{"id":"https://openalex.org/W2123979492","doi":"https://doi.org/10.1145/1390156.1390251","title":"An analysis of linear models, linear value-function approximation, and feature selection for reinforcement learning","display_name":"An analysis of linear models, linear value-function approximation, and feature selection for reinforcement learning","publication_year":2008,"publication_date":"2008-01-01","ids":{"openalex":"https://openalex.org/W2123979492","doi":"https://doi.org/10.1145/1390156.1390251","mag":"2123979492"},"language":"en","primary_location":{"id":"doi:10.1145/1390156.1390251","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390156.1390251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th international conference on Machine learning - ICML '08","raw_type":"proceedings-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/A5109839104","display_name":"Ronald Parr","orcid":null},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ronald Parr","raw_affiliation_strings":["Duke University, Durham, NC","Duke University Durham NC"],"affiliations":[{"raw_affiliation_string":"Duke University, Durham, NC","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Duke University Durham NC","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100711454","display_name":"Lihong Li","orcid":"https://orcid.org/0000-0002-5440-8242"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lihong Li","raw_affiliation_strings":["Rutgers University, Piscataway, NJ"],"affiliations":[{"raw_affiliation_string":"Rutgers University, Piscataway, NJ","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043788981","display_name":"Gavin Taylor","orcid":"https://orcid.org/0000-0002-3455-9430"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gavin Taylor","raw_affiliation_strings":["Duke University, Durham, NC","Duke University Durham NC"],"affiliations":[{"raw_affiliation_string":"Duke University, Durham, NC","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Duke University Durham NC","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060178852","display_name":"Christopher Painter-Wakefield","orcid":null},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Painter-Wakefield","raw_affiliation_strings":["Duke University, Durham, NC","Duke University Durham NC"],"affiliations":[{"raw_affiliation_string":"Duke University, Durham, NC","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Duke University Durham NC","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009722403","display_name":"Michael L. Littman","orcid":"https://orcid.org/0000-0002-5596-1840"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael L. Littman","raw_affiliation_strings":["Rutgers University, Piscataway, NJ"],"affiliations":[{"raw_affiliation_string":"Rutgers University, Piscataway, NJ","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5109839104"],"corresponding_institution_ids":["https://openalex.org/I170897317"],"apc_list":null,"apc_paid":null,"fwci":16.4244,"has_fulltext":false,"cited_by_count":160,"citation_normalized_percentile":{"value":0.99063486,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"752","last_page":"759"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9980999827384949,"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":0.9904000163078308,"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":0.7982898950576782},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.7042832970619202},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.6496795415878296},{"id":"https://openalex.org/keywords/linear-approximation","display_name":"Linear approximation","score":0.6323322653770447},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5845150947570801},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5773271322250366},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5696551203727722},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5502026081085205},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5485074520111084},{"id":"https://openalex.org/keywords/approximation-error","display_name":"Approximation error","score":0.532065212726593},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5092514753341675},{"id":"https://openalex.org/keywords/approximation-algorithm","display_name":"Approximation algorithm","score":0.4569130837917328},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.44629013538360596},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43624651432037354},{"id":"https://openalex.org/keywords/approximation-theory","display_name":"Approximation theory","score":0.4212881326675415},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3728483319282532},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.34675168991088867},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3447096645832062},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2636095881462097},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.15682953596115112},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.11442887783050537},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.08720400929450989}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7982898950576782},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.7042832970619202},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6496795415878296},{"id":"https://openalex.org/C160824197","wikidata":"https://www.wikidata.org/wiki/Q2071054","display_name":"Linear approximation","level":3,"score":0.6323322653770447},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5845150947570801},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5773271322250366},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5696551203727722},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5502026081085205},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5485074520111084},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.532065212726593},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5092514753341675},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.4569130837917328},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.44629013538360596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43624651432037354},{"id":"https://openalex.org/C145242015","wikidata":"https://www.wikidata.org/wiki/Q774123","display_name":"Approximation theory","level":2,"score":0.4212881326675415},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3728483319282532},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.34675168991088867},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3447096645832062},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2636095881462097},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.15682953596115112},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.11442887783050537},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.08720400929450989},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1390156.1390251","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390156.1390251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th international conference on Machine learning - ICML '08","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.140.3614","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.140.3614","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.duke.edu/~parr/icml08.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W115446000","https://openalex.org/W1519179592","https://openalex.org/W1588316674","https://openalex.org/W1597303641","https://openalex.org/W1688218840","https://openalex.org/W2011233848","https://openalex.org/W2072931156","https://openalex.org/W2100677568","https://openalex.org/W2121863487","https://openalex.org/W2138326839","https://openalex.org/W2151693816","https://openalex.org/W2161795906","https://openalex.org/W2165418472","https://openalex.org/W2911283634","https://openalex.org/W2964138387","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2171221472","https://openalex.org/W2046314839","https://openalex.org/W2108297731","https://openalex.org/W2167394514","https://openalex.org/W3177870706","https://openalex.org/W2087686193","https://openalex.org/W3113145869","https://openalex.org/W2768028474","https://openalex.org/W1963832283","https://openalex.org/W2096450101"],"abstract_inverted_index":{"We":[0,15,43],"show":[1,29,45],"that":[2],"linear":[3,12],"value-function":[4,41],"approximation":[5],"is":[6],"equivalent":[7],"to":[8],"a":[9,18],"form":[10],"of":[11,54],"model":[13,38],"approximation.":[14],"then":[16],"derive":[17],"relationship":[19,32],"between":[20],"the":[21,25,52],"model-approximation":[22],"error":[23],"and":[24,28],"Bellman":[26],"error,":[27],"how":[30,46],"this":[31],"can":[33],"guide":[34],"feature":[35],"selection":[36],"for":[37],"improvement":[39],"and/or":[40],"improvement.":[42],"also":[44],"these":[47],"results":[48],"give":[49],"insight":[50],"into":[51],"behavior":[53],"existing":[55],"feature-selection":[56],"algorithms.":[57]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":18},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":13},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":13},{"year":2012,"cited_by_count":10}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}