{"id":"https://openalex.org/W2042520683","doi":"https://doi.org/10.1109/icra.2014.6907423","title":"Reinforcement learning with multi-fidelity simulators","display_name":"Reinforcement learning with multi-fidelity simulators","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2042520683","doi":"https://doi.org/10.1109/icra.2014.6907423","mag":"2042520683"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2014.6907423","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2014.6907423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1721.1/104936","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020653160","display_name":"Mark Cutler","orcid":"https://orcid.org/0000-0002-2823-3223"},"institutions":[{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]},{"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":"Mark Cutler","raw_affiliation_strings":["Laboratory of Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, USA","Laboratory of Information and Decision Systems, Massachusetts Institute of Technology, 77 Massachusetts Ave., Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Laboratory of Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Laboratory of Information and Decision Systems, Massachusetts Institute of Technology, 77 Massachusetts Ave., Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210143601","https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071800632","display_name":"Thomas J. Walsh","orcid":"https://orcid.org/0000-0002-4142-8711"},"institutions":[{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]},{"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":"Thomas J. Walsh","raw_affiliation_strings":["Laboratory of Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, USA","Laboratory of Information and Decision Systems, Massachusetts Institute of Technology, 77 Massachusetts Ave., Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Laboratory of Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Laboratory of Information and Decision Systems, Massachusetts Institute of Technology, 77 Massachusetts Ave., Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210143601","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/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan P. How","raw_affiliation_strings":["Laboratory of Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, USA","Laboratory of Information and Decision Systems, Massachusetts Institute of Technology, 77 Massachusetts Ave., Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Laboratory of Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Laboratory of Information and Decision Systems, Massachusetts Institute of Technology, 77 Massachusetts Ave., Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210143601","https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5020653160"],"corresponding_institution_ids":["https://openalex.org/I4210143601","https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":7.1885,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":{"value":0.96992712,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3888","last_page":"3895"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976000189781189,"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":0.9976000189781189,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.982699990272522,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9800999760627747,"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":0.8502700924873352},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7245574593544006},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5594373941421509},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.48749446868896484},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4323786497116089},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3152030110359192},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14199110865592957},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0843532383441925}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8502700924873352},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7245574593544006},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5594373941421509},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.48749446868896484},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4323786497116089},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3152030110359192},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14199110865592957},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0843532383441925},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icra.2014.6907423","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2014.6907423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.697.2015","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.697.2015","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.research.rutgers.edu/%7Ethomaswa/pub/icra2014Car.pdf","raw_type":"text"},{"id":"pmh:oai:dspace.mit.edu:1721.1/104936","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/104936","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:1721.1/104936","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/104936","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1509646629","https://openalex.org/W1515851193","https://openalex.org/W1983130966","https://openalex.org/W2049423956","https://openalex.org/W2051223050","https://openalex.org/W2056655632","https://openalex.org/W2070735679","https://openalex.org/W2089488098","https://openalex.org/W2095658148","https://openalex.org/W2124770562","https://openalex.org/W2132602063","https://openalex.org/W2133040789","https://openalex.org/W2159810454","https://openalex.org/W2169209873","https://openalex.org/W2292999476","https://openalex.org/W2403765497","https://openalex.org/W2488247662","https://openalex.org/W2963228851","https://openalex.org/W6630402033","https://openalex.org/W6679818365","https://openalex.org/W6680922781","https://openalex.org/W6685331716","https://openalex.org/W6712898688"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2381850946","https://openalex.org/W4380449851","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,9,86,110],"framework":[3,27],"for":[4,72,126],"reinforcement":[5],"learning":[6,24,140],"(RL)":[7],"in":[8,37],"scenario":[10],"where":[11],"multiple":[12,115],"simulators":[13],"are":[14,102,107],"available":[15],"with":[16,60,114,130],"decreasing":[17],"amounts":[18],"of":[19,34,79,89,97],"fidelity":[20],"to":[21,30,46,48,122],"the":[22,32,44,52,73,98,127],"real-world":[23,133],"scenario.":[25],"Our":[26],"is":[28,83],"designed":[29],"limit":[31],"number":[33],"samples":[35,134],"used":[36],"each":[38],"successively":[39],"higher-fidelity/cost":[40],"simulator":[41],"by":[42],"allowing":[43],"agent":[45],"choose":[47],"run":[49],"trajectories":[50],"at":[51],"lowest":[53],"level":[54],"that":[55],"will":[56],"still":[57],"provide":[58],"it":[59],"information.":[61],"The":[62,117],"approach":[63,118],"transfers":[64],"state-action":[65],"Q-values":[66],"from":[67],"lower-fidelity":[68],"models":[69],"as":[70],"heuristics":[71],"\u201cKnows":[74],"What":[75],"It":[76],"Knows\u201d":[77],"family":[78],"RL":[80,120],"algorithms,":[81],"which":[82],"applicable":[84],"over":[85],"wide":[87],"range":[88],"possible":[90],"dynamics":[91],"and":[92,104],"reward":[93],"representations.":[94],"Theoretical":[95],"proofs":[96],"framework's":[99],"sample":[100],"complexity":[101],"given":[103],"empirical":[105],"results":[106],"demonstrated":[108],"on":[109],"remote":[111],"controlled":[112],"car":[113],"simulators.":[116,142],"allows":[119],"algorithms":[121],"find":[123],"near-optimal":[124],"policies":[125],"real":[128],"world":[129],"fewer":[131],"expensive":[132],"than":[135],"previous":[136],"transfer":[137],"approaches":[138],"or":[139],"without":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":5}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}