{"id":"https://openalex.org/W7083307985","doi":"https://doi.org/10.1016/j.neucom.2025.131581","title":"Towards unbiased action value estimation in reinforcement learning","display_name":"Towards unbiased action value estimation in reinforcement learning","publication_year":2025,"publication_date":"2025-09-22","ids":{"openalex":"https://openalex.org/W7083307985","doi":"https://doi.org/10.1016/j.neucom.2025.131581"},"language":"en","primary_location":{"id":"doi:10.1016/j.neucom.2025.131581","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neucom.2025.131581","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.neucom.2025.131581","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yuan Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Yuan Xue","raw_affiliation_strings":["L3S Research Centre, Appelstra\u00dfe 9A, Hanover, 30167, Lowersaxony, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L3S Research Centre, Appelstra\u00dfe 9A, Hanover, 30167, Lowersaxony, Germany","institution_ids":["https://openalex.org/I4210136150"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Daniel Kudenko","orcid":"https://orcid.org/0000-0003-3359-3255"},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel Kudenko","raw_affiliation_strings":["L3S Research Centre, Appelstra\u00dfe 9A, Hanover, 30167, Lowersaxony, Germany"],"raw_orcid":"https://orcid.org/0000-0003-3359-3255","affiliations":[{"raw_affiliation_string":"L3S Research Centre, Appelstra\u00dfe 9A, Hanover, 30167, Lowersaxony, Germany","institution_ids":["https://openalex.org/I4210136150"]}]},{"author_position":"last","author":{"id":null,"display_name":"Megha Khosla","orcid":null},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Megha Khosla","raw_affiliation_strings":["Multimedia Computing Group in the Intelligent Systems Department Delft University of Technology, Van Mourik Broekmanweg 6, Delft, 2628 XE, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Computing Group in the Intelligent Systems Department Delft University of Technology, Van Mourik Broekmanweg 6, Delft, 2628 XE, the Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210136150"],"apc_list":{"value":2470,"currency":"USD","value_usd":2470},"apc_paid":{"value":2470,"currency":"USD","value_usd":2470},"fwci":1.6796,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.90675328,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"683","issue":null,"first_page":"131581","last_page":"131581"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.40700000524520874,"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/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.40700000524520874,"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/T13177","display_name":"Geological and Geophysical Studies","score":0.03819999843835831,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13067","display_name":"Geological Modeling and Analysis","score":0.03150000050663948,"subfield":{"id":"https://openalex.org/subfields/1906","display_name":"Geochemistry and Petrology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7688000202178955},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5740000009536743},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5580000281333923},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.525600016117096},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.40869998931884766}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7688000202178955},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6876000165939331},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5740000009536743},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5580000281333923},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.525600016117096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4465000033378601},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.40869998931884766},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3776000142097473},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3411000072956085},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.31439998745918274},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.2694000005722046}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.neucom.2025.131581","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neucom.2025.131581","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.neucom.2025.131581","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neucom.2025.131581","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4648328125476837,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G367552324","display_name":"Internationales Leibniz Zukunftslabor K\u00fcnstliche Intelligenz","funder_award_id":"01DD20003","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2150339816","https://openalex.org/W4390413862","https://openalex.org/W4391621086","https://openalex.org/W4394063541","https://openalex.org/W4404201236"],"related_works":[],"abstract_inverted_index":{"The":[0,37],"publisher":[1],"regrets":[2],"that":[3],"this":[4],"article":[5,27,33],"has":[6],"been":[7],"temporarily":[8],"removed.":[9],"A":[10],"replacement":[11],"will":[12,28,34],"appear":[13],"as":[14,16],"soon":[15],"possible":[17],"in":[18],"which":[19],"the":[20,23,26,32],"reason":[21],"for":[22],"removal":[24],"of":[25],"be":[29,35,45],"specified,":[30],"or":[31],"reinstated.":[36],"full":[38],"Elsevier":[39],"Policy":[40],"on":[41],"Article":[42],"Withdrawal":[43],"can":[44],"found":[46],"at":[47],"https://www.elsevier.com/about/policies-and-standards/article-withdrawal":[48],".":[49]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}