{"id":"https://openalex.org/W2071055125","doi":"https://doi.org/10.1109/acc.2010.5530611","title":"Approximate dynamic programming using model-free Bellman Residual Elimination","display_name":"Approximate dynamic programming using model-free Bellman Residual Elimination","publication_year":2010,"publication_date":"2010-06-01","ids":{"openalex":"https://openalex.org/W2071055125","doi":"https://doi.org/10.1109/acc.2010.5530611","mag":"2071055125"},"language":"en","primary_location":{"id":"doi:10.1109/acc.2010.5530611","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2010.5530611","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 American Control Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1721.1/66203","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111637722","display_name":"Brett Bethke","orcid":null},"institutions":[{"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":true,"raw_author_name":"Brett Bethke","raw_affiliation_strings":["Massachusetts Inst. of Tech., USA","Massachusetts Institute Of Technology, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Inst. of Tech., USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute Of Technology, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011665886","display_name":"Jonathan P. How","orcid":"https://orcid.org/0000-0001-8576-1930"},"institutions":[{"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"]},{"id":"https://openalex.org/I46020346","display_name":"American Institute of Aeronautics and Astronautics","ror":"https://ror.org/00a1rzv11","country_code":"US","type":"other","lineage":["https://openalex.org/I46020346"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan P How","raw_affiliation_strings":["Aeronautics and Astronautics, Massachusetts Institute of Technology, USA","Aeronautics and Astronautics, MIT, USA"],"affiliations":[{"raw_affiliation_string":"Aeronautics and Astronautics, Massachusetts Institute of Technology, USA","institution_ids":["https://openalex.org/I46020346","https://openalex.org/I63966007"]},{"raw_affiliation_string":"Aeronautics and Astronautics, MIT, USA","institution_ids":["https://openalex.org/I46020346"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5111637722"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.12280216,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4146","last_page":"4151"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9905999898910522,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9857000112533569,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.7821996212005615},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7483124136924744},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.743281364440918},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7207081317901611},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6364038586616516},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6139187216758728},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.547801673412323},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5037938952445984},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4854641556739807},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.45995819568634033},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.41988861560821533},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.36299678683280945},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3550279140472412},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.34577223658561707},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21778133511543274},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2173832654953003},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.13289719820022583}],"concepts":[{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.7821996212005615},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7483124136924744},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.743281364440918},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7207081317901611},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6364038586616516},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6139187216758728},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.547801673412323},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5037938952445984},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4854641556739807},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.45995819568634033},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.41988861560821533},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.36299678683280945},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3550279140472412},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.34577223658561707},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21778133511543274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2173832654953003},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13289719820022583},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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":2,"locations":[{"id":"doi:10.1109/acc.2010.5530611","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2010.5530611","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 American Control Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/66203","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/66203","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE","raw_type":"http://purl.org/eprint/type/ConferencePaper"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/66203","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/66203","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE","raw_type":"http://purl.org/eprint/type/ConferencePaper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7799999713897705}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306077","display_name":"Boeing","ror":"https://ror.org/04sm5zn07"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W18322812","https://openalex.org/W1502893368","https://openalex.org/W1560724230","https://openalex.org/W1576452626","https://openalex.org/W1646707810","https://openalex.org/W1746819321","https://openalex.org/W1964357740","https://openalex.org/W1986280275","https://openalex.org/W2098432798","https://openalex.org/W2117355432","https://openalex.org/W2126025075","https://openalex.org/W2133733518","https://openalex.org/W2157504067","https://openalex.org/W2159476216","https://openalex.org/W2315807965","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W1589140671","https://openalex.org/W1760611253","https://openalex.org/W52153049","https://openalex.org/W2951545791","https://openalex.org/W1515117609","https://openalex.org/W2294884454","https://openalex.org/W4323315247","https://openalex.org/W3169161914","https://openalex.org/W3208638985"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3,26,30,120],"modification":[4],"to":[5,83,91,103,105],"the":[6,37,42,60,68,76,88,94,106,110,116,127,130],"method":[7],"of":[8,41,52,59,67,75,87,118,123,129,150],"Bellman":[9],"Residual":[10],"Elimination":[11],"(BRE)":[12],"for":[13,29],"approximate":[14,27,142],"dynamic":[15,143],"programming.":[16],"While":[17],"prior":[18],"work":[19,47],"on":[20,24,175],"BRE":[21,53,95,113,137,162],"has":[22],"focused":[23],"learning":[25],"policy":[28,107,155],"underlying":[31],"Markov":[32],"Decision":[33],"Process":[34],"(MDP)":[35],"when":[36],"state":[38,61,65],"transition":[39,62],"model":[40],"MDP":[43],"is":[44],"known,":[45],"this":[46],"proposes":[48],"a":[49,140,176],"model-free":[50,136],"variant":[51],"that":[54,161],"does":[55],"not":[56],"require":[57],"knowledge":[58],"model.":[63],"Instead,":[64],"trajectories":[66],"system,":[69],"generated":[70],"using":[71],"simulation":[72],"and/or":[73],"observations":[74],"real":[77],"system":[78],"in":[79,115,148],"operation,":[80],"are":[81],"used":[82],"build":[84],"stochastic":[85],"approximations":[86],"quantities":[89],"needed":[90],"carry":[92],"out":[93],"algorithm.":[96,145],"The":[97],"resulting":[98],"algorithm":[99,114],"can":[100],"be":[101],"shown":[102],"converge":[104],"produced":[108],"by":[109],"nominal,":[111],"model-based":[112,134],"limit":[117],"observing":[119],"infinite":[121],"number":[122],"trajectories.":[124],"To":[125],"validate":[126],"performance":[128,147],"approach,":[131],"we":[132,157],"compare":[133],"and":[135,154,169],"against":[138],"LSPI,":[139],"well-known":[141],"programming":[144],"Measuring":[146],"terms":[149],"both":[151],"computational":[152],"complexity":[153],"quality,":[156],"present":[158],"results":[159],"showing":[160],"performs":[163],"at":[164],"least":[165],"as":[166],"well":[167],"as,":[168],"sometimes":[170],"significantly":[171],"better":[172],"than,":[173],"LSPI":[174],"standard":[177],"benchmark":[178],"problem.":[179]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}