tournament","score":0.5921883583068848},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5649736523628235},{"id":"https://openalex.org/keywords/competition","display_name":"Competition (biology)","score":0.5372277498245239},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.5244698524475098},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48431292176246643},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45648854970932007},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.4500999450683594},{"id":"https://openalex.org/keywords/loss-aversion","display_name":"Loss aversion","score":0.41591113805770874},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39637207984924316},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.325687050819397},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.30356669425964355},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.14876285195350647},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1327170431613922},{"id":"https://openalex.org/keywords/microeconomics","display_name":"Microeconomics","score":0.12023034691810608},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.08530893921852112}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7609779834747314},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.6035766005516052},{"id":"https://openalex.org/C136975688","wikidata":"https://www.wikidata.org/wiki/Q1320634","display_name":"Tournament","level":2,"score":0.5921883583068848},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5649736523628235},{"id":"https://openalex.org/C91306197","wikidata":"https://www.wikidata.org/wiki/Q45767","display_name":"Competition (biology)","level":2,"score":0.5372277498245239},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.5244698524475098},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48431292176246643},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45648854970932007},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.4500999450683594},{"id":"https://openalex.org/C2778174566","wikidata":"https://www.wikidata.org/wiki/Q2874240","display_name":"Loss aversion","level":2,"score":0.41591113805770874},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39637207984924316},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.325687050819397},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.30356669425964355},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14876285195350647},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1327170431613922},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.12023034691810608},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.08530893921852112},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ssci44817.2019.9002814","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci44817.2019.9002814","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarlypublications.universiteitleiden.nl:item_3665598","is_oa":false,"landing_page_url":"https://hdl.handle.net/1887/3665598","pdf_url":null,"source":{"id":"https://openalex.org/S4306400850","display_name":"Leiden Repository (Leiden University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I121797337","host_organization_name":"Leiden University","host_organization_lineage":["https://openalex.org/I121797337"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2019 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"Article in monograph or in proceedings"},{"id":"mag:3042729524","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=202002241279121471","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","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":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.47999998927116394,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G7895041135","display_name":null,"funder_award_id":"201706990015","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"}],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W17749007","https://openalex.org/W1522301498","https://openalex.org/W1587022413","https://openalex.org/W1836465849","https://openalex.org/W1999319334","https://openalex.org/W2088043394","https://openalex.org/W2095705004","https://openalex.org/W2103196307","https://openalex.org/W2106953752","https://openalex.org/W2126316555","https://openalex.org/W2132994929","https://openalex.org/W2133067606","https://openalex.org/W2134264591","https://openalex.org/W2145339207","https://openalex.org/W2257979135","https://openalex.org/W2296073425","https://openalex.org/W2571592646","https://openalex.org/W2747592475","https://openalex.org/W2766447205","https://openalex.org/W2787567977","https://openalex.org/W2807637204","https://openalex.org/W2902907165","https://openalex.org/W2907738974","https://openalex.org/W2907796507","https://openalex.org/W2913340405","https://openalex.org/W2921487450","https://openalex.org/W2921830693","https://openalex.org/W2964121744","https://openalex.org/W2977978457","https://openalex.org/W4247855592","https://openalex.org/W4298857966","https://openalex.org/W6637967152","https://openalex.org/W6638667902","https://openalex.org/W6674330103","https://openalex.org/W6676297359","https://openalex.org/W6680105153","https://openalex.org/W6754807315","https://openalex.org/W6760258457","https://openalex.org/W6760347889"],"related_works":["https://openalex.org/W3123786980","https://openalex.org/W2994965880","https://openalex.org/W4287997709","https://openalex.org/W3083287393","https://openalex.org/W3094108612","https://openalex.org/W3125314910","https://openalex.org/W2982074041","https://openalex.org/W2130950591","https://openalex.org/W2041858633","https://openalex.org/W3122959053"],"abstract_inverted_index":{"Recently,":[0],"AlphaZero":[1,14],"has":[2,39],"achieved":[3],"outstanding":[4],"performance":[5,125,159],"in":[6,13,173,201,226],"playing":[7,171,199],"Go,":[8],"Chess,":[9],"and":[10,24,42,45,56,65,100,223],"Shogi.":[11],"Players":[12],"consist":[15],"of":[16,19,53,71,84,220],"a":[17,25,40,43,135,155,174],"combination":[18],"Monte":[20],"Carlo":[21],"Tree":[22],"Search":[23],"deep":[26,36],"neural":[27,37],"network,":[28],"that":[29,118,140,211],"is":[30,61,134,142,166,214],"trained":[31],"using":[32],"self-play.":[33],"The":[34,115],"unified":[35],"network":[38],"policy-head":[41],"value-head,":[44],"during":[46],"training,":[47],"the":[48,51,72,102,123,151,170,178,197,202,217],"optimizer":[49],"minimizes":[50],"sum":[52],"policy":[54,224],"loss":[55,73,195],"value":[57,194,221],"loss.":[58],"However,":[59],"it":[60,141],"not":[62],"clear":[63],"if":[64],"under":[66],"which":[67],"circumstances":[68],"other":[69],"formulations":[70],"function":[74,222,225],"are":[75],"better.":[76],"Therefore,":[77,148],"we":[78,109],"perform":[79],"experiments":[80,99],"with":[81],"different":[82,145],"combinations":[83],"these":[85],"two":[86],"minimization":[87],"targets.":[88],"In":[89],"contrast":[90],"to":[91,111,168],"many":[92],"recent":[93],"papers":[94],"who":[95],"adopt":[96],"single":[97],"run":[98],"use":[101,112],"whole":[103],"history":[104],"Elo":[105,164],"ratings":[106],"from":[107],"self-play,":[108],"propose":[110],"repeated":[113],"runs.":[114,147],"results":[116,209],"show":[117],"this":[119,187],"method":[120],"can":[121],"describe":[122],"training":[124,130,146],"quite":[126],"well":[127],"within":[128],"each":[129],"run,":[131],"but":[132],"there":[133],"high":[136],"self-play":[137,156],"bias,":[138],"such":[139],"incomparable":[143],"among":[144],"inspired":[149],"by":[150],"AlphaGo":[152],"series":[153],"papers,":[154],"bias":[157],"avoiding":[158],"assessment,":[160],"final":[161,203],"best":[162,204],"player":[163],"rating,":[165],"adopted":[167],"evaluate":[169],"strength":[172,200],"direct":[175],"competition":[176],"between":[177],"evolved":[179],"players.":[180],"For":[181],"relatively":[182],"small":[183,227],"games,":[184],"based":[185],"on":[186],"new":[188],"evaluation":[189],"method,":[190],"surprisingly,":[191],"minimizing":[192],"only":[193],"achieves":[196],"strongest":[198],"players'":[205],"round-robin":[206],"tournament.":[207],"These":[208],"indicate":[210],"more":[212],"research":[213],"needed":[215],"into":[216],"relative":[218],"importance":[219],"games.":[228]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}