{"id":"https://openalex.org/W2160284799","doi":"https://doi.org/10.1109/acc.2009.5160611","title":"Regularized Fitted Q-Iteration for planning in continuous-space Markovian decision problems","display_name":"Regularized Fitted Q-Iteration for planning in continuous-space Markovian decision problems","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W2160284799","doi":"https://doi.org/10.1109/acc.2009.5160611","mag":"2160284799"},"language":"en","primary_location":{"id":"doi:10.1109/acc.2009.5160611","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2009.5160611","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 American Control Conference","raw_type":"proceedings-article"},"type":"conference-paper","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/A5109234479","display_name":"Amir massoud Farahmand","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Amir massoud Farahmand","raw_affiliation_strings":["Department of Computing Science, University of Alberta, Edmonton, AB, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013843778","display_name":"Mohammad Ghavamzadeh","orcid":"https://orcid.org/0000-0003-0930-8688"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mohammad Ghavamzadeh","raw_affiliation_strings":["Department of Computing Science, University of Alberta, Edmonton, AB, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069856068","display_name":"Csaba Szepesv\u00e1ri","orcid":"https://orcid.org/0000-0002-9286-2892"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Csaba Szepesvari","raw_affiliation_strings":["Department of Computing Science, University of Alberta, Edmonton, AB, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","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 & Computer Engineering, McGill University, Montreal, QUE, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical & Computer Engineering, McGill University, Montreal, QUE, Canada","institution_ids":["https://openalex.org/I5023651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.8993,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.94743562,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"725","last_page":"730"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.996999979019165,"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":0.9071663618087769},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.7585015296936035},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7159919142723083},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.6365759372711182},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5538342595100403},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.5476488471031189},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5340437293052673},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.5118705630302429},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4694858193397522},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.46862131357192993},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4148428440093994},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.36520087718963623},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3601204454898834},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.31551289558410645},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.107108473777771}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9071663618087769},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.7585015296936035},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7159919142723083},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6365759372711182},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5538342595100403},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.5476488471031189},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5340437293052673},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.5118705630302429},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4694858193397522},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.46862131357192993},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4148428440093994},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36520087718963623},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3601204454898834},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.31551289558410645},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.107108473777771},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/acc.2009.5160611","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2009.5160611","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 American Control Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:publications.polymtl.ca:63130","is_oa":false,"landing_page_url":"https://publications.polymtl.ca/63130/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401013","display_name":"PolyPublie (\u00c9cole Polytechnique de Montr\u00e9al)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45683168","host_organization_name":"Polytechnique Montr\u00e9al","host_organization_lineage":["https://openalex.org/I45683168"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Communication de conf\u00e9rence"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.150.3614","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.150.3614","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.sztaki.hu/~szcsaba/papers/RegPlan-ACC09.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7699999809265137,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W74861005","https://openalex.org/W565357261","https://openalex.org/W1484867920","https://openalex.org/W1529558080","https://openalex.org/W1982795744","https://openalex.org/W1988882685","https://openalex.org/W1998172110","https://openalex.org/W2045756756","https://openalex.org/W2082991751","https://openalex.org/W2097452095","https://openalex.org/W2104753538","https://openalex.org/W2112531253","https://openalex.org/W2120346334","https://openalex.org/W2134289401","https://openalex.org/W2138326839","https://openalex.org/W2151416233","https://openalex.org/W2156974606","https://openalex.org/W2158738729","https://openalex.org/W2158883409","https://openalex.org/W2160284799","https://openalex.org/W3101040439","https://openalex.org/W3119651796","https://openalex.org/W6603123960","https://openalex.org/W6677737365","https://openalex.org/W6679703492"],"related_works":["https://openalex.org/W2152670157","https://openalex.org/W4308702637","https://openalex.org/W2386410636","https://openalex.org/W176737593","https://openalex.org/W2808418668","https://openalex.org/W2903299703","https://openalex.org/W2016648086","https://openalex.org/W3105579180","https://openalex.org/W2156021013","https://openalex.org/W4399157305"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,24,42,62],"with":[2],"linear":[3],"and":[4,63,73],"non-linear":[5],"function":[6,59],"approximation":[7],"has":[8,34],"been":[9,36],"studied":[10],"extensively":[11],"in":[12,60],"the":[13,29,40,54,57,68,92,96],"last":[14],"decade.":[15],"However,":[16],"as":[17,26],"opposed":[18],"to":[19,49,52,90],"other":[20],"fields":[21],"of":[22,31,56,94],"machine":[23],"such":[25],"supervised":[27],"learning,":[28],"effect":[30],"finite":[32],"sample":[33,81],"not":[35],"thoroughly":[37],"addressed":[38],"within":[39],"reinforcement":[41,61],"framework.":[43],"In":[44],"this":[45],"paper":[46],"we":[47],"propose":[48],"use":[50],"L2regularization":[51],"control":[53],"complexity":[55],"value":[58],"planning":[64],"problems.":[65],"We":[66],"consider":[67],"Regularized":[69],"Fitted":[70],"Q-Iteration":[71],"algorithm":[72],"provide":[74],"generalization":[75],"bounds":[76],"that":[77],"account":[78],"for":[79],"small":[80],"sizes.":[82],"Finally,":[83],"a":[84],"realistic":[85],"visual-servoing":[86],"problem":[87],"is":[88],"used":[89],"illustrate":[91],"benefits":[93],"using":[95],"regularization":[97],"procedure.":[98]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}