{"id":"https://openalex.org/W2112264645","doi":"https://doi.org/10.1145/1553374.1553442","title":"Regularization and feature selection in least-squares temporal difference learning","display_name":"Regularization and feature selection in least-squares temporal difference learning","publication_year":2009,"publication_date":"2009-06-14","ids":{"openalex":"https://openalex.org/W2112264645","doi":"https://doi.org/10.1145/1553374.1553442","mag":"2112264645"},"language":"en","primary_location":{"id":"doi:10.1145/1553374.1553442","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1553374.1553442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th Annual International Conference on Machine Learning","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/A5075035644","display_name":"J. Zico Kolter","orcid":"https://orcid.org/0000-0002-8106-5759"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"J. Zico Kolter","raw_affiliation_strings":["Stanford University, CA"],"affiliations":[{"raw_affiliation_string":"Stanford University, CA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112456378","display_name":"Andrew Y. Ng","orcid":"https://orcid.org/0000-0001-5547-3196"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Y. Ng","raw_affiliation_strings":["Stanford University, CA"],"affiliations":[{"raw_affiliation_string":"Stanford University, CA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5075035644"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":19.0279,"has_fulltext":false,"cited_by_count":183,"citation_normalized_percentile":{"value":0.99623988,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"521","last_page":"528"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9947999715805054,"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"}},"topics":[{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9947999715805054,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9585999846458435,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9473999738693237,"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/temporal-difference-learning","display_name":"Temporal difference learning","score":0.8076189160346985},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.7353744506835938},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6042062044143677},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5573940873146057},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5369389653205872},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5209859013557434},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5164482593536377},{"id":"https://openalex.org/keywords/convex-function","display_name":"Convex function","score":0.49193501472473145},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4472730755805969},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4361609220504761},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.38274872303009033},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3539959192276001}],"concepts":[{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.8076189160346985},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.7353744506835938},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6042062044143677},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5573940873146057},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5369389653205872},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5209859013557434},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5164482593536377},{"id":"https://openalex.org/C145446738","wikidata":"https://www.wikidata.org/wiki/Q319913","display_name":"Convex function","level":3,"score":0.49193501472473145},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4472730755805969},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4361609220504761},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.38274872303009033},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3539959192276001},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1553374.1553442","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1553374.1553442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th Annual International Conference on Machine Learning","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.149.5506","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.5506","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.mcgill.ca/~icml2009/papers/439.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.154.2962","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.154.2962","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.robotics.stanford.edu/~ang/papers/icml09-RegularizationFeatureSelectionLSTD.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.154.3271","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.154.3271","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.robotics.stanford.edu/~ang/papers/icml09-RegularizationFeatureSelectionLSTD-full.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6664096962","display_name":null,"funder_award_id":"FA8650-05-C-7261","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"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":30,"referenced_works":["https://openalex.org/W74861005","https://openalex.org/W86816279","https://openalex.org/W1488435683","https://openalex.org/W1515851193","https://openalex.org/W1542938076","https://openalex.org/W1998172110","https://openalex.org/W2004915807","https://openalex.org/W2011233848","https://openalex.org/W2063978378","https://openalex.org/W2072931156","https://openalex.org/W2100677568","https://openalex.org/W2112264645","https://openalex.org/W2118556122","https://openalex.org/W2121863487","https://openalex.org/W2122825543","https://openalex.org/W2132351269","https://openalex.org/W2135046866","https://openalex.org/W2138326839","https://openalex.org/W2139418546","https://openalex.org/W2158738729","https://openalex.org/W2158883409","https://openalex.org/W2610857016","https://openalex.org/W2963056604","https://openalex.org/W3022380717","https://openalex.org/W4214717370","https://openalex.org/W4285719527","https://openalex.org/W6603123960","https://openalex.org/W6636318421","https://openalex.org/W6677916085","https://openalex.org/W6683356630"],"related_works":["https://openalex.org/W2149418961","https://openalex.org/W4308702637","https://openalex.org/W4256087190","https://openalex.org/W4240668504","https://openalex.org/W2100100236","https://openalex.org/W3038962357","https://openalex.org/W2971484784","https://openalex.org/W2808418668","https://openalex.org/W61119710","https://openalex.org/W4288112126"],"abstract_inverted_index":{"We":[0],"consider":[1],"the":[2,18,29,32,37,48,63,75,96,115,125,131,134],"task":[3],"of":[4,31,39,77,133],"reinforcement":[5],"learning":[6,28],"with":[7],"linear":[8],"value":[9,33],"function":[10],"approximation.":[11],"Temporal":[12,20],"difference":[13],"algorithms,":[14],"and":[15,50,86],"in":[16],"particular":[17],"Least-Squares":[19],"Difference":[21],"(LSTD)":[22],"algorithm,":[23],"provide":[24],"a":[25,59,90,105],"method":[26,91],"for":[27,62,92],"parameters":[30],"function,":[34],"but":[35],"when":[36],"number":[38],"features":[40,85],"is":[41,51,81],"large":[42],"this":[43,55],"algorithm":[44,65,112,120,135],"can":[45,122],"over-fit":[46],"to":[47,83,114],"data":[49],"computationally":[52],"expensive.":[53],"In":[54,70],"paper,":[56],"we":[57,72,109,129],"propose":[58],"regularization":[60],"framework":[61],"LSTD":[64,99],"that":[66,121],"overcomes":[67],"these":[68],"difficulties.":[69],"particular,":[71],"focus":[73],"on":[74],"case":[76],"l1":[78,97],"regularization,":[79],"which":[80],"robust":[82],"irrelevant":[84],"also":[87],"serves":[88],"as":[89,104],"feature":[93],"selection.":[94],"Although":[95],"regularized":[98],"solution":[100],"cannot":[101],"be":[102],"expressed":[103],"convex":[106],"optimization":[107],"problem,":[108],"present":[110],"an":[111],"similar":[113],"Least":[116],"Angle":[117],"Regression":[118],"(LARS)":[119],"efficiently":[123],"compute":[124],"optimal":[126],"solution.":[127],"Finally,":[128],"demonstrate":[130],"performance":[132],"experimentally.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":16},{"year":2013,"cited_by_count":16},{"year":2012,"cited_by_count":19}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}