{"id":"https://openalex.org/W4246906609","doi":"https://doi.org/10.1023/a:1018056104778","title":"Linear Least-Squares Algorithms for Temporal Difference Learning","display_name":"Linear Least-Squares Algorithms for Temporal Difference Learning","publication_year":1996,"publication_date":"1996-01-01","ids":{"openalex":"https://openalex.org/W4246906609","doi":"https://doi.org/10.1023/a:1018056104778"},"language":"en","primary_location":{"id":"doi:10.1023/a:1018056104778","is_oa":true,"landing_page_url":"https://doi.org/10.1023/a:1018056104778","pdf_url":"https://link.springer.com/content/pdf/10.1023/A:1018056104778.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"Machine Learning","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/10.1023/A:1018056104778.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081885151","display_name":"Steven J. Bradtke","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Steven J. Bradtke","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5089808068","display_name":"Andrew G. Barto","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrew G. Barto","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5081885151"],"corresponding_institution_ids":[],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.39389628,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"22","issue":"1-3","first_page":"33","last_page":"57"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9919000267982483,"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/T10320","display_name":"Neural Networks and Applications","score":0.9919000267982483,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9812999963760376,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11236","display_name":"Control Systems and Identification","score":0.9801999926567078,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/recursive-least-squares-filter","display_name":"Recursive least squares filter","score":0.6538529396057129},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.581325113773346},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.5787855386734009},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.5578756332397461},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5551862716674805},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5415743589401245},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5329044461250305},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5054318904876709},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.45403194427490234},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4398178458213806},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.42325082421302795},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.41465508937835693},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3649415373802185},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.34918808937072754},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.28057020902633667},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.25436025857925415},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22704964876174927},{"id":"https://openalex.org/keywords/adaptive-filter","display_name":"Adaptive filter","score":0.19159430265426636},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.17723843455314636}],"concepts":[{"id":"https://openalex.org/C145249878","wikidata":"https://www.wikidata.org/wiki/Q2835868","display_name":"Recursive least squares filter","level":3,"score":0.6538529396057129},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.581325113773346},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.5787855386734009},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.5578756332397461},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5551862716674805},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5415743589401245},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5329044461250305},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5054318904876709},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45403194427490234},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4398178458213806},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.42325082421302795},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.41465508937835693},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3649415373802185},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.34918808937072754},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28057020902633667},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.25436025857925415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22704964876174927},{"id":"https://openalex.org/C102248274","wikidata":"https://www.wikidata.org/wiki/Q168388","display_name":"Adaptive filter","level":2,"score":0.19159430265426636},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.17723843455314636},{"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1023/a:1018056104778","is_oa":true,"landing_page_url":"https://doi.org/10.1023/a:1018056104778","pdf_url":"https://link.springer.com/content/pdf/10.1023/A:1018056104778.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"Machine Learning","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1023/a:1018056104778","is_oa":true,"landing_page_url":"https://doi.org/10.1023/a:1018056104778","pdf_url":"https://link.springer.com/content/pdf/10.1023/A:1018056104778.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"No poverty","id":"https://metadata.un.org/sdg/1"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4246906609.pdf","grobid_xml":"https://content.openalex.org/works/W4246906609.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W6614468","https://openalex.org/W8452924","https://openalex.org/W1551329771","https://openalex.org/W1569296262","https://openalex.org/W1966517492","https://openalex.org/W1971129545","https://openalex.org/W1994616650","https://openalex.org/W2165131254","https://openalex.org/W4229739354","https://openalex.org/W4240813273","https://openalex.org/W4246808543","https://openalex.org/W4248400504","https://openalex.org/W4298871068","https://openalex.org/W6669063669"],"related_works":["https://openalex.org/W2348126519","https://openalex.org/W3106446092","https://openalex.org/W1907128005","https://openalex.org/W3206576350","https://openalex.org/W2772472730","https://openalex.org/W2514909387","https://openalex.org/W3008618380","https://openalex.org/W2964123095","https://openalex.org/W4241680091","https://openalex.org/W2072931156"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-03-31T07:56:22.981413","created_date":"2022-05-12T00:00:00"}