{"id":"https://openalex.org/W1972336342","doi":"https://doi.org/10.1109/icra.2012.6225241","title":"Improving the efficiency of Bayesian inverse reinforcement learning","display_name":"Improving the efficiency of Bayesian inverse reinforcement learning","publication_year":2012,"publication_date":"2012-05-01","ids":{"openalex":"https://openalex.org/W1972336342","doi":"https://doi.org/10.1109/icra.2012.6225241","mag":"1972336342"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2012.6225241","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2012.6225241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Robotics and Automation","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1721.1/81489","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027275884","display_name":"Bernard Michini","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":"Bernard Michini","raw_affiliation_strings":["AeroSpace Controls Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA","Aerospace Controls Laboratory, Massachusetts Institute of Technology, Cambridge, 02139 USA"],"affiliations":[{"raw_affiliation_string":"AeroSpace Controls Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Aerospace Controls Laboratory, Massachusetts Institute of Technology, Cambridge, 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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan P. How","raw_affiliation_strings":["AeroSpace Controls Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA","Aerospace Controls Laboratory, Massachusetts Institute of Technology, Cambridge, 02139 USA"],"affiliations":[{"raw_affiliation_string":"AeroSpace Controls Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Aerospace Controls Laboratory, Massachusetts Institute of Technology, Cambridge, 02139 USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5027275884"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":2.2106,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.88231961,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"50","issue":null,"first_page":"3651","last_page":"3656"},"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9933000206947327,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.989300012588501,"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/computer-science","display_name":"Computer science","score":0.7053935527801514},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6700731515884399},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6502527594566345},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6498078107833862},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5832580327987671},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5595135688781738},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5553742051124573},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5484998822212219},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5347921252250671},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.5243780016899109},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43512898683547974},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.42790675163269043},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.42531082034111023},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4203304946422577},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.35233235359191895},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1516633927822113},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08934217691421509}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7053935527801514},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6700731515884399},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6502527594566345},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6498078107833862},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5832580327987671},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5595135688781738},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5553742051124573},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5484998822212219},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5347921252250671},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.5243780016899109},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43512898683547974},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.42790675163269043},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42531082034111023},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4203304946422577},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.35233235359191895},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1516633927822113},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08934217691421509},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icra.2012.6225241","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2012.6225241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Robotics and Automation","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.310.4398","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.310.4398","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.mit.edu/papers/michini-icra-2012.pdf","raw_type":"text"},{"id":"pmh:oai:dspace.mit.edu:1721.1/81489","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/81489","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:1721.1/81489","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/81489","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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7200000286102295}],"awards":[],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1560724230","https://openalex.org/W1591675293","https://openalex.org/W1986014385","https://openalex.org/W2061562262","https://openalex.org/W2098774185","https://openalex.org/W2109675615","https://openalex.org/W2113023245","https://openalex.org/W2116442740","https://openalex.org/W2121863487","https://openalex.org/W2126105931","https://openalex.org/W2135194391","https://openalex.org/W2156163138","https://openalex.org/W2169498096","https://openalex.org/W2262174858","https://openalex.org/W2950989964","https://openalex.org/W3195149063","https://openalex.org/W4214717370","https://openalex.org/W6635261211","https://openalex.org/W6674884181","https://openalex.org/W6676471219","https://openalex.org/W6676728370","https://openalex.org/W6677631742","https://openalex.org/W6729118241","https://openalex.org/W7075682605"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894"],"abstract_inverted_index":{"Inverse":[0],"reinforcement":[1],"learning":[2,8,46],"(IRL)":[3],"is":[4,97,113,160],"the":[5,9,21,49,52,57,80,94,100,115,130,136,140,149,153,171,175],"task":[6,117],"of":[7,12,20,27,44,108,174],"reward":[10,45,150],"function":[11,23,151],"a":[13,25,39,105],"Markov":[14],"Decision":[15],"Process":[16],"(MDP)":[17],"given":[18],"knowledge":[19],"transition":[22],"and":[24,41,89,99,162],"set":[26],"expert":[28,101,141],"demonstrations.":[29],"While":[30],"many":[31],"IRL":[32,36,83],"algorithms":[33],"exist,":[34],"Bayesian":[35,53,82],"[1]":[37],"provides":[38],"general":[40],"principled":[42],"method":[43],"by":[47,129],"casting":[48],"problem":[50,73],"in":[51,91],"inference":[54,116],"framework.":[55],"However,":[56],"algorithm":[58,84,159],"as":[59,132],"originally":[60],"presented":[61,161],"suffers":[62],"from":[63],"several":[64],"inefficiencies":[65],"that":[66,114,123,139],"prohibit":[67],"its":[68,87],"use":[69],"for":[70],"even":[71],"moderate":[72],"sizes.":[74],"This":[75],"paper":[76],"proposes":[77],"modifications":[78],"to":[79,85,126,134,146],"original":[81,176],"improve":[86],"efficiency":[88],"tractability":[90],"situations":[92],"where":[93],"state":[95,155],"space":[96],"large":[98],"demonstrations":[102,142],"span":[103],"only":[104],"small":[106],"portion":[107],"it.":[109],"The":[110],"key":[111],"insight":[112],"should":[118],"be":[119],"focused":[120],"on":[121],"states":[122],"are":[124],"similar":[125],"those":[127],"encountered":[128],"expert,":[131],"opposed":[133],"making":[135],"naive":[137],"assumption":[138],"contain":[143],"enough":[144],"information":[145],"accurately":[147],"infer":[148],"over":[152],"entire":[154],"space.":[156],"A":[157],"modified":[158],"experimental":[163],"results":[164],"show":[165],"substantially":[166],"faster":[167],"convergence":[168],"while":[169],"maintaining":[170],"solution":[172],"quality":[173],"method.":[177]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}