{"id":"https://openalex.org/W1947938122","doi":"https://doi.org/10.1109/cig.2015.7317910","title":"An improved approach to reinforcement learning in Computer Go","display_name":"An improved approach to reinforcement learning in Computer Go","publication_year":2015,"publication_date":"2015-08-01","ids":{"openalex":"https://openalex.org/W1947938122","doi":"https://doi.org/10.1109/cig.2015.7317910","mag":"1947938122"},"language":"en","primary_location":{"id":"doi:10.1109/cig.2015.7317910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cig.2015.7317910","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Conference on Computational Intelligence and Games (CIG)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/conference_contribution/An_improved_approach_to_reinforcement_learning_in_computer_go/27392481","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067907544","display_name":"Michael Dann","orcid":"https://orcid.org/0000-0002-7658-022X"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]},{"id":"https://openalex.org/I4210095297","display_name":"MIT University","ror":"https://ror.org/00v140q16","country_code":"MK","type":"education","lineage":["https://openalex.org/I4210095297"]}],"countries":["AU","MK"],"is_corresponding":true,"raw_author_name":"Michael Dann","raw_affiliation_strings":["School of Computer Science and Information Technology RMIT University, Melbourne","School of Computer Science and, Information Technology, RMIT University Melbourne, Victoria 3000"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Technology RMIT University, Melbourne","institution_ids":["https://openalex.org/I4210095297","https://openalex.org/I82951845"]},{"raw_affiliation_string":"School of Computer Science and, Information Technology, RMIT University Melbourne, Victoria 3000","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061528333","display_name":"Fabio Zambetta","orcid":"https://orcid.org/0000-0003-4133-7913"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]},{"id":"https://openalex.org/I4210095297","display_name":"MIT University","ror":"https://ror.org/00v140q16","country_code":"MK","type":"education","lineage":["https://openalex.org/I4210095297"]}],"countries":["AU","MK"],"is_corresponding":false,"raw_author_name":"Fabio Zambettau","raw_affiliation_strings":["RMIT University, Melbourne, VIC, AU","School of Computer Science and Information Technology | RMIT University"],"affiliations":[{"raw_affiliation_string":"RMIT University, Melbourne, VIC, AU","institution_ids":["https://openalex.org/I4210095297","https://openalex.org/I82951845"]},{"raw_affiliation_string":"School of Computer Science and Information Technology | RMIT University","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007500988","display_name":"John Thangarajah","orcid":"https://orcid.org/0000-0002-7699-6444"},"institutions":[{"id":"https://openalex.org/I4210095297","display_name":"MIT University","ror":"https://ror.org/00v140q16","country_code":"MK","type":"education","lineage":["https://openalex.org/I4210095297"]},{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU","MK"],"is_corresponding":false,"raw_author_name":"John Thangarajah","raw_affiliation_strings":["School of Computer Science and Information Technology RMIT University, Melbourne","School of Computer Science and Information Technology | RMIT University"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Technology RMIT University, Melbourne","institution_ids":["https://openalex.org/I4210095297","https://openalex.org/I82951845"]},{"raw_affiliation_string":"School of Computer Science and Information Technology | RMIT University","institution_ids":["https://openalex.org/I82951845"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5067907544"],"corresponding_institution_ids":["https://openalex.org/I4210095297","https://openalex.org/I82951845"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.04093734,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"8","issue":null,"first_page":"169","last_page":"176"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9925000071525574,"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/T11197","display_name":"Digital Games and Media","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.8396822214126587},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7808890342712402},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.726570188999176},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.57941734790802},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5375949740409851},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37861570715904236}],"concepts":[{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.8396822214126587},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7808890342712402},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.726570188999176},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.57941734790802},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5375949740409851},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37861570715904236},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/cig.2015.7317910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cig.2015.7317910","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Conference on Computational Intelligence and Games (CIG)","raw_type":"proceedings-article"},{"id":"pmh:oai:alma61RMIT.INST:11247884400001341","is_oa":false,"landing_page_url":"https://researchrepository.rmit.edu.au/esploro/outputs/conferenceProceeding/An-improved-approach-to-reinforcement-learning/9921862523401341","pdf_url":null,"source":{"id":"https://openalex.org/S4306402074","display_name":"RMIT Research Repository (RMIT University Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I82951845","host_organization_name":"RMIT University","host_organization_lineage":["https://openalex.org/I82951845"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:alma.61RMIT_INST:11247884400001341","is_oa":false,"landing_page_url":"http://doi.org/10.1109/CIG.2015.7317910","pdf_url":null,"source":{"id":"https://openalex.org/S4306402074","display_name":"RMIT Research Repository (RMIT University Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I82951845","host_organization_name":"RMIT University","host_organization_lineage":["https://openalex.org/I82951845"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:figshare.com:article/27392481","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/An_improved_approach_to_reinforcement_learning_in_computer_go/27392481","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/27392481","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/An_improved_approach_to_reinforcement_learning_in_computer_go/27392481","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1500868819","https://openalex.org/W1597864774","https://openalex.org/W1625390266","https://openalex.org/W1714211023","https://openalex.org/W1778554682","https://openalex.org/W1947291763","https://openalex.org/W1997840820","https://openalex.org/W2020135152","https://openalex.org/W2101101673","https://openalex.org/W2121863487","https://openalex.org/W2126316555","https://openalex.org/W2153678894","https://openalex.org/W2156361796","https://openalex.org/W2168405694","https://openalex.org/W2339749518","https://openalex.org/W2913764096","https://openalex.org/W2949501655","https://openalex.org/W4214717370","https://openalex.org/W6630013472","https://openalex.org/W6638026421","https://openalex.org/W6640581306","https://openalex.org/W6703964178"],"related_works":["https://openalex.org/W2571592646","https://openalex.org/W4247855592","https://openalex.org/W2567165815","https://openalex.org/W2740304877","https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2112583639","https://openalex.org/W2766259847","https://openalex.org/W3136325136"],"abstract_inverted_index":{"Monte-Carlo":[0,55],"Tree":[1],"Search":[2],"(MCTS)":[3],"has":[4],"revolutionized,":[5],"Computer":[6,84],"Go,":[7],"with":[8,57,63],"programs":[9],"based":[10],"on":[11,81],"the":[12,26,64,73,82,101,104,131],"algorithm,":[13],"achieving":[14],"a":[15,30,44,78,93],"level":[16],"of":[17,103,142],"play":[18],"that":[19,47,100],"previously":[20],"seemed":[21],"decades":[22],"away.,":[23],"However,":[24],"since":[25],"technique":[27],"involves":[28],"constructing":[29],"search":[31],"tree,":[32],"its":[33],"performance":[34,102],"tends":[35],"to":[36,49,116,137],"degrade":[37],"in":[38,133],"larger":[39],"state":[40,58],"spaces.":[41],"Dyna-2,":[42],"is":[43],"hybrid":[45],"approach":[46],"attempts":[48],"overcome":[50],"this":[51],"shortcoming,":[52],"by":[53,77,110],"combining":[54],"methods":[56],"abstraction.":[59],"While,":[60],"not":[61],"competitive":[62],"strongest":[65,120],"MCTS-based":[66],"programs,":[67],"the,":[68],"Dyna-2-based":[69],"program":[70,80,122],"RLGO":[71],"achieved":[72,123],"highest":[74],"ever":[75],"rating,":[76],"traditional":[79],"9\u00d79":[83],"Go":[85],"Server.":[86],"Plain,":[87],"Dyna-2":[88],"uses":[89],"_-greedy":[90],"exploration":[91],"and":[92],"flat":[94],"learning":[95],"rate,":[96],"but":[97],"we,":[98],"show":[99],"algorithm":[105],"can":[106],"be":[107],"significantly,":[108],"improved":[109],"making":[111],"some":[112],"relatively":[113],"minor":[114],"adjustments":[115],"this,":[117],"configuration.":[118],"Our":[119],"modified":[121],"an":[124,138],"Elo,":[125],"rating":[126],"289":[127],"points":[128],"higher":[129],"than":[130],"original":[132],"head-to-head":[134],"play,":[135],"equivalent":[136],"expected":[139],"win":[140],"rate":[141],"84%.":[143]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}