{"id":"https://openalex.org/W2592857946","doi":"https://doi.org/10.1109/icra.2017.7989186","title":"Virtual vs. real: Trading off simulations and physical experiments in reinforcement learning with Bayesian optimization","display_name":"Virtual vs. real: Trading off simulations and physical experiments in reinforcement learning with Bayesian optimization","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2592857946","doi":"https://doi.org/10.1109/icra.2017.7989186","mag":"2592857946"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2017.7989186","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2017.7989186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1703.01250","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014762489","display_name":"Alonso Marco","orcid":"https://orcid.org/0000-0002-5764-6713"},"institutions":[{"id":"https://openalex.org/I4210135521","display_name":"Max Planck Institute for Intelligent Systems","ror":"https://ror.org/04fq9j139","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210135521"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alonso Marco","raw_affiliation_strings":["Max Planck ETH Center for Learning Systems, T\u00fcbingen, Switzerland","Max Planck Institute for Intelligent Systems, T\u00fcbingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck ETH Center for Learning Systems, T\u00fcbingen, Switzerland","institution_ids":[]},{"raw_affiliation_string":"Max Planck Institute for Intelligent Systems, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I4210135521"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023706410","display_name":"Felix Berkenkamp","orcid":"https://orcid.org/0000-0002-5179-6606"},"institutions":[{"id":"https://openalex.org/I2799323385","display_name":"Board of the Swiss Federal Institutes of Technology","ror":"https://ror.org/01rvn4p91","country_code":"CH","type":"government","lineage":["https://openalex.org/I2799323385"]},{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Felix Berkenkamp","raw_affiliation_strings":["Eidgenossische Technische Hochschule Zurich, Zurich, ZH, CH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eidgenossische Technische Hochschule Zurich, Zurich, ZH, CH","institution_ids":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022872779","display_name":"Philipp Hennig","orcid":"https://orcid.org/0000-0001-7293-6092"},"institutions":[{"id":"https://openalex.org/I4210135521","display_name":"Max Planck Institute for Intelligent Systems","ror":"https://ror.org/04fq9j139","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210135521"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Philipp Hennig","raw_affiliation_strings":["Max Planck ETH Center for Learning Systems, T\u00fcbingen, Switzerland","Max Planck Institute for Intelligent Systems, T\u00fcbingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck ETH Center for Learning Systems, T\u00fcbingen, Switzerland","institution_ids":[]},{"raw_affiliation_string":"Max Planck Institute for Intelligent Systems, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I4210135521"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052147335","display_name":"Angela P. Schoellig","orcid":"https://orcid.org/0000-0003-4012-4668"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Angela P. Schoellig","raw_affiliation_strings":["Dynamic Systems Lab (DSL), University of Toronto Institute for Aerospace Studies (UTIAS), Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dynamic Systems Lab (DSL), University of Toronto Institute for Aerospace Studies (UTIAS), Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003040843","display_name":"Andreas Krause","orcid":"https://orcid.org/0000-0001-7260-9673"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Andreas Krause","raw_affiliation_strings":["Learning & Adaptive Systems Group (LAS), ETH Zurich, Switzerland","Max Planck ETH Center for Learning Systems, T\u00fcbingen, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Learning & Adaptive Systems Group (LAS), ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"Max Planck ETH Center for Learning Systems, T\u00fcbingen, Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029642293","display_name":"Stefan Schaal","orcid":"https://orcid.org/0000-0001-5660-1874"},"institutions":[{"id":"https://openalex.org/I4210135521","display_name":"Max Planck Institute for Intelligent Systems","ror":"https://ror.org/04fq9j139","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210135521"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Schaal","raw_affiliation_strings":["Max-Planck-Institut fur Intelligente Systeme, Stuttgart, Baden-W\u00c3\u00bcrttemberg, DE","Max-Planck-Institut fur Intelligente Systeme, Stuttgart, Baden-W\u00fcrttemberg, DE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max-Planck-Institut fur Intelligente Systeme, Stuttgart, Baden-W\u00c3\u00bcrttemberg, DE","institution_ids":[]},{"raw_affiliation_string":"Max-Planck-Institut fur Intelligente Systeme, Stuttgart, Baden-W\u00fcrttemberg, DE","institution_ids":["https://openalex.org/I4210135521"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023990842","display_name":"Sebastian Trimpe","orcid":"https://orcid.org/0000-0002-2785-2487"},"institutions":[{"id":"https://openalex.org/I4210135521","display_name":"Max Planck Institute for Intelligent Systems","ror":"https://ror.org/04fq9j139","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210135521"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian Trimpe","raw_affiliation_strings":["Max Planck ETH Center for Learning Systems, T\u00fcbingen, Switzerland","Max Planck Institute for Intelligent Systems, T\u00fcbingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck ETH Center for Learning Systems, T\u00fcbingen, Switzerland","institution_ids":[]},{"raw_affiliation_string":"Max Planck Institute for Intelligent Systems, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I4210135521"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":115,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1557","last_page":"1563"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9994999766349792,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9970999956130981,"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/bayesian-optimization","display_name":"Bayesian optimization","score":0.8118332624435425},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7917098999023438},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7850581407546997},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5821372866630554},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5360636115074158},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5087307095527649},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.5033189654350281},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49875307083129883},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4833909571170807},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.46647530794143677}],"concepts":[{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.8118332624435425},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7917098999023438},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7850581407546997},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5821372866630554},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5360636115074158},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5087307095527649},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.5033189654350281},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49875307083129883},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4833909571170807},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.46647530794143677},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icra.2017.7989186","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2017.7989186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1703.01250","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1703.01250","pdf_url":"https://arxiv.org/pdf/1703.01250","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1703.01250","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1703.01250","pdf_url":"https://arxiv.org/pdf/1703.01250","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1512921589","display_name":null,"funder_award_id":"IIS-1205249","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1749632606","display_name":null,"funder_award_id":"RGPIN-2014","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G3927908034","display_name":"AIS:Learning Motor Skills from Trajectory-based Reinforcement Learning","funder_award_id":"0926052","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4227778692","display_name":null,"funder_award_id":"EECS-0926052","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5509073077","display_name":"RI:  Small:  Vision-Based Mobile Manipulation and Navigation","funder_award_id":"1017134","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5599649393","display_name":null,"funder_award_id":"200020","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6115495753","display_name":null,"funder_award_id":"IIS-1017134","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G628552264","display_name":null,"funder_award_id":"200020","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G8490259380","display_name":null,"funder_award_id":"RGPIN-2014-04634","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G8647679944","display_name":"Explore-exploit with Gaussian Processes under Complex Constraints","funder_award_id":"159557","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"},{"id":"https://openalex.org/F4320322434","display_name":"Max-Planck-Gesellschaft","ror":"https://ror.org/01hhn8329"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"},{"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":38,"referenced_works":["https://openalex.org/W1483202606","https://openalex.org/W1522531528","https://openalex.org/W1587009522","https://openalex.org/W1693986406","https://openalex.org/W1964710473","https://openalex.org/W1977046327","https://openalex.org/W1977655452","https://openalex.org/W1982886636","https://openalex.org/W2012758201","https://openalex.org/W2020732830","https://openalex.org/W2091568354","https://openalex.org/W2097381042","https://openalex.org/W2110029398","https://openalex.org/W2111241577","https://openalex.org/W2113145584","https://openalex.org/W2121863487","https://openalex.org/W2127107099","https://openalex.org/W2132602063","https://openalex.org/W2155927283","https://openalex.org/W2204090322","https://openalex.org/W2284548247","https://openalex.org/W2289490314","https://openalex.org/W2311870199","https://openalex.org/W2346505884","https://openalex.org/W2578799909","https://openalex.org/W2951665052","https://openalex.org/W3105904426","https://openalex.org/W3124229194","https://openalex.org/W4211049957","https://openalex.org/W4214717370","https://openalex.org/W4293275986","https://openalex.org/W4296278153","https://openalex.org/W6629021139","https://openalex.org/W6637591494","https://openalex.org/W6674600207","https://openalex.org/W6676544178","https://openalex.org/W6676817345","https://openalex.org/W6764988152"],"related_works":["https://openalex.org/W3106461837","https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4401858220","https://openalex.org/W2970690932","https://openalex.org/W2110715801"],"abstract_inverted_index":{"In":[0,37],"practice,":[1],"the":[2,78,111,121,136],"parameters":[3],"of":[4,80],"control":[5,126],"policies":[6,127],"are":[7,54],"often":[8,29],"tuned":[9],"manually.":[10],"This":[11],"is":[12,18,86],"time-consuming":[13],"and":[14,101],"frustrating.":[15],"Reinforcement":[16],"learning":[17],"a":[19,42,66,87,106,115],"promising":[20],"alternative":[21],"that":[22,70,120],"aims":[23],"to":[24,34,44,77,90,114],"automate":[25],"this":[26,38,45],"process,":[27],"yet":[28],"requires":[30],"too":[31],"many":[32],"experiments":[33,104,130],"be":[35],"practical.":[36],"paper,":[39],"we":[40,62],"propose":[41],"solution":[43],"problem":[46],"by":[47],"exploiting":[48],"prior":[49],"knowledge":[50],"from":[51,74,97],"simulations,":[52],"which":[53,118],"readily":[55],"available":[56],"for":[57],"most":[58],"robotic":[59],"platforms.":[60],"Specifically,":[61],"extend":[63],"Entropy":[64],"Search,":[65],"Bayesian":[67,133],"optimization":[68,134],"algorithm":[69,122],"maximizes":[71],"information":[72,82,96],"gain":[73],"each":[75],"experiment,":[76],"case":[79],"multiple":[81],"sources.":[83],"The":[84],"result":[85],"principled":[88],"way":[89],"automatically":[91],"combine":[92],"cheap,":[93],"but":[94],"inaccurate":[95],"simulations":[98],"with":[99,128],"expensive":[100],"accurate":[102],"physical":[103,137],"in":[105],"cost-effective":[107],"manner.":[108],"We":[109],"apply":[110],"resulting":[112],"method":[113],"cart-pole":[116],"system,":[117],"confirms":[119],"can":[123],"find":[124],"good":[125],"fewer":[129],"than":[131],"standard":[132],"on":[135],"system":[138],"only.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":18},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2017-03-16T00:00:00"}