{"id":"https://openalex.org/W1979586407","doi":"https://doi.org/10.1109/acc.2009.5160511","title":"Robust adaptive Markov Decision Processes in multi-vehicle applications","display_name":"Robust adaptive Markov Decision Processes in multi-vehicle applications","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W1979586407","doi":"https://doi.org/10.1109/acc.2009.5160511","mag":"1979586407"},"language":"en","primary_location":{"id":"doi:10.1109/acc.2009.5160511","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2009.5160511","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/1721.1/58886","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065742112","display_name":"Luca F. Bertuccelli","orcid":null},"institutions":[{"id":"https://openalex.org/I4210157567","display_name":"Aerospace Testing (United States)","ror":"https://ror.org/04j7z5d67","country_code":"US","type":"company","lineage":["https://openalex.org/I4210157567"]},{"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":"Luca F. Bertuccelli","raw_affiliation_strings":["Aerospace Controls Laboratory, Massachusetts Institute of Technology, USA","[AeroSpace Controls Laboratory, Massachusetts Institute of Technology, USA]"],"affiliations":[{"raw_affiliation_string":"Aerospace Controls Laboratory, Massachusetts Institute of Technology, USA","institution_ids":["https://openalex.org/I4210157567","https://openalex.org/I63966007"]},{"raw_affiliation_string":"[AeroSpace Controls Laboratory, Massachusetts Institute of Technology, USA]","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111637722","display_name":"Brett Bethke","orcid":null},"institutions":[{"id":"https://openalex.org/I4210157567","display_name":"Aerospace Testing (United States)","ror":"https://ror.org/04j7z5d67","country_code":"US","type":"company","lineage":["https://openalex.org/I4210157567"]},{"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":"Brett Bethke","raw_affiliation_strings":["Aerospace Controls Laboratory, Massachusetts Institute of Technology, USA","[AeroSpace Controls Laboratory, Massachusetts Institute of Technology, USA]"],"affiliations":[{"raw_affiliation_string":"Aerospace Controls Laboratory, Massachusetts Institute of Technology, USA","institution_ids":["https://openalex.org/I4210157567","https://openalex.org/I63966007"]},{"raw_affiliation_string":"[AeroSpace Controls Laboratory, 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/I4210157567","display_name":"Aerospace Testing (United States)","ror":"https://ror.org/04j7z5d67","country_code":"US","type":"company","lineage":["https://openalex.org/I4210157567"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan P. How","raw_affiliation_strings":["Aerospace Controls Laboratory, Massachusetts Institute of Technology, USA","[AeroSpace Controls Laboratory, Massachusetts Institute of Technology, USA]"],"affiliations":[{"raw_affiliation_string":"Aerospace Controls Laboratory, Massachusetts Institute of Technology, USA","institution_ids":["https://openalex.org/I4210157567","https://openalex.org/I63966007"]},{"raw_affiliation_string":"[AeroSpace Controls Laboratory, Massachusetts Institute of Technology, USA]","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5065742112"],"corresponding_institution_ids":["https://openalex.org/I4210157567","https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.9033,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.79696887,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"ac 27","issue":null,"first_page":"1304","last_page":"1309"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9776999950408936,"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":0.9776999950408936,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9754999876022339,"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"}},{"id":"https://openalex.org/T10933","display_name":"Real-Time Systems Scheduling","score":0.9664999842643738,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/markov-decision-process","display_name":"Markov decision process","score":0.7889974117279053},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.756155252456665},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6948128938674927},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.595770001411438},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5732027292251587},{"id":"https://openalex.org/keywords/transient","display_name":"Transient (computer programming)","score":0.5654308795928955},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5350919961929321},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4737958312034607},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.414737731218338},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2551353871822357},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09734556078910828}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7889974117279053},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.756155252456665},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6948128938674927},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.595770001411438},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5732027292251587},{"id":"https://openalex.org/C2780799671","wikidata":"https://www.wikidata.org/wiki/Q17087362","display_name":"Transient (computer programming)","level":2,"score":0.5654308795928955},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5350919961929321},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4737958312034607},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.414737731218338},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2551353871822357},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09734556078910828},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/acc.2009.5160511","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2009.5160511","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:dspace.mit.edu:1721.1/58886","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/58886","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:1721.1/58906","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/58906","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:1721.1/58886","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/58886","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":[{"display_name":"Peace, Justice and strong institutions","score":0.800000011920929,"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/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":30,"referenced_works":["https://openalex.org/W20510943","https://openalex.org/W1515851193","https://openalex.org/W1526144783","https://openalex.org/W1577863597","https://openalex.org/W1965878388","https://openalex.org/W2009533501","https://openalex.org/W2036931518","https://openalex.org/W2067603665","https://openalex.org/W2069045459","https://openalex.org/W2078618768","https://openalex.org/W2099724000","https://openalex.org/W2100321578","https://openalex.org/W2108692343","https://openalex.org/W2118219918","https://openalex.org/W2119567691","https://openalex.org/W2141154005","https://openalex.org/W2142500134","https://openalex.org/W2149446687","https://openalex.org/W2149670996","https://openalex.org/W2162527779","https://openalex.org/W2166529145","https://openalex.org/W2167960247","https://openalex.org/W2168565265","https://openalex.org/W2175937483","https://openalex.org/W2623785075","https://openalex.org/W4298023569","https://openalex.org/W6600816730","https://openalex.org/W6631529720","https://openalex.org/W6674894272","https://openalex.org/W6678008115"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W2379651310","https://openalex.org/W2113019827","https://openalex.org/W1541249122","https://openalex.org/W2413828414","https://openalex.org/W2367222340","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532"],"abstract_inverted_index":{"This":[0,80],"paper":[1],"presents":[2],"a":[3,91,113],"new":[4,64],"robust":[5,81],"and":[6,82,98,127,131,141],"adaptive":[7,83],"framework":[8,84,122],"for":[9,15,47],"Markov":[10],"decision":[11],"processes":[12],"that":[13,66],"accounts":[14],"errors":[16],"in":[17,34,77,109,125,137],"the":[18,35,41,57,68,72,86,95,104,110,138],"transition":[19,118],"probabilities.":[20],"Robust":[21],"policies":[22],"are":[23,44],"typically":[24],"found":[25],"off-line,":[26],"but":[27,50],"can":[28],"be":[29],"extremely":[30],"conservative":[31],"when":[32],"implemented":[33],"real":[36],"system.":[37],"Adaptive":[38],"policies,":[39],"on":[40],"other":[42],"hand,":[43],"specifically":[45],"suited":[46],"on-line":[48],"implementation,":[49],"may":[51],"display":[52],"undesirable":[53],"transient":[54,135],"performance":[55,93],"as":[56],"model":[58,96],"is":[59,75,99,123],"updated":[60],"though":[61],"learning.":[62],"A":[63],"method":[65],"exploits":[67],"individual":[69],"strengths":[70],"of":[71,112,116],"two":[73],"approaches":[74],"presented":[76],"this":[78],"paper.":[79],"protects":[85],"adaptation":[87,139],"process":[88,140],"from":[89],"exhibiting":[90],"worst-case":[92],"during":[94],"updating,":[97],"shown":[100,132],"to":[101,103,133],"converge":[102],"true,":[105],"optimal":[106],"value":[107],"function":[108],"limit":[111],"large":[114],"number":[115],"state":[117],"observations.":[119],"The":[120],"proposed":[121],"investigated":[124],"simulation":[126],"actual":[128],"flight":[129],"experiments,":[130],"improve":[134],"behavior":[136],"overall":[142],"mission":[143],"performance.":[144]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}