{"id":"https://openalex.org/W1587009522","doi":"https://doi.org/10.1109/icra.2015.7139550","title":"Efficient reinforcement learning for robots using informative simulated priors","display_name":"Efficient reinforcement learning for robots using informative simulated priors","publication_year":2015,"publication_date":"2015-05-01","ids":{"openalex":"https://openalex.org/W1587009522","doi":"https://doi.org/10.1109/icra.2015.7139550","mag":"1587009522"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2015.7139550","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2015.7139550","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 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/1721.1/109303","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, 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, 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, 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, USA","institution_ids":["https://openalex.org/I4210143601","https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":9.7921,"has_fulltext":false,"cited_by_count":65,"citation_normalized_percentile":{"value":0.9794348,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2605","last_page":"2612"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","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/T12814","display_name":"Gaussian Processes and Bayesian Inference","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/T11236","display_name":"Control Systems and Identification","score":0.9984999895095825,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9983999729156494,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.740352988243103},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7344477772712708},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6823238730430603},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6603715419769287},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6589067578315735},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.6188074350357056},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.5411895513534546},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4846254289150238},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.44939759373664856},{"id":"https://openalex.org/keywords/black-box","display_name":"Black box","score":0.4352053999900818},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.41480207443237305},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.26440566778182983},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10009941458702087}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.740352988243103},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7344477772712708},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6823238730430603},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6603715419769287},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6589067578315735},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.6188074350357056},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.5411895513534546},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4846254289150238},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.44939759373664856},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.4352053999900818},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.41480207443237305},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.26440566778182983},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10009941458702087},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icra.2015.7139550","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2015.7139550","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/109303","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/109303","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:1721.1/109303","is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/109303","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":[{"score":0.8500000238418579,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G4808005909","display_name":null,"funder_award_id":"0645960","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6894402473","display_name":null,"funder_award_id":"Fellowship","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1511334422","https://openalex.org/W1526654727","https://openalex.org/W1540685400","https://openalex.org/W1746819321","https://openalex.org/W1949804828","https://openalex.org/W1967736575","https://openalex.org/W1977655452","https://openalex.org/W1998179438","https://openalex.org/W2018705428","https://openalex.org/W2042520683","https://openalex.org/W2104533781","https://openalex.org/W2117341272","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2130105540","https://openalex.org/W2131600418","https://openalex.org/W2132602063","https://openalex.org/W2133040789","https://openalex.org/W2139053308","https://openalex.org/W2140135625","https://openalex.org/W2162717641","https://openalex.org/W2179284380","https://openalex.org/W2292999476","https://openalex.org/W2334782222","https://openalex.org/W2403765497","https://openalex.org/W2787259794","https://openalex.org/W4211049957","https://openalex.org/W4214717370","https://openalex.org/W6629804754","https://openalex.org/W6631500254","https://openalex.org/W6632235069","https://openalex.org/W6640712829","https://openalex.org/W6655145722","https://openalex.org/W6675740164","https://openalex.org/W6679818365","https://openalex.org/W6680657880","https://openalex.org/W6685744914","https://openalex.org/W6712898688"],"related_works":["https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W2930863966","https://openalex.org/W4297873223","https://openalex.org/W3009457412","https://openalex.org/W2350784623","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W2126211886"],"abstract_inverted_index":{"Autonomous":[0],"learning":[1,21,37,60,162],"through":[2],"interaction":[3],"with":[4],"the":[5,29,45,49,56,59,110,122,131,137,146,153,157,161],"physical":[6],"world":[7],"is":[8,24,92,104],"a":[9,67,74,77,83,95,107],"promising":[10],"approach":[11],"to":[12,28,43,76],"designing":[13],"controllers":[14],"and":[15,125,149],"decision-making":[16],"policies":[17],"for":[18,35,70,85,109,113],"robots.":[19],"Unfortunately,":[20],"on":[22],"robots":[23],"often":[25],"difficult":[26],"due":[27],"large":[30],"number":[31],"of":[32,55,101,127,136,155],"samples":[33,46],"needed":[34,47],"many":[36],"algorithms.":[38],"Simulators":[39],"are":[40],"one":[41],"way":[42],"decrease":[44],"from":[48,73,94],"robot":[50],"by":[51,129,145],"incorporating":[52],"prior":[53,84,91,108,120,158],"knowledge":[54,159],"dynamics":[57],"into":[58],"algorithm.":[61,117],"In":[62],"this":[63,102],"paper":[64],"we":[65],"present":[66],"novel":[68],"method":[69],"transferring":[71],"data":[72,81],"simulator":[75],"robot,":[78],"using":[79,156],"simulated":[80,119],"as":[82,106],"real-world":[86],"learning.":[87],"A":[88],"Bayesian":[89],"nonparametric":[90],"learned":[93],"potentially":[96],"black-box":[97],"simulator.":[98],"The":[99,118],"mean":[100],"function":[103],"used":[105],"Probabilistic":[111],"Inference":[112],"Learning":[114],"Control":[115],"(PILCO)":[116],"improves":[121],"convergence":[123],"rate":[124],"performance":[126],"PILCO":[128],"directing":[130],"policy":[132],"search":[133],"in":[134,160],"areas":[135],"state-space":[138],"that":[139],"have":[140],"not":[141],"yet":[142],"been":[143],"observed":[144],"robot.":[147],"Simulated":[148],"hardware":[150],"results":[151],"show":[152],"benefits":[154],"framework.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":5}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}