{"id":"https://openalex.org/W2020135152","doi":"https://doi.org/10.1145/1273496.1273531","title":"Combining online and offline knowledge in UCT","display_name":"Combining online and offline knowledge in UCT","publication_year":2007,"publication_date":"2007-06-20","ids":{"openalex":"https://openalex.org/W2020135152","doi":"https://doi.org/10.1145/1273496.1273531","mag":"2020135152"},"language":"en","primary_location":{"id":"doi:10.1145/1273496.1273531","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1273496.1273531","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th international conference on Machine learning","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/inria-00164003","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041958651","display_name":"Sylvain Gelly","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sylvain Gelly","raw_affiliation_strings":["Univ. Paris Sud, INRIA, France","Univ. Paris Sud, INRIA, France#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. Paris Sud, INRIA, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"Univ. Paris Sud, INRIA, France#TAB#","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091771290","display_name":"David Silver","orcid":"https://orcid.org/0000-0002-5197-2892"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"David Silver","raw_affiliation_strings":["University of Alberta, Edmonton, Alberta","University of Alberta. Edmonton. Alberta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, Alberta","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"University of Alberta. Edmonton. Alberta","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":458,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"273","last_page":"280"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9987000226974487,"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":0.9954000115394592,"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/computer-science","display_name":"Computer science","score":0.73316890001297},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5851418972015381},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5800407528877258},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5204946398735046},{"id":"https://openalex.org/keywords/online-and-offline","display_name":"Online and offline","score":0.5129215717315674},{"id":"https://openalex.org/keywords/offline-learning","display_name":"Offline learning","score":0.5111647248268127},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.49618014693260193},{"id":"https://openalex.org/keywords/online-algorithm","display_name":"Online algorithm","score":0.4851570725440979},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48270106315612793},{"id":"https://openalex.org/keywords/value-network","display_name":"Value network","score":0.46662437915802},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.43369942903518677},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41447386145591736},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3662859797477722},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.34643810987472534},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.3247048854827881},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17649269104003906},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0947689414024353}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.73316890001297},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5851418972015381},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5800407528877258},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5204946398735046},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.5129215717315674},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.5111647248268127},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.49618014693260193},{"id":"https://openalex.org/C196921405","wikidata":"https://www.wikidata.org/wiki/Q786431","display_name":"Online algorithm","level":2,"score":0.4851570725440979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48270106315612793},{"id":"https://openalex.org/C89249532","wikidata":"https://www.wikidata.org/wiki/Q7912758","display_name":"Value network","level":3,"score":0.46662437915802},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.43369942903518677},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41447386145591736},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3662859797477722},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.34643810987472534},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.3247048854827881},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17649269104003906},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0947689414024353},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C4216890","wikidata":"https://www.wikidata.org/wiki/Q815823","display_name":"Business model","level":2,"score":0.0},{"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/1273496.1273531","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1273496.1273531","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th international conference on Machine learning","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.75.3544","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.75.3544","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://imls.engr.oregonstate.edu/www/htdocs/proceedings/icml2007/papers/387.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.86.5248","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.86.5248","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.ualberta.ca/~silver/research/publications/files/combining_uct.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:inria-00164003v1","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00164003","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Conference of Machine Learning, Jun 2007, Corvallis, United States","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:1347376","is_oa":false,"landing_page_url":"http://discovery.ucl.ac.uk/1347376/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"In: (pp. pp. 273-280). (2007)","raw_type":"Proceedings paper"}],"best_oa_location":{"id":"pmh:oai:HAL:inria-00164003v1","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00164003","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Conference of Machine Learning, Jun 2007, Corvallis, United States","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W103174825","https://openalex.org/W182596629","https://openalex.org/W1491843047","https://openalex.org/W1515851193","https://openalex.org/W1563895031","https://openalex.org/W1625390266","https://openalex.org/W1714211023","https://openalex.org/W1778554682","https://openalex.org/W1888434271","https://openalex.org/W2100677568","https://openalex.org/W2121863487","https://openalex.org/W2124175081","https://openalex.org/W2156361796","https://openalex.org/W2159920598","https://openalex.org/W2168405694","https://openalex.org/W4214717370","https://openalex.org/W4285719527","https://openalex.org/W6638026421","https://openalex.org/W6677916085"],"related_works":["https://openalex.org/W3042122676","https://openalex.org/W4221145086","https://openalex.org/W4226221094","https://openalex.org/W4387293922","https://openalex.org/W4225619808","https://openalex.org/W4388482290","https://openalex.org/W4388872820","https://openalex.org/W4220668416","https://openalex.org/W4318719276","https://openalex.org/W92125585"],"abstract_inverted_index":{"The":[0,11,95,118,124],"UCT":[1,37,55,80,101,111,122,128],"algorithm":[2,13,97,120,126],"learns":[3],"a":[4,16,47,61,103,113],"value":[5,17,33,42,56,71],"function":[6,18,43,57,72],"online":[7,32,63],"using":[8],"sample-based":[9],"search.":[10],"TD(\u03bb)":[12],"can":[14],"learn":[15],"offline":[19,30,41,70],"for":[20,28],"the":[21,36,40,54,69,79,139],"on-policy":[22],"distribution.":[23],"We":[24,83,133],"consider":[25],"three":[26],"approaches":[27],"combining":[29],"and":[31],"functions":[34],"in":[35,78,87,137],"algorithm.":[38],"First,":[39],"is":[44,58,73],"used":[45,74],"as":[46,75],"default":[48],"policy":[49],"during":[50],"Monte-Carlo":[51],"simulation.":[52],"Second,":[53],"combined":[59],"with":[60,102,112,129],"rapid":[62],"estimate":[64],"of":[65],"action":[66],"values.":[67],"Third,":[68],"prior":[76,131],"knowledge":[77],"search":[81],"tree.":[82],"evaluate":[84],"these":[85,135],"algorithms":[86,136],"9":[88,90,142,144],"x":[89,143],"Go":[91,145],"against":[92],"GnuGo":[93],"3.7.10.":[94],"first":[96],"performs":[98],"better":[99],"than":[100,110],"random":[104],"simulation":[105,116],"policy,":[106],"but":[107],"surprisingly,":[108],"worse":[109],"weaker,":[114],"handcrafted":[115,130],"policy.":[117],"second":[119],"outperforms":[121,127],"altogether.":[123],"third":[125],"knowledge.":[132],"combine":[134],"MoGo,":[138],"world's":[140],"strongest":[141],"program.":[146],"Each":[147],"technique":[148],"significantly":[149],"improves":[150],"MoGo's":[151],"playing":[152],"strength.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":24},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":30},{"year":2017,"cited_by_count":21},{"year":2016,"cited_by_count":28},{"year":2015,"cited_by_count":24},{"year":2014,"cited_by_count":32},{"year":2013,"cited_by_count":31},{"year":2012,"cited_by_count":41}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}