{"id":"https://openalex.org/W2004229888","doi":"https://doi.org/10.1109/acc.2012.6314997","title":"Model estimation within planning and learning","display_name":"Model estimation within planning and learning","publication_year":2012,"publication_date":"2012-06-01","ids":{"openalex":"https://openalex.org/W2004229888","doi":"https://doi.org/10.1109/acc.2012.6314997","mag":"2004229888"},"language":"en","primary_location":{"id":"doi:10.1109/acc.2012.6314997","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2012.6314997","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 American Control Conference (ACC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1721.1/82023","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059864597","display_name":"Alborz Geramifard","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":"Alborz Geramifard","raw_affiliation_strings":["Robust Robotics Group, AeroSpace Controls Laboratory, MIT, Cambridge, MA, USA","Aerospace Controls Laboratory, MIT Cambridge, MA 02139 USA"],"affiliations":[{"raw_affiliation_string":"Robust Robotics Group, AeroSpace Controls Laboratory, MIT, Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"Aerospace Controls Laboratory, MIT Cambridge, MA 02139 USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029154307","display_name":"Joshua Redding","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107838","display_name":"Robust Chip (United States)","ror":"https://ror.org/01rp86637","country_code":"US","type":"company","lineage":["https://openalex.org/I4210107838"]},{"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":"J. D. Redding","raw_affiliation_strings":["Robust Robotics Group, MIT, Cambridge, MA, USA","Aerospace Controls Laboratory, MIT Cambridge, MA 02139 USA"],"affiliations":[{"raw_affiliation_string":"Robust Robotics Group, MIT, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210107838"]},{"raw_affiliation_string":"Aerospace Controls Laboratory, MIT Cambridge, MA 02139 USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102842112","display_name":"James Joseph","orcid":"https://orcid.org/0000-0001-6270-2559"},"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":"J. Joseph","raw_affiliation_strings":["AeroSpace Controls Laboratory, MIT, Cambridge, MA, USA","Robust Robotics Group, MIT Cambridge, MA 02139 USA"],"affiliations":[{"raw_affiliation_string":"AeroSpace Controls Laboratory, MIT, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210157567"]},{"raw_affiliation_string":"Robust Robotics Group, MIT Cambridge, MA 02139 USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103263485","display_name":"Nicholas Roy","orcid":"https://orcid.org/0000-0001-9307-4196"},"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":"N. Roy","raw_affiliation_strings":["AeroSpace Controls Laboratory, MIT, Cambridge, MA, USA","Robust Robotics Group, MIT Cambridge, MA 02139 USA"],"affiliations":[{"raw_affiliation_string":"AeroSpace Controls Laboratory, MIT, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210157567"]},{"raw_affiliation_string":"Robust Robotics Group, MIT Cambridge, MA 02139 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/I4210107838","display_name":"Robust Chip (United States)","ror":"https://ror.org/01rp86637","country_code":"US","type":"company","lineage":["https://openalex.org/I4210107838"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. P. How","raw_affiliation_strings":["Robust Robotics Group, MIT, Cambridge, MA, USA","Aerospace Controls Laboratory, MIT Cambridge, MA 02139 USA"],"affiliations":[{"raw_affiliation_string":"Robust Robotics Group, MIT, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210107838"]},{"raw_affiliation_string":"Aerospace Controls Laboratory, MIT Cambridge, MA 02139 USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5059864597"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":2.2106,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.88461296,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"793","last_page":"799"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.9922000169754028,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.8538309931755066},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7392328977584839},{"id":"https://openalex.org/keywords/constructive","display_name":"Constructive","score":0.7344790101051331},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.6236802339553833},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.544479489326477},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.5213305354118347},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5181959271430969},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4911503493785858},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.43505164980888367},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3981872797012329}],"concepts":[{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.8538309931755066},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7392328977584839},{"id":"https://openalex.org/C2778701210","wikidata":"https://www.wikidata.org/wiki/Q28130034","display_name":"Constructive","level":3,"score":0.7344790101051331},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6236802339553833},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.544479489326477},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.5213305354118347},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5181959271430969},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4911503493785858},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.43505164980888367},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3981872797012329},{"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/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/acc.2012.6314997","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2012.6314997","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 American Control Conference (ACC)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.353.5949","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.353.5949","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/~wingated/www/icml2011_workshop/main.pdf","raw_type":"text"},{"id":"pmh:oai:dspace.mit.edu:1721.1/82023","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/82023","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-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"MIT web domain","raw_type":"http://purl.org/eprint/type/ConferencePaper"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/82023","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/82023","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-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"MIT web domain","raw_type":"http://purl.org/eprint/type/ConferencePaper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","score":0.4000000059604645,"display_name":"Partnerships for the goals"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332467","display_name":"U.S. Air Force","ror":"https://ror.org/006gmme17"},{"id":"https://openalex.org/F4320335640","display_name":"Institute of Chemistry, Chinese Academy of Sciences","ror":null},{"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":26,"referenced_works":["https://openalex.org/W649108059","https://openalex.org/W1505937442","https://openalex.org/W1516698920","https://openalex.org/W2028145673","https://openalex.org/W2036507610","https://openalex.org/W2100677568","https://openalex.org/W2102585303","https://openalex.org/W2107105626","https://openalex.org/W2113873863","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2122410182","https://openalex.org/W2136462844","https://openalex.org/W2142544818","https://openalex.org/W2151661095","https://openalex.org/W2168003214","https://openalex.org/W2168024904","https://openalex.org/W2168359464","https://openalex.org/W2296687165","https://openalex.org/W2314097980","https://openalex.org/W2800222226","https://openalex.org/W3041202696","https://openalex.org/W3139377883","https://openalex.org/W4214717370","https://openalex.org/W4285719527","https://openalex.org/W6675731943"],"related_works":["https://openalex.org/W2051058708","https://openalex.org/W154868527","https://openalex.org/W1494268238","https://openalex.org/W1983207144","https://openalex.org/W2490706771","https://openalex.org/W2480116122","https://openalex.org/W1976468483","https://openalex.org/W1516574938","https://openalex.org/W804484174","https://openalex.org/W1568779110"],"abstract_inverted_index":{"Risk":[0],"and":[1,26,42,75,94,98,118,127],"reward":[2],"are":[3],"fundamental":[4],"concepts":[5],"in":[6,122],"the":[7,31,44,55,62,67,84,91,107,149,158],"cooperative":[8,24,57,92],"control":[9,58],"of":[10,46,54,69,109],"unmanned":[11],"systems.":[12],"In":[13],"this":[14],"research,":[15],"we":[16,138],"focus":[17],"on":[18,66],"developing":[19],"a":[20,70,115,128],"constructive":[21],"relationship":[22],"between":[23],"planning":[25,131],"learning":[27,32,120],"algorithms":[28],"to":[29,100,142,145],"mitigate":[30],"risk,":[33],"while":[34],"boosting":[35],"system":[36],"(planner":[37],"&":[38],"learner)":[39],"asymptotic":[40],"performance":[41],"guaranteeing":[43],"safety":[45],"agent":[47],"behavior.":[48],"Our":[49],"framework":[50],"is":[51],"an":[52,111,123],"instance":[53],"intelligent":[56],"architecture":[59],"(iCCA)":[60],"where":[61,148],"learner":[63],"incrementally":[64],"improves":[65],"output":[68],"baseline":[71],"planner":[72,93],"through":[73,157],"interaction":[74],"constrained":[76],"exploration.":[77],"We":[78,104],"extend":[79],"previous":[80],"work":[81],"by":[82],"extracting":[83],"embedded":[85],"parameterized":[86],"transition":[87],"model":[88,113,117,151],"from":[89],"within":[90],"making":[95],"it":[96],"adaptable":[97],"accessible":[99],"all":[101],"iCCA":[102],"modules.":[103],"empirically":[105],"demonstrate":[106],"advantage":[108],"using":[110],"adaptive":[112],"over":[114],"static":[116],"pure":[119],"approaches":[121],"example":[124],"GridWorld":[125],"problem":[126],"UAV":[129],"mission":[130],"scenario":[132],"with":[133],"200":[134],"million":[135],"possibilities.":[136],"Finally":[137],"discuss":[139],"two":[140],"extensions":[141],"our":[143],"approach":[144],"handle":[146],"cases":[147],"true":[150],"can":[152],"not":[153],"be":[154],"captured":[155],"exactly":[156],"presumed":[159],"functional":[160],"form.":[161]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}