{"id":"https://openalex.org/W2153267861","doi":"https://doi.org/10.1109/adprl.2009.4927528","title":"Basis function adaptation methods for cost approximation in MDP","display_name":"Basis function adaptation methods for cost approximation in MDP","publication_year":2009,"publication_date":"2009-03-01","ids":{"openalex":"https://openalex.org/W2153267861","doi":"https://doi.org/10.1109/adprl.2009.4927528","mag":"2153267861"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2009.4927528","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2009.4927528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement 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/A5014937312","display_name":"Huizhen Yu","orcid":"https://orcid.org/0000-0002-3673-0094"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Huizhen Yu","raw_affiliation_strings":["Department of Computer Science and HIIT, University of Helsinki, Helsinki, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and HIIT, University of Helsinki, Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039911471","display_name":"Dimitri P. Bertsekas","orcid":"https://orcid.org/0000-0001-6909-7208"},"institutions":[{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dimitri P. Bertsekas","raw_affiliation_strings":["Laboratory of Information and Decision Systems (LIDS), Massachusetts Institute of Technology, MA, USA"],"affiliations":[{"raw_affiliation_string":"Laboratory of Information and Decision Systems (LIDS), Massachusetts Institute of Technology, MA, USA","institution_ids":["https://openalex.org/I4210143601","https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5014937312"],"corresponding_institution_ids":["https://openalex.org/I133731052"],"apc_list":null,"apc_paid":null,"fwci":7.6782,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.97321916,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"74","last_page":"81"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9855999946594238,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9632999897003174,"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/basis","display_name":"Basis (linear algebra)","score":0.6897790431976318},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6312811374664307},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6137458086013794},{"id":"https://openalex.org/keywords/basis-function","display_name":"Basis function","score":0.6029906868934631},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5530939698219299},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5330114960670471},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.4928913116455078},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.48311376571655273},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.46717438101768494},{"id":"https://openalex.org/keywords/approximation-theory","display_name":"Approximation theory","score":0.44610539078712463},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4322316646575928},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4288231134414673},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.42587849497795105},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.399432510137558},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2663705348968506},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14847013354301453},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.13749542832374573},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.07912251353263855},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.057768434286117554}],"concepts":[{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.6897790431976318},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6312811374664307},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6137458086013794},{"id":"https://openalex.org/C5917680","wikidata":"https://www.wikidata.org/wiki/Q2621825","display_name":"Basis function","level":2,"score":0.6029906868934631},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5530939698219299},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5330114960670471},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.4928913116455078},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.48311376571655273},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.46717438101768494},{"id":"https://openalex.org/C145242015","wikidata":"https://www.wikidata.org/wiki/Q774123","display_name":"Approximation theory","level":2,"score":0.44610539078712463},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4322316646575928},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4288231134414673},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.42587849497795105},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.399432510137558},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2663705348968506},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14847013354301453},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.13749542832374573},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.07912251353263855},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.057768434286117554},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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":1,"locations":[{"id":"doi:10.1109/adprl.2009.4927528","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2009.4927528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6800000071525574}],"awards":[{"id":"https://openalex.org/G1494807058","display_name":"Control over Networks","funder_award_id":"0801549","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337392","display_name":"Division of Electrical, Communications and Cyber Systems","ror":"https://ror.org/01krpsy48"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1518539242","https://openalex.org/W1576452626","https://openalex.org/W1597303641","https://openalex.org/W1997394097","https://openalex.org/W1998172110","https://openalex.org/W2009303086","https://openalex.org/W2015192378","https://openalex.org/W2019172585","https://openalex.org/W2027378843","https://openalex.org/W2062541405","https://openalex.org/W2098432798","https://openalex.org/W2100677568","https://openalex.org/W2156168464","https://openalex.org/W2156737235","https://openalex.org/W2158278868","https://openalex.org/W2911283634","https://openalex.org/W2914656440","https://openalex.org/W3041202696","https://openalex.org/W4243772471","https://openalex.org/W4249513058","https://openalex.org/W6635767209","https://openalex.org/W6683392610"],"related_works":["https://openalex.org/W2979432606","https://openalex.org/W2235525867","https://openalex.org/W2766569526","https://openalex.org/W1859974437","https://openalex.org/W3119329039","https://openalex.org/W4306703873","https://openalex.org/W2964123095","https://openalex.org/W2064547980","https://openalex.org/W3177870706","https://openalex.org/W1997991996"],"abstract_inverted_index":{"We":[0],"generalize":[1],"a":[2,46,68],"basis":[3,25,78],"adaptation":[4,56,79],"method":[5,52],"for":[6,87],"cost":[7,41,95],"approximation":[8,43],"in":[9,67],"Markov":[10],"decision":[11],"processes":[12],"(MDP),":[13],"extending":[14],"earlier":[15],"work":[16],"of":[17],"Menache,":[18],"Mannor,":[19],"and":[20,29,63,92],"Shimkin.":[21],"In":[22,75],"our":[23],"context,":[24],"functions":[26],"are":[27,32],"parametrized":[28],"their":[30],"parameters":[31],"tuned":[33],"by":[34],"minimizing":[35],"an":[36],"objective":[37],"function":[38,42],"involving":[39],"the":[40,76],"obtained":[44],"when":[45],"temporal":[47],"differences":[48],"(TD)":[49],"or":[50],"other":[51],"is":[53],"used.":[54],"The":[55],"scheme":[57],"involves":[58],"only":[59],"low":[60],"order":[61],"calculations":[62],"can":[64],"be":[65],"implemented":[66],"way":[69],"analogous":[70],"to":[71,84,93],"policy":[72],"gradient":[73],"methods.":[74],"generalized":[77],"framework":[80],"we":[81],"provide":[82],"extensions":[83],"TD":[85],"methods":[86],"nonlinear":[88],"optimal":[89],"stopping":[90],"problems":[91],"alternative":[94],"approximations":[96],"beyond":[97],"those":[98],"based":[99],"on":[100],"TD.":[101]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}