{"id":"https://openalex.org/W2008491003","doi":"https://doi.org/10.1109/icra.2013.6630592","title":"Scalable reward learning from demonstration","display_name":"Scalable reward learning from demonstration","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2008491003","doi":"https://doi.org/10.1109/icra.2013.6630592","mag":"2008491003"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2013.6630592","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2013.6630592","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 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/1721.1/96946","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"]},{"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":true,"raw_author_name":"Bernard Michini","raw_affiliation_strings":["Aerospace Controls Laboratory, Massachusetts Institute of Technology, USA","Aerosp. Controls Lab., Massachusetts Inst. of Technol., Cambridge, MA, 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":"Aerosp. Controls Lab., Massachusetts Inst. of Technol., Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020653160","display_name":"Mark Cutler","orcid":"https://orcid.org/0000-0002-2823-3223"},"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":"Mark Cutler","raw_affiliation_strings":["Aerospace Controls Laboratory, Massachusetts Institute of Technology, USA","Aerosp. Controls Lab., Massachusetts Inst. of Technol., Cambridge, MA, 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":"Aerosp. Controls Lab., Massachusetts Inst. of Technol., Cambridge, MA, 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","Aerosp. Controls Lab., Massachusetts Inst. of Technol., Cambridge, MA, 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":"Aerosp. Controls Lab., Massachusetts Inst. of Technol., Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027275884"],"corresponding_institution_ids":["https://openalex.org/I4210157567","https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":5.9309,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.95850925,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"5","issue":null,"first_page":"303","last_page":"308"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9896000027656555,"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"}},{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9850000143051147,"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/markov-decision-process","display_name":"Markov decision process","score":0.8675590753555298},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8396351337432861},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7614485621452332},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6084957122802734},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5974762439727783},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5927147269248962},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5680440068244934},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5413962602615356},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.49516358971595764},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4184314012527466},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.41505861282348633},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4129684567451477},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.27818021178245544},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12029701471328735},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07229089736938477}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8675590753555298},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8396351337432861},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7614485621452332},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6084957122802734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5974762439727783},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5927147269248962},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5680440068244934},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5413962602615356},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.49516358971595764},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4184314012527466},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.41505861282348633},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4129684567451477},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.27818021178245544},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12029701471328735},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07229089736938477},{"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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icra.2013.6630592","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2013.6630592","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Robotics and Automation","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.310.8915","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.310.8915","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-2013.pdf","raw_type":"text"},{"id":"pmh:oai:dspace.mit.edu:1721.1/96946","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/96946","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/JournalArticle"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/96946","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/96946","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/JournalArticle"},"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G4584167293","display_name":null,"funder_award_id":"N000140910625","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G4776870722","display_name":null,"funder_award_id":"unknown","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W52822972","https://openalex.org/W1546511338","https://openalex.org/W1551893515","https://openalex.org/W1591675293","https://openalex.org/W1986014385","https://openalex.org/W1997063559","https://openalex.org/W1999874108","https://openalex.org/W2009533501","https://openalex.org/W2020999234","https://openalex.org/W2061562262","https://openalex.org/W2080972498","https://openalex.org/W2091797506","https://openalex.org/W2098774185","https://openalex.org/W2113023245","https://openalex.org/W2116442740","https://openalex.org/W2121863487","https://openalex.org/W2138158112","https://openalex.org/W2151516755","https://openalex.org/W2169498096","https://openalex.org/W2950989964","https://openalex.org/W4214717370","https://openalex.org/W6602158427","https://openalex.org/W6635261211","https://openalex.org/W6674884181","https://openalex.org/W6676728370","https://openalex.org/W6677631742"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894","https://openalex.org/W2386410636","https://openalex.org/W3038962357"],"abstract_inverted_index":{"Reward":[0],"learning":[1,21,60],"from":[2],"demonstration":[3],"is":[4],"the":[5,9,24,41,76,85,88],"task":[6],"of":[7,13,43,65,75,87],"inferring":[8],"intents":[10],"or":[11,78],"goals":[12],"an":[14,66],"agent":[15],"demonstrating":[16],"a":[17,53],"task.":[18],"Inverse":[19],"reinforcement":[20,59],"methods":[22],"utilize":[23],"Markov":[25],"decision":[26],"process":[27],"(MDP)":[28],"framework":[29],"to":[30,52,91,93],"learn":[31,97],"rewards,":[32],"but":[33],"typically":[34],"scale":[35,92],"poorly":[36],"since":[37],"they":[38],"rely":[39],"on":[40],"calculation":[42,64],"optimal":[44,67],"value":[45,68],"functions.":[46],"Several":[47],"key":[48],"modifications":[49],"are":[50],"made":[51],"previously":[54],"developed":[55],"Bayesian":[56],"nonparametric":[57],"inverse":[58],"algorithm":[61,90],"that":[62],"avoid":[63],"function":[69],"and":[70,96],"no":[71],"longer":[72],"require":[73],"discretization":[74],"state":[77],"action":[79],"spaces.":[80],"Experimental":[81],"results":[82],"given":[83],"demonstrate":[84],"ability":[86],"resulting":[89],"larger":[94],"problems":[95],"in":[98],"domains":[99],"with":[100],"continuous":[101],"demonstrations.":[102]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":5},{"year":2014,"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"}