{"id":"https://openalex.org/W2002428251","doi":"https://doi.org/10.1109/icra.2013.6630686","title":"Reinforcement learning with misspecified model classes","display_name":"Reinforcement learning with misspecified model classes","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2002428251","doi":"https://doi.org/10.1109/icra.2013.6630686","mag":"2002428251"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2013.6630686","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2013.6630686","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/1721.1/96945","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008206154","display_name":"Joshua Joseph","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":"Joshua Joseph","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA","Massachusetts Institute of Technology; ,; Cambridge MA USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute of Technology; ,; Cambridge MA USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","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":false,"raw_author_name":"Alborz Geramifard","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA","Massachusetts Institute of Technology; ,; Cambridge MA USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute of Technology; ,; Cambridge MA USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000226143","display_name":"John W. Roberts","orcid":"https://orcid.org/0000-0002-0870-952X"},"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":"John W. Roberts","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA","Massachusetts Institute of Technology; ,; Cambridge MA USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute of Technology; ,; Cambridge MA USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","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":["Massachusetts Institute of Technology, Cambridge, MA, USA","Massachusetts Institute of Technology; ,; Cambridge MA USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute of Technology; ,; Cambridge MA USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004980809","display_name":"Nicholas Roy","orcid":"https://orcid.org/0000-0002-4277-2928"},"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":"Nicholas Roy","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA","Massachusetts Institute of Technology; ,; Cambridge MA USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute of Technology; ,; Cambridge MA USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5008206154"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":2.9663,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.9146984,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"939","last_page":"946"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9919000267982483,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7715753316879272},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7472843527793884},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6885848045349121},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6701611280441284},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5717262029647827},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5567721724510193},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.548335075378418},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5196586847305298},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5147616863250732},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4939778447151184},{"id":"https://openalex.org/keywords/model-selection","display_name":"Model selection","score":0.47156497836112976},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21441805362701416},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1751214861869812}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7715753316879272},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7472843527793884},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6885848045349121},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6701611280441284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5717262029647827},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5567721724510193},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.548335075378418},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5196586847305298},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5147616863250732},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4939778447151184},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.47156497836112976},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21441805362701416},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1751214861869812},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icra.2013.6630686","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2013.6630686","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:dspace.mit.edu:1721.1/96945","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/96945","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:1721.1/96945","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/96945","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W165060581","https://openalex.org/W1481051778","https://openalex.org/W1575130825","https://openalex.org/W1590243462","https://openalex.org/W1619551699","https://openalex.org/W1758031947","https://openalex.org/W1936364850","https://openalex.org/W1966312294","https://openalex.org/W2017137572","https://openalex.org/W2091565802","https://openalex.org/W2095779990","https://openalex.org/W2097575529","https://openalex.org/W2100469802","https://openalex.org/W2101307636","https://openalex.org/W2107726111","https://openalex.org/W2110486110","https://openalex.org/W2113913482","https://openalex.org/W2118318536","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2123979492","https://openalex.org/W2126217565","https://openalex.org/W2129442128","https://openalex.org/W2134461419","https://openalex.org/W2139174822","https://openalex.org/W2140135625","https://openalex.org/W2141514599","https://openalex.org/W2145680191","https://openalex.org/W2155027007","https://openalex.org/W2164056559","https://openalex.org/W2169209873","https://openalex.org/W2200611301","https://openalex.org/W2591436094","https://openalex.org/W2798766386","https://openalex.org/W3103182070","https://openalex.org/W3139377883","https://openalex.org/W3143922204","https://openalex.org/W4214717370","https://openalex.org/W4230563027","https://openalex.org/W4237733001","https://openalex.org/W4242606736","https://openalex.org/W4246784033","https://openalex.org/W4254313632","https://openalex.org/W4285719527","https://openalex.org/W6602901451","https://openalex.org/W6606800287","https://openalex.org/W6635158312","https://openalex.org/W6638058698","https://openalex.org/W6640607047","https://openalex.org/W6674428451","https://openalex.org/W6675007360","https://openalex.org/W6676007687","https://openalex.org/W6676335607","https://openalex.org/W6677834374","https://openalex.org/W6678315428","https://openalex.org/W6680195895","https://openalex.org/W6680569831","https://openalex.org/W6680657880","https://openalex.org/W6682093400","https://openalex.org/W6683204974","https://openalex.org/W6684199269","https://openalex.org/W6687901895","https://openalex.org/W6786397483"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W1482441085","https://openalex.org/W2966858528","https://openalex.org/W2151687600"],"abstract_inverted_index":{"Real-world":[0],"robots":[1],"commonly":[2],"have":[3],"to":[4,32,63,69,77,116,168,185],"act":[5],"in":[6,55,190],"complex,":[7],"poorly":[8],"understood":[9],"environments":[10],"where":[11],"the":[12,21,58,65,87,109,117,128,138,142,148,158,163,186,206],"true":[13,66],"world":[14,23],"dynamics":[15,213],"are":[16],"unknown.":[17],"To":[18],"compensate":[19],"for":[20,156,195],"unknown":[22],"dynamics,":[24,67],"we":[25,85,177],"often":[26,183],"provide":[27],"a":[28,33,39,43,49,75,79,191,202,209],"class":[29,60,89,165],"of":[30,51,95],"models":[31],"learner":[34,189],"so":[35],"it":[36],"may":[37],"select":[38],"model,":[40],"typically":[41],"using":[42],"minimum":[44,112],"prediction":[45,113],"error":[46,114],"metric":[47,134],"over":[48],"set":[50],"training":[52],"data.":[53],"Often":[54],"real-world":[56,204],"domains":[57],"model":[59,88,110,132,139,161,164],"is":[61,97,106,166,182],"unable":[62],"capture":[64],"due":[68],"either":[70],"limited":[71],"domain":[72,210],"knowledge":[73],"or":[74],"desire":[76],"use":[78],"small":[80],"model.":[81,151],"In":[82,121],"these":[83],"cases":[84],"call":[86],"misspecified,":[90],"and":[91,103,174,201],"an":[92,154],"unfortunate":[93],"consequence":[94],"misspecification":[96],"that":[98,179],"even":[99],"with":[100,111],"unlimited":[101,172],"data":[102,173],"computation":[104],"there":[105],"no":[107],"guarantee":[108],"leads":[115],"best":[118],"performing":[119,160],"policy.":[120],"this":[122],"work,":[123],"our":[124,180],"approach":[125],"improves":[126],"upon":[127],"standard":[129],"maximum":[130,187],"likelihood":[131,188],"selection":[133],"by":[135],"explicitly":[136],"selecting":[137],"which":[140,157],"achieves":[141],"highest":[143,159],"expected":[144],"reward,":[145],"rather":[146],"than":[147],"most":[149],"likely":[150],"We":[152],"present":[153],"algorithm":[155,181],"from":[162],"guaranteed":[167],"be":[169,215],"found":[170],"given":[171],"computation.":[175],"Empirically,":[176],"demonstrate":[178],"superior":[184],"batch":[192],"learning":[193],"setting":[194],"two":[196],"common":[197],"RL":[198],"benchmark":[199],"problems":[200],"third":[203],"system,":[205],"hydrodynamic":[207],"cart-pole,":[208],"whose":[211],"complex":[212],"cannot":[214],"known":[216],"exactly.":[217]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":6},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}