{"id":"https://openalex.org/W2132602063","doi":"https://doi.org/10.1145/1143844.1143845","title":"Using inaccurate models in reinforcement learning","display_name":"Using inaccurate models in reinforcement learning","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2132602063","doi":"https://doi.org/10.1145/1143844.1143845","mag":"2132602063"},"language":"en","primary_location":{"id":"doi:10.1145/1143844.1143845","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1143844.1143845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international conference on Machine learning  - ICML '06","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049349154","display_name":"Pieter Abbeel","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pieter Abbeel","raw_affiliation_strings":["Stanford University, Stanford, CA","Stanford University Stanford CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University Stanford CA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013155801","display_name":"Morgan Quigley","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Morgan Quigley","raw_affiliation_strings":["Stanford University, Stanford, CA","Stanford University Stanford CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University Stanford CA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112456378","display_name":"Andrew Y. Ng","orcid":"https://orcid.org/0000-0001-5547-3196"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Y. Ng","raw_affiliation_strings":["Stanford University, Stanford, CA","Stanford University Stanford CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University Stanford CA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":216,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9962999820709229,"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":0.9869999885559082,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8800641298294067},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7611043453216553},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7533748745918274},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5947365164756775},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5714013576507568},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5371189117431641},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5268192291259766},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.455074667930603},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4264349639415741},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3972381055355072},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3055928945541382},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1303957998752594}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8800641298294067},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7611043453216553},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7533748745918274},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5947365164756775},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5714013576507568},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5371189117431641},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5268192291259766},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.455074667930603},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4264349639415741},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3972381055355072},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3055928945541382},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1303957998752594},{"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/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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1143844.1143845","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1143844.1143845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international conference on Machine learning  - ICML '06","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.75.559","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.75.559","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.robotics.stanford.edu/~ang/papers/icml06-usinginaccuratemodelsinrl.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.77.764","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.77.764","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.robotics.stanford.edu/~ang/papers/icml06-usinginaccuratemodelsinrl-long.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320333566","display_name":"National Defense Science and Engineering Graduate","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W177093312","https://openalex.org/W344488496","https://openalex.org/W658381347","https://openalex.org/W1495343868","https://openalex.org/W1515851193","https://openalex.org/W1522531528","https://openalex.org/W1540685400","https://openalex.org/W1544193923","https://openalex.org/W1576452626","https://openalex.org/W1597173708","https://openalex.org/W1965878388","https://openalex.org/W2037539475","https://openalex.org/W2098432798","https://openalex.org/W2111999018","https://openalex.org/W2121863487","https://openalex.org/W2137002893","https://openalex.org/W2153192722","https://openalex.org/W2167647761","https://openalex.org/W2168110243","https://openalex.org/W2917990073","https://openalex.org/W3195133498"],"related_works":["https://openalex.org/W1985560493","https://openalex.org/W2386410636","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W2808418668","https://openalex.org/W3096874164","https://openalex.org/W2357975469","https://openalex.org/W2937181779","https://openalex.org/W2145363145","https://openalex.org/W3168977894"],"abstract_inverted_index":{"In":[0,68],"the":[1,19,41,97,107,125,130,158],"model-based":[2],"policy":[3,45,98],"search":[4],"approach":[5],"to":[6,33,60,94,104,110],"reinforcement":[7],"learning":[8],"(RL),":[9],"policies":[10],"are":[11],"found":[12],"using":[13,100],"a":[14,44,73,84,142,146],"model":[15,109,131,144],"(or":[16],"\"simulator\")":[17],"of":[18,65,87,149],"Markov":[20],"decision":[21],"process.":[22],"However,":[23],"for":[24],"high-dimensional":[25],"continuous-state":[26],"tasks,":[27],"it":[28],"can":[29,153],"be":[30],"extremely":[31],"difficult":[32],"build":[34],"an":[35,79],"accurate":[36],"model,":[37,81],"and":[38,82,145],"thus":[39],"often":[40],"algorithm":[42,75,120,152],"returns":[43],"that":[46,76,118],"works":[47],"in":[48,52,124,157],"simulation":[49],"but":[50,103],"not":[51],"real-life.":[53],"The":[54,90],"other":[55],"extreme,":[56],"model-free":[57],"RL,":[58],"tends":[59],"require":[61],"infeasibly":[62],"large":[63],"numbers":[64],"real-life":[66,88,101,150],"trials.":[67,89],"this":[69,119],"paper,":[70],"we":[71],"present":[72],"hybrid":[74],"requires":[77],"only":[78,83,133,141],"approximate":[80,108],"small":[85,147],"number":[86,148],"key":[91],"idea":[92],"is":[93,132],"successively":[95],"\"ground\"":[96],"evaluations":[99],"trials,":[102],"rely":[105],"on":[106],"suggest":[111],"local":[112],"changes.":[113],"Our":[114],"theoretical":[115],"results":[116,136],"show":[117],"achieves":[121],"near-optimal":[122,155],"performance":[123,156],"real":[126,159],"system,":[127],"even":[128],"when":[129],"approximate.":[134],"Empirical":[135],"also":[137],"demonstrate":[138],"that---when":[139],"given":[140],"crude":[143],"trials---our":[151],"obtain":[154],"system.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":25},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":21},{"year":2018,"cited_by_count":17},{"year":2017,"cited_by_count":17},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}