{"id":"https://openalex.org/W1998172110","doi":"https://doi.org/10.1007/s10479-005-5732-z","title":"Basis Function Adaptation in Temporal Difference Reinforcement Learning","display_name":"Basis Function Adaptation in Temporal Difference Reinforcement Learning","publication_year":2005,"publication_date":"2005-02-01","ids":{"openalex":"https://openalex.org/W1998172110","doi":"https://doi.org/10.1007/s10479-005-5732-z","mag":"1998172110"},"language":"en","primary_location":{"id":"doi:10.1007/s10479-005-5732-z","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10479-005-5732-z","pdf_url":null,"source":{"id":"https://openalex.org/S57667410","display_name":"Annals of Operations Research","issn_l":"0254-5330","issn":["0254-5330","1572-9338"],"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":"Annals of Operations Research","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032872922","display_name":"Ishai Menache","orcid":"https://orcid.org/0000-0002-2540-236X"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Ishai Menache","raw_affiliation_strings":["Department of Electrical Engineering, Technion, Israel Institute of Technology, Haifa, 32000, Israel","Department of Electrical Engineering, Technion??Israel Institute of Technology, Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Technion, Israel Institute of Technology, Haifa, 32000, Israel","institution_ids":["https://openalex.org/I174306211"]},{"raw_affiliation_string":"Department of Electrical Engineering, Technion??Israel Institute of Technology, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036260775","display_name":"Shie Mannor","orcid":"https://orcid.org/0000-0003-4439-7647"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Shie Mannor","raw_affiliation_strings":["Department of Electrical and Computer Engineering, McGill University, 3480 University Street, Montreal, Quebec, Canada","[Department of Electrical and Computer Engineering, McGill University, Montr\u00e9al, Canada]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, McGill University, 3480 University Street, Montreal, Quebec, Canada","institution_ids":["https://openalex.org/I5023651"]},{"raw_affiliation_string":"[Department of Electrical and Computer Engineering, McGill University, Montr\u00e9al, Canada]","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007808379","display_name":"Nahum Shimkin","orcid":"https://orcid.org/0000-0001-7105-9956"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Nahum Shimkin","raw_affiliation_strings":["Department of Electrical Engineering, Technion, Israel Institute of Technology, Haifa, 32000, Israel","Department of Electrical Engineering, Technion??Israel Institute of Technology, Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Technion, Israel Institute of Technology, Haifa, 32000, Israel","institution_ids":["https://openalex.org/I174306211"]},{"raw_affiliation_string":"Department of Electrical Engineering, Technion??Israel Institute of Technology, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5032872922"],"corresponding_institution_ids":["https://openalex.org/I174306211"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":12.3307,"has_fulltext":false,"cited_by_count":190,"citation_normalized_percentile":{"value":0.98537018,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"134","issue":"1","first_page":"215","last_page":"238"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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/T10462","display_name":"Reinforcement Learning in Robotics","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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8139339685440063},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7245966792106628},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.660291314125061},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.6294196844100952},{"id":"https://openalex.org/keywords/basis-function","display_name":"Basis function","score":0.6226484775543213},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.6211646199226379},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6131221055984497},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.6088859438896179},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5905370712280273},{"id":"https://openalex.org/keywords/theory-of-computation","display_name":"Theory of computation","score":0.45716938376426697},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.448515921831131},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.43547478318214417},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.35858750343322754},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3378279209136963},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31064310669898987},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.28597623109817505},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.19063764810562134}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8139339685440063},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7245966792106628},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.660291314125061},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.6294196844100952},{"id":"https://openalex.org/C5917680","wikidata":"https://www.wikidata.org/wiki/Q2621825","display_name":"Basis function","level":2,"score":0.6226484775543213},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.6211646199226379},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6131221055984497},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.6088859438896179},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5905370712280273},{"id":"https://openalex.org/C24858836","wikidata":"https://www.wikidata.org/wiki/Q844718","display_name":"Theory of computation","level":2,"score":0.45716938376426697},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.448515921831131},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.43547478318214417},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.35858750343322754},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3378279209136963},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31064310669898987},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28597623109817505},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.19063764810562134},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s10479-005-5732-z","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10479-005-5732-z","pdf_url":null,"source":{"id":"https://openalex.org/S57667410","display_name":"Annals of Operations Research","issn_l":"0254-5330","issn":["0254-5330","1572-9338"],"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":"Annals of Operations Research","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.110.1768","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.110.1768","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ee.technion.ac.il/people/shimkin/preprints/basisadaptation_dec03.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.15.5876","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.15.5876","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ee.technion.ac.il/people/shimkin/PREPRINTS/MMS03_basis_adpatation.pdf","raw_type":"text"},{"id":"pmh:oai:RePEc:spr:annopr:v:134:y:2005:i:1:p:215-238:10.1007/s10479-005-5732-z","is_oa":false,"landing_page_url":"http://hdl.handle.net/10.1007/s10479-005-5732-z","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1502364872","https://openalex.org/W1507222174","https://openalex.org/W1522950143","https://openalex.org/W1536990779","https://openalex.org/W1576452626","https://openalex.org/W1577352482","https://openalex.org/W1579779079","https://openalex.org/W1601777908","https://openalex.org/W1730555343","https://openalex.org/W1966517492","https://openalex.org/W2054940200","https://openalex.org/W2072931156","https://openalex.org/W2091565802","https://openalex.org/W2098432798","https://openalex.org/W2099833070","https://openalex.org/W2100677568","https://openalex.org/W2101762657","https://openalex.org/W2104335146","https://openalex.org/W2107726111","https://openalex.org/W2117853077","https://openalex.org/W2118911876","https://openalex.org/W2121832485","https://openalex.org/W2121863487","https://openalex.org/W2124776405","https://openalex.org/W2125510930","https://openalex.org/W2132083787","https://openalex.org/W2132351269","https://openalex.org/W2139418546","https://openalex.org/W2143435603","https://openalex.org/W2163302320","https://openalex.org/W2169982856","https://openalex.org/W2334782222","https://openalex.org/W2588399964","https://openalex.org/W4214717370","https://openalex.org/W4246906609","https://openalex.org/W4253187718","https://openalex.org/W4285719527","https://openalex.org/W6600374106","https://openalex.org/W6634528131","https://openalex.org/W6637597983","https://openalex.org/W6674995601","https://openalex.org/W6675086535","https://openalex.org/W6675100857","https://openalex.org/W6678851513","https://openalex.org/W6678900246","https://openalex.org/W6684126333","https://openalex.org/W7037644959"],"related_works":["https://openalex.org/W2955790965","https://openalex.org/W4308702637","https://openalex.org/W4289355352","https://openalex.org/W2149418961","https://openalex.org/W1501190258","https://openalex.org/W2806157618","https://openalex.org/W2808418668","https://openalex.org/W4256087190","https://openalex.org/W4240668504","https://openalex.org/W2011233848"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":17},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":13},{"year":2012,"cited_by_count":15}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}