{"id":"https://openalex.org/W4293830054","doi":"https://doi.org/10.1142/s0219622022500547","title":"Analysis of Hyper-Parameters for AlphaZero-Like Deep Reinforcement Learning","display_name":"Analysis of Hyper-Parameters for AlphaZero-Like Deep Reinforcement Learning","publication_year":2022,"publication_date":"2022-08-19","ids":{"openalex":"https://openalex.org/W4293830054","doi":"https://doi.org/10.1142/s0219622022500547"},"language":"en","primary_location":{"id":"doi:10.1142/s0219622022500547","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219622022500547","pdf_url":null,"source":{"id":"https://openalex.org/S207089700","display_name":"International Journal of Information Technology & Decision Making","issn_l":"0219-6220","issn":["0219-6220","1793-6845"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Information Technology & Decision Making","raw_type":"journal-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/A5133339924","display_name":"Hui Wang","orcid":"https://orcid.org/0000-0003-1799-6273"},"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":true,"raw_author_name":"Hui Wang","raw_affiliation_strings":["Universiteit Leiden, Leiden Institute of Advanced Computer Science, Leiden, Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-1799-6273","affiliations":[{"raw_affiliation_string":"Universiteit Leiden, Leiden Institute of Advanced Computer Science, Leiden, 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":["Universiteit Leiden, Leiden Institute of Advanced Computer Science, Leiden, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universiteit Leiden, Leiden Institute of Advanced Computer Science, Leiden, 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":["Universiteit Leiden, Leiden Institute of Advanced Computer Science, Leiden, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universiteit Leiden, Leiden Institute of Advanced Computer Science, Leiden, 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":["Universiteit Leiden, Leiden Institute of Advanced Computer Science, Leiden, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universiteit Leiden, Leiden Institute of Advanced Computer Science, Leiden, Netherlands","institution_ids":["https://openalex.org/I121797337"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5133339924"],"corresponding_institution_ids":["https://openalex.org/I121797337"],"apc_list":null,"apc_paid":null,"fwci":0.971,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.79780166,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"22","issue":"02","first_page":"829","last_page":"853"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9965000152587891,"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":0.9965000152587891,"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":0.9940999746322632,"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/T11674","display_name":"Sports Analytics and Performance","score":0.9930999875068665,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8184117674827576},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.7717225551605225},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7130725383758545},{"id":"https://openalex.org/keywords/parameter-space","display_name":"Parameter space","score":0.6114304661750793},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6048958897590637},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5914540886878967},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5869737863540649},{"id":"https://openalex.org/keywords/inner-loop","display_name":"Inner loop","score":0.5842475295066833},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5433285236358643},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.5104398131370544},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4885595738887787},{"id":"https://openalex.org/keywords/loop","display_name":"Loop (graph theory)","score":0.4629669189453125},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.45026683807373047},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18874138593673706},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.14214301109313965}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8184117674827576},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.7717225551605225},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7130725383758545},{"id":"https://openalex.org/C73586568","wikidata":"https://www.wikidata.org/wiki/Q2600211","display_name":"Parameter space","level":2,"score":0.6114304661750793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6048958897590637},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5914540886878967},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5869737863540649},{"id":"https://openalex.org/C58716799","wikidata":"https://www.wikidata.org/wiki/Q6035648","display_name":"Inner loop","level":3,"score":0.5842475295066833},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5433285236358643},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.5104398131370544},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4885595738887787},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.4629669189453125},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.45026683807373047},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18874138593673706},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14214301109313965},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1142/s0219622022500547","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219622022500547","pdf_url":null,"source":{"id":"https://openalex.org/S207089700","display_name":"International Journal of Information Technology & Decision Making","issn_l":"0219-6220","issn":["0219-6220","1793-6845"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Information Technology & Decision Making","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:wsi:ijitdm:v:22:y:2023:i:02:n:s0219622022500547","is_oa":false,"landing_page_url":"http://www.worldscientific.com/doi/abs/10.1142/S0219622022500547","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"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":"article"},{"id":"pmh:oai:scholarlypublications.universiteitleiden.nl:item_3502407","is_oa":false,"landing_page_url":"https://hdl.handle.net/1887/3502407","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":"International Journal of Information Technology & Decision Making","raw_type":"Article / Letter to editor"},{"id":"pmh:ul:oai:scholarlypublications.universiteitleiden.nl:item_3502407","is_oa":false,"landing_page_url":"http://hdl.handle.net/1887/3502407","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Journal of Information Technology & Decision Making. WORLD SCIENTIFIC PUBL CO PTE LTD","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W60686164","https://openalex.org/W1587022413","https://openalex.org/W2076063813","https://openalex.org/W2088043394","https://openalex.org/W2092667854","https://openalex.org/W2103196307","https://openalex.org/W2126316555","https://openalex.org/W2131600418","https://openalex.org/W2133067606","https://openalex.org/W2257979135","https://openalex.org/W2316978694","https://openalex.org/W2734806994","https://openalex.org/W2766447205","https://openalex.org/W2787567977","https://openalex.org/W2807637204","https://openalex.org/W2902907165","https://openalex.org/W2913340405","https://openalex.org/W2921830693","https://openalex.org/W2990211277","https://openalex.org/W3000642679","https://openalex.org/W3006868496","https://openalex.org/W3096808766","https://openalex.org/W4212900945"],"related_works":["https://openalex.org/W4293159346","https://openalex.org/W154155438","https://openalex.org/W2087746955","https://openalex.org/W2353268890","https://openalex.org/W3084132679","https://openalex.org/W3136325136","https://openalex.org/W2078202596","https://openalex.org/W2261448047","https://openalex.org/W2482256034","https://openalex.org/W2982633646"],"abstract_inverted_index":{"The":[0,39,153],"landmark":[1],"achievements":[2],"of":[3,63,127,141,156,164,184,190],"AlphaGo":[4],"Zero":[5],"have":[6],"created":[7],"great":[8],"research":[9,51],"interest":[10],"into":[11],"self-play":[12,83,128,157],"in":[13,36,80,151,162],"reinforcement":[14],"learning.":[15],"In":[16,73],"self-play,":[17],"Monte":[18],"Carlo":[19],"Tree":[20],"Search":[21],"(MCTS)":[22],"is":[23,32,41,123],"used":[24,34],"to":[25,68,91,101,117,178],"train":[26],"a":[27,139],"deep":[28],"neural":[29],"network,":[30],"which":[31,194],"then":[33],"itself":[35],"tree":[37],"searches.":[38],"training":[40,113,136],"governed":[42],"by":[43],"many":[44],"hyper-parameters.":[45],"There":[46],"has":[47],"been":[48],"surprisingly":[49],"little":[50],"on":[52,147],"design":[53],"choices":[54],"for":[55,171,193],"hyper-parameter":[56,149],"values":[57,150],"and":[58,85,135],"loss":[59],"functions,":[60],"presumably":[61],"because":[62],"the":[64,70,125,165,172,188],"prohibitive":[65],"computational":[66],"cost":[67],"explore":[69],"parameter":[71],"space.":[72],"this":[74],"paper,":[75],"we":[76,96,106,144,195],"investigate":[77],"12":[78],"hyper-parameters":[79,100,170],"an":[81],"AlphaZero-like":[82],"algorithm":[84],"evaluate":[86],"how":[87],"these":[88],"parameters":[89],"contribute":[90],"training.":[92],"Through":[93],"multi-objective":[94],"analysis,":[95],"identify":[97],"four":[98],"important":[99],"further":[102],"assess.":[103],"To":[104],"start,":[105],"find":[107],"surprising":[108],"results":[109],"where":[110],"too":[111],"much":[112],"can":[114],"sometimes":[115],"lead":[116],"lower":[118,179],"performance.":[119],"Our":[120],"main":[121],"result":[122,183],"that":[124],"number":[126],"iterations":[129,158],"subsumes":[130],"MCTS-search":[131],"simulations,":[132],"game":[133],"episodes":[134],"epochs.":[137],"As":[138],"consequence":[140],"our":[142,185],"experiments,":[143],"provide":[145,197],"recommendations":[146],"setting":[148],"self-play.":[152],"outer":[154],"loop":[155],"should":[159,175],"be":[160,176],"emphasized,":[161],"favor":[163],"inner":[166,173],"loop.":[167],"This":[168],"means":[169],"loop,":[174],"set":[177],"values.":[180],"A":[181],"secondary":[182],"experiments":[186],"concerns":[187],"choice":[189],"optimization":[191],"goals,":[192],"also":[196],"recommendations.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}