{"id":"https://openalex.org/W3170943554","doi":"https://doi.org/10.1007/s00521-021-05928-5","title":"Value targets in off-policy AlphaZero: a new greedy backup","display_name":"Value targets in off-policy AlphaZero: a new greedy backup","publication_year":2021,"publication_date":"2021-06-16","ids":{"openalex":"https://openalex.org/W3170943554","doi":"https://doi.org/10.1007/s00521-021-05928-5","mag":"3170943554"},"language":"en","primary_location":{"id":"doi:10.1007/s00521-021-05928-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-021-05928-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-021-05928-5.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://link.springer.com/content/pdf/10.1007/s00521-021-05928-5.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065810966","display_name":"Dani\u00ebl Willemsen","orcid":"https://orcid.org/0000-0003-3943-5805"},"institutions":[{"id":"https://openalex.org/I1341640284","display_name":"Centrum Wiskunde & Informatica","ror":"https://ror.org/00x7ekv49","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1341640284","https://openalex.org/I2800991832"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Daniel Willemsen","raw_affiliation_strings":["Centrum Wiskunde en Informatica, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"Centrum Wiskunde en Informatica, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I1341640284"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065056119","display_name":"Hendrik Baier","orcid":"https://orcid.org/0000-0002-7211-8070"},"institutions":[{"id":"https://openalex.org/I1341640284","display_name":"Centrum Wiskunde & Informatica","ror":"https://ror.org/00x7ekv49","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1341640284","https://openalex.org/I2800991832"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Hendrik Baier","raw_affiliation_strings":["Centrum Wiskunde en Informatica, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"Centrum Wiskunde en Informatica, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I1341640284"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069752991","display_name":"Michael Kaisers","orcid":null},"institutions":[{"id":"https://openalex.org/I1341640284","display_name":"Centrum Wiskunde & Informatica","ror":"https://ror.org/00x7ekv49","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1341640284","https://openalex.org/I2800991832"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Michael Kaisers","raw_affiliation_strings":["Centrum Wiskunde en Informatica, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"Centrum Wiskunde en Informatica, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I1341640284"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5065810966"],"corresponding_institution_ids":["https://openalex.org/I1341640284"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":1.1185,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.82017349,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"34","issue":"3","first_page":"1801","last_page":"1814"},"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":0.9940999746322632,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9851999878883362,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7872228026390076},{"id":"https://openalex.org/keywords/backup","display_name":"Backup","score":0.7414610385894775},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7279520034790039},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6699068546295166},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5363956689834595},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.517305850982666},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.48233768343925476},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4811619222164154},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.480197548866272},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.4695007801055908},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.46262550354003906},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.45170390605926514},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4370286464691162},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4358299970626831},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3025156259536743},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.3001464605331421},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12844079732894897},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.07445350289344788}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7872228026390076},{"id":"https://openalex.org/C2780945871","wikidata":"https://www.wikidata.org/wiki/Q194274","display_name":"Backup","level":2,"score":0.7414610385894775},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7279520034790039},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6699068546295166},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5363956689834595},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.517305850982666},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.48233768343925476},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4811619222164154},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.480197548866272},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.4695007801055908},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.46262550354003906},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.45170390605926514},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4370286464691162},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4358299970626831},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3025156259536743},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.3001464605331421},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12844079732894897},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.07445350289344788},{"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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1007/s00521-021-05928-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-021-05928-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-021-05928-5.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},{"id":"pmh:oai:pure.tue.nl:openaire/1fd12741-af52-43ae-9e7e-04be9ee50fce","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/1fd12741-af52-43ae-9e7e-04be9ee50fce","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Willemsen, D, Baier, H & Kaisers, M 2022, 'Value targets in off-policy AlphaZero : A new greedy backup', Neural Computing and Applications, vol. 34, no. 3, pp. 1801-1814. https://doi.org/10.1007/S00521-021-05928-5","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:cwi.nl:30870","is_oa":true,"landing_page_url":"https://ir.cwi.nl/pub/30870","pdf_url":"https://ir.cwi.nl/pub/30870/30870.pdf","source":{"id":"https://openalex.org/S7407055335","display_name":"Centrum Wiskunde & Informatica (CWI), the national research institute for mathematics and computer science in the Netherlands","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Neural Computing and Applications vol. 34, pp. 1801-1814","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pure.tue.nl:publications/1fd12741-af52-43ae-9e7e-04be9ee50fce","is_oa":true,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=85108151407&partnerID=8YFLogxK","pdf_url":"https://pure.tue.nl/ws/files/217685150/s00521_021_05928_5.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Willemsen, D, Baier, H & Kaisers, M 2022, 'Value targets in off-policy AlphaZero : A new greedy backup', Neural Computing and Applications, vol. 34, no. 3, pp. 1801-1814. https://doi.org/10.1007/S00521-021-05928-5","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:tue:oai:pure.tue.nl:publications/1fd12741-af52-43ae-9e7e-04be9ee50fce","is_oa":true,"landing_page_url":"https://research.tue.nl/nl/publications/1fd12741-af52-43ae-9e7e-04be9ee50fce","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Neural Computing and Applications, 34(3), 1801 - 1814. Springer","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1007/s00521-021-05928-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-021-05928-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-021-05928-5.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G433653202","display_name":null,"funder_award_id":"TEUE117015","funder_id":"https://openalex.org/F4320314237","funder_display_name":"Rijksdienst voor Ondernemend Nederland"}],"funders":[{"id":"https://openalex.org/F4320314237","display_name":"Rijksdienst voor Ondernemend Nederland","ror":null},{"id":"https://openalex.org/F4320338229","display_name":"TKI Urban Energy","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3170943554.pdf","grobid_xml":"https://content.openalex.org/works/W3170943554.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W161513061","https://openalex.org/W1515851193","https://openalex.org/W1548403904","https://openalex.org/W1625390266","https://openalex.org/W1636614024","https://openalex.org/W1714211023","https://openalex.org/W1757796397","https://openalex.org/W2114735315","https://openalex.org/W2115211925","https://openalex.org/W2126316555","https://openalex.org/W2138076661","https://openalex.org/W2173248099","https://openalex.org/W2257979135","https://openalex.org/W2618097077","https://openalex.org/W2766447205","https://openalex.org/W2803928381","https://openalex.org/W2911296969","https://openalex.org/W2953722837","https://openalex.org/W2963938771","https://openalex.org/W2965560556","https://openalex.org/W2989847975","https://openalex.org/W2994486527","https://openalex.org/W3118210634","https://openalex.org/W3170943554","https://openalex.org/W6608490358"],"related_works":["https://openalex.org/W2955195711","https://openalex.org/W2354454611","https://openalex.org/W2993266126","https://openalex.org/W2392283887","https://openalex.org/W2351388597","https://openalex.org/W2939925694","https://openalex.org/W2829881200","https://openalex.org/W2184647741","https://openalex.org/W1974217798","https://openalex.org/W137535787"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
