{"id":"https://openalex.org/W2159476216","doi":"https://doi.org/10.1109/acc.2009.5160344","title":"Approximate dynamic programming using Bellman residual elimination and Gaussian process regression","display_name":"Approximate dynamic programming using Bellman residual elimination and Gaussian process regression","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W2159476216","doi":"https://doi.org/10.1109/acc.2009.5160344","mag":"2159476216"},"language":"en","primary_location":{"id":"doi:10.1109/acc.2009.5160344","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2009.5160344","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1721.1/58878","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"]},{"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":true,"raw_author_name":"Brett Bethke","raw_affiliation_strings":["Department of Aeronautics and Astronautics, Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Aeronautics and Astronautics, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I46020346","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/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, MIT, USA"],"affiliations":[{"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/I46020346","https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":4.0649,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.94190333,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"16","issue":null,"first_page":"745","last_page":"750"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9968000054359436,"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":0.9968000054359436,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.995199978351593,"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":0.9947999715805054,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6711054444313049},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6589526534080505},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.569034993648529},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5686284303665161},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.48529642820358276},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4754186272621155},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4690818190574646},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.44033223390579224},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.438494473695755},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.433304101228714},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.43270355463027954},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.40363940596580505},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.33518487215042114},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2865909934043884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.10838967561721802},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08469367027282715}],"concepts":[{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6711054444313049},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6589526534080505},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.569034993648529},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5686284303665161},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.48529642820358276},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4754186272621155},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4690818190574646},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44033223390579224},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.438494473695755},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.433304101228714},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.43270355463027954},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.40363940596580505},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.33518487215042114},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2865909934043884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.10838967561721802},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08469367027282715},{"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/acc.2009.5160344","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2009.5160344","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:CiteSeerX.psu:10.1.1.547.5256","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.547.5256","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://web.mit.edu/aeroastro/academics/grad/proposals/Bethke_proposal.pdf","raw_type":"text"},{"id":"pmh:oai:dspace.mit.edu:1721.1/58878","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/58878","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"},{"id":"pmh:oai:dspace.mit.edu:1721.1/58907","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/58907","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/JournalArticle"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/58878","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/58878","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":[{"score":0.7300000190734863,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1523888516","display_name":null,"funder_award_id":"FA9550-","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G5809100787","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"}],"funders":[{"id":"https://openalex.org/F4320306077","display_name":"Boeing","ror":"https://ror.org/04sm5zn07"},{"id":"https://openalex.org/F4320306132","display_name":"American Society for Engineering Education","ror":"https://ror.org/03ac64295"},{"id":"https://openalex.org/F4320308782","display_name":"Hertz Foundation","ror":"https://ror.org/01ycgxf29"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1515851193","https://openalex.org/W1576452626","https://openalex.org/W1646707810","https://openalex.org/W1746819321","https://openalex.org/W1986280275","https://openalex.org/W2013614847","https://openalex.org/W2037448290","https://openalex.org/W2040766536","https://openalex.org/W2098432798","https://openalex.org/W2104753538","https://openalex.org/W2106451198","https://openalex.org/W2121863487","https://openalex.org/W2131600418","https://openalex.org/W2133733518","https://openalex.org/W2139212933","https://openalex.org/W2139816856","https://openalex.org/W2151268438","https://openalex.org/W2157504067","https://openalex.org/W2787259794","https://openalex.org/W3193477162","https://openalex.org/W4205326910","https://openalex.org/W4211049957","https://openalex.org/W4214717370","https://openalex.org/W4242606736","https://openalex.org/W4285719527","https://openalex.org/W6676174466","https://openalex.org/W6679859942","https://openalex.org/W7066478640"],"related_works":["https://openalex.org/W4255265352","https://openalex.org/W4239477580","https://openalex.org/W4389475841","https://openalex.org/W2152670157","https://openalex.org/W2903299703","https://openalex.org/W4281791088","https://openalex.org/W2117282672","https://openalex.org/W4385342861","https://openalex.org/W1574958246","https://openalex.org/W2807018115"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3],"approximate":[4],"policy":[5,109,157],"iteration":[6,110],"algorithm":[7,26,54,101,122,153],"for":[8,16,62],"solving":[9],"infinite-horizon,":[10],"discounted":[11],"Markov":[12],"decision":[13],"processes":[14],"(MDPs)":[15],"which":[17,63],"a":[18,71,145,155],"model":[19],"of":[20,73,114,128],"the":[21,47,53,64,90,96,112,116,121,126,138,152],"system":[22],"is":[23,27,55],"available.":[24],"The":[25],"similar":[28],"in":[29,111],"spirit":[30],"to":[31,57,105,107],"Bellman":[32,65,85,91],"residual":[33,86],"minimization":[34],"methods.":[35],"However,":[36],"by":[37],"using":[38],"Gaussian":[39],"process":[40],"regression":[41],"with":[42],"nondegenerate":[43],"kernel":[44,131],"functions":[45],"as":[46],"underlying":[48],"cost-to-go":[49,60,140],"function":[50],"approximation":[51],"architecture,":[52],"able":[56],"explicitly":[58],"construct":[59],"solutions":[61],"residuals":[66,92],"are":[67,93],"identically":[68],"zero":[69,94],"at":[70,95],"set":[72],"chosen":[74],"sample":[75,97],"states.":[76],"For":[77],"this":[78],"reason,":[79],"we":[80],"have":[81],"named":[82],"our":[83,99],"approach":[84],"elimination":[87],"(BRE).":[88],"Since":[89],"states,":[98],"BRE":[100],"can":[102,123],"be":[103],"proven":[104],"reduce":[106],"exact":[108],"limit":[113],"sampling":[115],"entire":[117],"state":[118],"space.":[119],"Furthermore,":[120],"automatically":[124],"optimize":[125],"choice":[127],"any":[129],"free":[130],"parameters":[132],"and":[133,158],"provide":[134],"error":[135],"bounds":[136],"on":[137,144],"resulting":[139],"solution.":[141],"Computational":[142],"results":[143],"classic":[146],"reinforcement":[147],"learning":[148],"problem":[149],"indicate":[150],"that":[151],"yields":[154],"high-quality":[156],"cost":[159],"approximation.":[160]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}